From 5b1018434eb145b2d110fa40a901af0834decd66 Mon Sep 17 00:00:00 2001 From: CI Date: Mon, 3 Feb 2025 16:59:21 +0000 Subject: [PATCH] Build branch main with version main (861319f) Build pipeline: vsh-ci-template-8vdc6 Source commit: https://github.com/viash-hub/playground/commit/861319f5ddc22d51899493bcd30e7066c42193cb Source message: Merge pull request #4 from viash-hub/update-star-align-params update param --- README.md | 88 + README.qmd | 84 + nextflow.config | 22 +- src/mapping_and_qc/config.vsh.yaml | 5 +- src/mapping_and_qc/main.nf | 38 +- .../nextflow/cutadapt/.config.vsh.yaml | 54 +- .../{v0.1 => main}/nextflow/cutadapt/main.nf | 180 +- .../nextflow/cutadapt/nextflow.config | 3 +- .../nextflow/cutadapt/nextflow_schema.json | 108 +- .../nextflow/falco/.config.vsh.yaml | 32 +- .../{v0.1 => main}/nextflow/falco/main.nf | 127 +- .../nextflow/falco/nextflow.config | 3 +- .../nextflow/falco/nextflow_schema.json | 20 +- .../nextflow/multiqc/.config.vsh.yaml | 51 +- .../{v0.1 => main}/nextflow/multiqc/main.nf | 192 +- .../nextflow/multiqc/nextflow.config | 3 +- .../nextflow/multiqc/nextflow_schema.json | 62 +- .../samtools/samtools_stats/.config.vsh.yaml | 76 +- .../nextflow/samtools/samtools_stats/main.nf | 166 +- .../samtools/samtools_stats/nextflow.config | 3 +- .../samtools_stats/nextflow_schema.json | 74 +- .../star/star_align_reads/.config.vsh.yaml | 1287 ++++-- .../nextflow/star/star_align_reads/main.nf | 1702 ++++++-- .../star/star_align_reads/nextflow.config | 3 +- .../star_align_reads/nextflow_schema.json | 2314 ++++++++++ .../v0.1/nextflow/pear/.config.vsh.yaml | 406 -- .../vsh/vsh/biobox/v0.1/nextflow/pear/main.nf | 3821 ----------------- .../biobox/v0.1/nextflow/pear/nextflow.config | 125 - .../v0.1/nextflow/pear/nextflow_schema.json | 284 -- .../star_align_reads/nextflow_schema.json | 171 - .../nextflow/mapping_and_qc/.config.vsh.yaml | 30 +- target/nextflow/mapping_and_qc/main.nf | 71 +- .../mapping_and_qc/nextflow_schema.json | 2 +- test_data.sh | 17 +- 34 files changed, 5633 insertions(+), 5991 deletions(-) create mode 100644 README.md create mode 100644 README.qmd rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/cutadapt/.config.vsh.yaml (93%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/cutadapt/main.nf (96%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/cutadapt/nextflow.config (98%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/cutadapt/nextflow_schema.json (89%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/falco/.config.vsh.yaml (93%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/falco/main.nf (97%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/falco/nextflow.config (98%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/falco/nextflow_schema.json (95%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/multiqc/.config.vsh.yaml (93%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/multiqc/main.nf (97%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/multiqc/nextflow.config (98%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/multiqc/nextflow_schema.json (92%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/samtools/samtools_stats/.config.vsh.yaml (87%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/samtools/samtools_stats/main.nf (96%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/samtools/samtools_stats/nextflow.config (98%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/samtools/samtools_stats/nextflow_schema.json (81%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/star/star_align_reads/.config.vsh.yaml (63%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/star/star_align_reads/main.nf (71%) rename target/dependencies/vsh/vsh/biobox/{v0.1 => main}/nextflow/star/star_align_reads/nextflow.config (98%) create mode 100644 target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/nextflow_schema.json delete mode 100644 target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/.config.vsh.yaml delete mode 100644 target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/main.nf delete mode 100644 target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/nextflow.config delete mode 100644 target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/nextflow_schema.json delete mode 100644 target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/nextflow_schema.json diff --git a/README.md b/README.md new file mode 100644 index 0000000..d712ae9 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ + + +# πŸ›πŸ“¦ playground + +[![GitHub](https://img.shields.io/badge/GitHub-viash--hub%2Fplayground-blue.png)](https://github.com/viash-hub/playground) +[![Viash +version](https://img.shields.io/badge/Viash-v0.9.0--RC6-blue)](https://viash.io) + +A collection of bioinformatics pipelines to illustrate the use of biobox +(and biotools). + +## Quickstart + +### Requirements + +To run the components and workflows included in this repository, you +need to have the following software installed: + +- Bash (\>= 3.2) or an equivalent shell +- Java Development Kit (\>= 12) +- Docker +- Viash (\>= 0.6.7) +- Nextflow (\>= 21.04) + +### Cloning the repository + +To clone this repository to your local machine, copy the URL of the +forked repository by clicking the green β€œCode” button and selecting +HTTPS or SSH. In your terminal or command prompt, navigate to the +directory where you want to clone the repository and enter the following +command: + +``` bash +git clone playground +cd playground +``` + +### Test dataset + +You will also need to download the test resources by running the +following command. From the repository root, run: + +``` bash +./test_data.sh +``` + +This will create the `test_data` folder and a file called +`params_file.yaml`; the latter can be used to run the worklow with the +generated test data. + +### Building + +Before running the workflow, the viash components need to be build and +the docker images generated. + +``` bash +viash ns build --parallel --setup cachedbuild +``` + +> [!NOTE] +> +> The `--setup cachedbuild` enables building the docker images. + +You will now see a `target` folder inside the root of the repository. + +### Testing the workflow + +To use the workflow with test data, use the following command (from the +root of the repository): + +``` bash +nextflow run . -main-script ./target/nextflow/mapping_and_qc/main.nf \ +-params-file ./params_file.yaml \ +-profile docker \ +-c ./target/nextflow/mapping_and_qc/nextflow.config +``` + +The output will be written to the folder `test_run_output`, as specified +in the `publish_dir` argument in the `params_file.yaml`. + +## Support and Community + +For support, questions, or to join our community: + +- **Issues**: Submit questions or issues via the [GitHub issue + tracker](https://github.com/viash-hub/playground/issues). +- **Discussions**: Join our discussions via [GitHub + Discussions](https://github.com/viash-hub/playground/discussions). diff --git a/README.qmd b/README.qmd new file mode 100644 index 0000000..7731907 --- /dev/null +++ b/README.qmd @@ -0,0 +1,84 @@ +--- +format: gfm +--- +```{r setup, include=FALSE} +project <- yaml::read_yaml("_viash.yaml") +``` +# πŸ›πŸ“¦ `r project$name` + +[![GitHub](https://img.shields.io/badge/GitHub-viash--hub%2F`r project$name`-blue)](`r project$links$repository`) +[![Viash version](https://img.shields.io/badge/Viash-v`r gsub("-", "--", project$viash_version)`-blue)](https://viash.io) + +`r project$description` + +## Quickstart + +### Requirements + +To run the components and workflows included in this repository, you need to have the following software installed: + +* Bash (>= 3.2) or an equivalent shell +* Java Development Kit (>= 12) +* Docker +* Viash (>= 0.6.7) +* Nextflow (>= 21.04) + +### Cloning the repository +To clone this repository to your local machine, copy the URL of the forked repository by clicking the green "Code" button and selecting HTTPS or SSH. +In your terminal or command prompt, navigate to the directory where you want to clone the repository and enter the following command: + +```{bash} +#| eval: false +git clone playground +cd playground +``` + +### Test dataset + +You will also need to download the test resources by running the following command. +From the repository root, run: + +```{bash} +#| eval: false +./test_data.sh +``` + +This will create the `test_data` folder and a file called `params_file.yaml`; the latter can be +used to run the worklow with the generated test data. + +### Building + +Before running the workflow, the viash components need to be build and the docker images generated. + +```{bash} +#| eval: false +viash ns build --parallel --setup cachedbuild +``` + +::: {.callout-note} +The `--setup cachedbuild` enables building the docker images. +::: + +You will now see a `target` folder inside the root of the repository. + +### Testing the workflow + +To use the workflow with test data, use the following command (from the root of the repository): + +```{bash} +#| eval: false +nextflow run . -main-script ./target/nextflow/mapping_and_qc/main.nf \ +-params-file ./params_file.yaml \ +-profile docker \ +-c ./target/nextflow/mapping_and_qc/nextflow.config +``` + +The output will be written to the folder `test_run_output`, as specified in the `publish_dir` argument +in the `params_file.yaml`. + +## Support and Community + +For support, questions, or to join our community: + +- **Issues**: Submit questions or issues via the [GitHub issue tracker](`r project$links$issue_tracker`). +- **Discussions**: Join our discussions via [GitHub Discussions](`r project$links$repository`/discussions). \ No newline at end of file diff --git a/nextflow.config b/nextflow.config index f8bb790..9889b4d 100644 --- a/nextflow.config +++ b/nextflow.config @@ -1 +1,21 @@ -docker.fixOwnership = true \ No newline at end of file +process.container = "nextflow/nextflow:21.04.3" +docker { + enabled = true + fixOwnership = true +} + + +process { + memory = 1.GB + cpus = 1 + + withLabel: singlecpu { cpus = 1 } + withLabel: lowcpu { cpus = 4 } + withLabel: midcpu { cpus = 8 } + withLabel: highcpu { cpus = 10 } + + withLabel: lowmem { memory = 5.GB } + withLabel: midmem { memory = 8.GB } + withLabel: highmem { memory = 25.GB } +} + diff --git a/src/mapping_and_qc/config.vsh.yaml b/src/mapping_and_qc/config.vsh.yaml index 3105a0b..55e9975 100644 --- a/src/mapping_and_qc/config.vsh.yaml +++ b/src/mapping_and_qc/config.vsh.yaml @@ -31,8 +31,6 @@ resources: dependencies: - name: cutadapt repository: bb - - name: pear - repository: bb - name: falco repository: bb - name: multiqc @@ -46,8 +44,7 @@ repositories: - name: bb type: vsh repo: vsh/biobox - tag: v0.1 - + tag: main runners: - type: nextflow diff --git a/src/mapping_and_qc/main.nf b/src/mapping_and_qc/main.nf index fdeff20..cc765b4 100644 --- a/src/mapping_and_qc/main.nf +++ b/src/mapping_and_qc/main.nf @@ -17,14 +17,18 @@ workflow run_wf { }, toState: [ "output_falco": "outdir", - ] + ], + directives: [label: ["lowmem", "lowcpu"]] ) + | niceView() | cutadapt.run( fromState: {id, state -> [ "input": state.input_r1, "input_r2": state.input_r2, - "quality_cutoff": "20", // Could make this a parameter + "quality_cutoff": "30", // Could make this a parameter + "quality_cutoff_r2": "30", // Could make this a parameter + "minimum_length": "60:60", // Could make this a parameter "adapter": "CTGTCTCTTATACACATCT", // Could make this a parameter "adapter_r2": "CTGTCTCTTATACACATCT", // Could make this a parameter "output": "*.fastq", @@ -34,29 +38,23 @@ workflow run_wf { def newKeys = [ "trimmed_r1": output_state["output"][0], "trimmed_r2": output_state["output"][1], - "output_cutadapt": output_state["output"] ] def new_state = state + newKeys return new_state - } - ) - | pear.run( - fromState: [ - "forward_fastq": "trimmed_r1", - "reverse_fastq": "trimmed_r2", - ], - toState: [ - "output_pear": "assembled", - ] + }, + directives: [label: ["midmem", "midmem"]] ) | star_align_reads.run( fromState: [ - "input": "output_pear", - "genomeDir": "reference", + "input": "trimmed_r1", + "input_r2": "trimmed_r2", + "genome_dir": "reference", ], toState: [ "output_star": "aligned_reads", - ] + ], + directives: [label: ["highmem", "midcpu"]] + ) | samtools_stats.run( fromState: [ @@ -64,7 +62,9 @@ workflow run_wf { ], toState: [ "output_samtools_stats": "output", - ] + ], + directives: [label: ["midmem", "lowcpu"]] + ) | toSortedList() | map { events -> @@ -81,7 +81,9 @@ workflow run_wf { ], toState: [ "multiqc_output": "output_report", - ] + ], + directives: [label: ["midmem", "lowcpu"]] + ) | setState(["multiqc_output", "_meta"]) diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/.config.vsh.yaml b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/.config.vsh.yaml similarity index 93% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/.config.vsh.yaml rename to target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/.config.vsh.yaml index d26efaf..7cbe26a 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/.config.vsh.yaml +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/.config.vsh.yaml @@ -1,5 +1,18 @@ name: "cutadapt" -version: "v0.1.0" +version: "main" +authors: +- name: "Toni Verbeiren" + roles: + - "author" + - "maintainer" + info: + links: + github: "tverbeiren" + linkedin: "verbeiren" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist and CEO" argument_groups: - name: "Specify Adapters for R1" arguments: @@ -238,7 +251,7 @@ argument_groups: direction: "input" multiple: false multiple_sep: ";" - - type: "boolean_false" + - type: "boolean_true" name: "--no_indels" description: "Allow only mismatches in alignments.\n" info: null @@ -273,7 +286,7 @@ argument_groups: description: "Interpret IUPAC wildcards in reads.\n" info: null direction: "input" - - type: "boolean_false" + - type: "boolean_true" name: "--no_match_adapter_wildcards" description: "Do not interpret IUPAC wildcards in adapters.\n" info: null @@ -305,6 +318,26 @@ argument_groups: \ If match is on reverse-complemented version,\noutput that one.\n" info: null direction: "input" +- name: "Demultiplexing options" + arguments: + - type: "string" + name: "--demultiplex_mode" + description: "Enable demultiplexing and set the mode for it.\nWith mode 'unique_dual',\ + \ adapters from the first and second read are used,\nand the indexes from the\ + \ reads are only used in pairs. This implies\n--pair_adapters.\nEnabling mode\ + \ 'combinatorial_dual' allows all combinations of the sets of indexes\non R1\ + \ and R2. It is necessary to write each read pair to an output\nfile depending\ + \ on the adapters found on both R1 and R2.\nMode 'single', uses indexes or barcodes\ + \ located at the 5'\nend of the R1 read (single). \n" + info: null + required: false + choices: + - "single" + - "unique_dual" + - "combinatorial_dual" + direction: "input" + multiple: false + multiple_sep: ";" - name: "Read modifications" arguments: - type: "integer" @@ -685,7 +718,7 @@ engines: id: "docker" image: "python:3.12" target_registry: "images.viash-hub.com" - target_tag: "v0.1.0" + target_tag: "main" namespace_separator: "/" setup: - type: "python" @@ -706,22 +739,23 @@ build_info: engine: "docker|native" output: "target/nextflow/cutadapt" executable: "target/nextflow/cutadapt/main.nf" - viash_version: "0.9.0-RC6" - git_commit: "b84b29747d0635f2ac83ea63b496be9a9edb6724" - git_remote: "https://github.com/viash-hub/biobox" + viash_version: "0.9.0" + git_commit: "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b" + git_remote: "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox" + git_tag: "v0.2.0-27-g952ff08" package_config: name: "biobox" - version: "v0.1.0" + version: "main" description: "A collection of bioinformatics tools for working with sequence data.\n" info: null - viash_version: "0.9.0-RC6" + viash_version: "0.9.0" source: "src" target: "target" config_mods: - ".requirements.commands := ['ps']\n" - ".engines += { type: \"native\" }" - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'" - - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" + - ".engines[.type == 'docker'].target_tag := 'main'" keywords: - "bioinformatics" - "modules" diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/main.nf b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/main.nf similarity index 96% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/main.nf rename to target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/main.nf index 8956722..a7f02e1 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/main.nf +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/main.nf @@ -1,13 +1,16 @@ -// cutadapt v0.1.0 +// cutadapt main // -// This wrapper script is auto-generated by viash 0.9.0-RC6 and is thus a -// derivative work thereof. This software comes with ABSOLUTELY NO WARRANTY from -// Data Intuitive. +// This wrapper script is auto-generated by viash 0.9.0 and is thus a derivative +// work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data +// Intuitive. // // The component may contain files which fall under a different license. The // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Toni Verbeiren (author, maintainer) //////////////////////////// // VDSL3 helper functions // @@ -760,8 +763,11 @@ def runEach(Map args) { def fromState_ = args.fromState def toState_ = args.toState def filter_ = args.filter + def runIf_ = args.runIf def id_ = args.id + assert !runIf_ || runIf_ instanceof Closure: "runEach: must pass a Closure to runIf." + workflow runEachWf { take: input_ch main: @@ -783,7 +789,20 @@ def runEach(Map args) { [new_id] + tup.drop(1) } : filter_ch - def data_ch = id_ch | map{tup -> + def chPassthrough = null + def chRun = null + if (runIf_) { + def idRunIfBranch = id_ch.branch{ tup -> + run: runIf_(tup[0], tup[1], comp_) + passthrough: true + } + chPassthrough = idRunIfBranch.passthrough + chRun = idRunIfBranch.run + } else { + chRun = id_ch + chPassthrough = Channel.empty() + } + def data_ch = chRun | map{tup -> def new_data = tup[1] if (fromState_ instanceof Map) { new_data = fromState_.collectEntries{ key0, key1 -> @@ -821,8 +840,11 @@ def runEach(Map args) { [tup[0], new_state] + tup.drop(3) } : out_ch + + def return_ch = post_ch + | concat(chPassthrough) - post_ch + return_ch } // mix all results @@ -1598,8 +1620,8 @@ def findStates(Map params, Map config) { // construct renameMap if (args.rename_keys) { def renameMap = args.rename_keys.collectEntries{renameString -> - def split = renameString.split(";") - assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey,newKey:oldKey'" + def split = renameString.split(":") + assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey', or 'newKey:oldKey;newKey:oldKey' in case of multiple values" split } @@ -1709,7 +1731,9 @@ def publishStates(Map args) { def yamlFilename = yamlTemplate_ .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) // TODO: do the pathnames in state_ match up with the outputFilenames_? @@ -1780,7 +1804,9 @@ def publishStatesByConfig(Map args) { def yamlTemplate = params.containsKey("output_state") ? params.output_state : '$id.$key.state.yaml' def yamlFilename = yamlTemplate .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) def yamlDir = java.nio.file.Paths.get(yamlFilename).getParent() // the processed state is a list of [key, value, inputPath, outputFilename] tuples, where @@ -1822,7 +1848,9 @@ def publishStatesByConfig(Map args) { // instantiate the template def filename = filenameTemplate .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) if (par.multiple) { // if the parameter is multiple: true, the filename // should contain a wildcard '*' that is replaced with @@ -2626,30 +2654,31 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { tuple } - def chModifiedFiltered = workflowArgs.filter ? - chModified | filter{workflowArgs.filter(it)} : - chModified def chRun = null def chPassthrough = null if (workflowArgs.runIf) { - def runIfBranch = chModifiedFiltered.branch{ tup -> + def runIfBranch = chModified.branch{ tup -> run: workflowArgs.runIf(tup[0], tup[1]) passthrough: true } chRun = runIfBranch.run chPassthrough = runIfBranch.passthrough } else { - chRun = chModifiedFiltered + chRun = chModified chPassthrough = Channel.empty() } + def chRunFiltered = workflowArgs.filter ? + chRun | filter{workflowArgs.filter(it)} : + chRun + def chArgs = workflowArgs.fromState ? - chRun | map{ + chRunFiltered | map{ def new_data = workflowArgs.fromState(it.take(2)) [it[0], new_data] } : - chRun | map {tup -> tup.take(2)} + chRunFiltered | map {tup -> tup.take(2)} // fill in defaults def chArgsWithDefaults = chArgs @@ -2720,7 +2749,7 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { // | view{"chInitialOutput: ${it.take(3)}"} // join the output [prev_id, new_id, output] with the previous state [prev_id, state, ...] - def chNewState = safeJoin(chInitialOutput, chModifiedFiltered, key_) + def chNewState = safeJoin(chInitialOutput, chRunFiltered, key_) // input tuple format: [join_id, id, output, prev_state, ...] // output tuple format: [join_id, id, new_state, ...] | map{ tup -> @@ -2779,7 +2808,29 @@ meta = [ "resources_dir": moduleDir.toRealPath().normalize(), "config": processConfig(readJsonBlob('''{ "name" : "cutadapt", - "version" : "v0.1.0", + "version" : "main", + "authors" : [ + { + "name" : "Toni Verbeiren", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "links" : { + "github" : "tverbeiren", + "linkedin" : "verbeiren" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist and CEO" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Specify Adapters for R1", @@ -3012,7 +3063,7 @@ meta = [ "multiple_sep" : ";" }, { - "type" : "boolean_false", + "type" : "boolean_true", "name" : "--no_indels", "description" : "Allow only mismatches in alignments.\n", "direction" : "input" @@ -3054,7 +3105,7 @@ meta = [ "direction" : "input" }, { - "type" : "boolean_false", + "type" : "boolean_true", "name" : "--no_match_adapter_wildcards", "description" : "Do not interpret IUPAC wildcards in adapters.\n", "direction" : "input" @@ -3089,6 +3140,25 @@ meta = [ } ] }, + { + "name" : "Demultiplexing options", + "arguments" : [ + { + "type" : "string", + "name" : "--demultiplex_mode", + "description" : "Enable demultiplexing and set the mode for it.\nWith mode 'unique_dual', adapters from the first and second read are used,\nand the indexes from the reads are only used in pairs. This implies\n--pair_adapters.\nEnabling mode 'combinatorial_dual' allows all combinations of the sets of indexes\non R1 and R2. It is necessary to write each read pair to an output\nfile depending on the adapters found on both R1 and R2.\nMode 'single', uses indexes or barcodes located at the 5'\nend of the R1 read (single). \n", + "required" : false, + "choices" : [ + "single", + "unique_dual", + "combinatorial_dual" + ], + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + } + ] + }, { "name" : "Read modifications", "arguments" : [ @@ -3519,7 +3589,7 @@ meta = [ "id" : "docker", "image" : "python:3.12", "target_registry" : "images.viash-hub.com", - "target_tag" : "v0.1.0", + "target_tag" : "main", "namespace_separator" : "/", "setup" : [ { @@ -3548,22 +3618,23 @@ meta = [ "runner" : "nextflow", "engine" : "docker|native", "output" : "target/nextflow/cutadapt", - "viash_version" : "0.9.0-RC6", - "git_commit" : "b84b29747d0635f2ac83ea63b496be9a9edb6724", - "git_remote" : "https://github.com/viash-hub/biobox" + "viash_version" : "0.9.0", + "git_commit" : "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b", + "git_remote" : "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox", + "git_tag" : "v0.2.0-27-g952ff08" }, "package_config" : { "name" : "biobox", - "version" : "v0.1.0", + "version" : "main", "description" : "A collection of bioinformatics tools for working with sequence data.\n", - "viash_version" : "0.9.0-RC6", + "viash_version" : "0.9.0", "source" : "src", "target" : "target", "config_mods" : [ ".requirements.commands := ['ps']\n", ".engines += { type: \\"native\\" }", ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'", - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" + ".engines[.type == 'docker'].target_tag := 'main'" ], "keywords" : [ "bioinformatics", @@ -3618,6 +3689,7 @@ $( if [ ! -z ${VIASH_PAR_MATCH_READ_WILDCARDS+x} ]; then echo "${VIASH_PAR_MATCH $( if [ ! -z ${VIASH_PAR_NO_MATCH_ADAPTER_WILDCARDS+x} ]; then echo "${VIASH_PAR_NO_MATCH_ADAPTER_WILDCARDS}" | sed "s#'#'\\"'\\"'#g;s#.*#par_no_match_adapter_wildcards='&'#" ; else echo "# par_no_match_adapter_wildcards="; fi ) $( if [ ! -z ${VIASH_PAR_ACTION+x} ]; then echo "${VIASH_PAR_ACTION}" | sed "s#'#'\\"'\\"'#g;s#.*#par_action='&'#" ; else echo "# par_action="; fi ) $( if [ ! -z ${VIASH_PAR_REVCOMP+x} ]; then echo "${VIASH_PAR_REVCOMP}" | sed "s#'#'\\"'\\"'#g;s#.*#par_revcomp='&'#" ; else echo "# par_revcomp="; fi ) +$( if [ ! -z ${VIASH_PAR_DEMULTIPLEX_MODE+x} ]; then echo "${VIASH_PAR_DEMULTIPLEX_MODE}" | sed "s#'#'\\"'\\"'#g;s#.*#par_demultiplex_mode='&'#" ; else echo "# par_demultiplex_mode="; fi ) $( if [ ! -z ${VIASH_PAR_CUT+x} ]; then echo "${VIASH_PAR_CUT}" | sed "s#'#'\\"'\\"'#g;s#.*#par_cut='&'#" ; else echo "# par_cut="; fi ) $( if [ ! -z ${VIASH_PAR_CUT_R2+x} ]; then echo "${VIASH_PAR_CUT_R2}" | sed "s#'#'\\"'\\"'#g;s#.*#par_cut_r2='&'#" ; else echo "# par_cut_r2="; fi ) $( if [ ! -z ${VIASH_PAR_NEXTSEQ_TRIM+x} ]; then echo "${VIASH_PAR_NEXTSEQ_TRIM}" | sed "s#'#'\\"'\\"'#g;s#.*#par_nextseq_trim='&'#" ; else echo "# par_nextseq_trim="; fi ) @@ -3754,9 +3826,9 @@ debug # Input arguments ########################################################### echo ">> Parsing input arguments" -[[ "\\$par_no_indels" == "true" ]] && unset par_no_indels +[[ "\\$par_no_indels" == "false" ]] && unset par_no_indels [[ "\\$par_match_read_wildcards" == "false" ]] && unset par_match_read_wildcards -[[ "\\$par_no_match_adapter_wildcards" == "true" ]] && unset par_no_match_adapter_wildcards +[[ "\\$par_no_match_adapter_wildcards" == "false" ]] && unset par_no_match_adapter_wildcards [[ "\\$par_revcomp" == "false" ]] && unset par_revcomp input_args=\\$(echo \\\\ @@ -3766,7 +3838,7 @@ input_args=\\$(echo \\\\ \\${par_overlap:+--overlap "\\${par_overlap}"} \\\\ \\${par_match_read_wildcards:+--match-read-wildcards} \\\\ \\${par_no_match_adapter_wildcards:+--no-match-adapter-wildcards} \\\\ - \\${par_action:+--action "\\${par_action}"} \\\\ + \\${par_action:+--action="\\${par_action}"} \\\\ \\${par_revcomp:+--revcomp} \\\\ ) debug "Arguments to cutadapt:" @@ -3785,7 +3857,7 @@ mod_args=\\$(echo \\\\ \\${par_cut_r2:+--cut_r2 "\\${par_cut_r2}"} \\\\ \\${par_nextseq_trim:+--nextseq-trim "\\${par_nextseq_trim}"} \\\\ \\${par_quality_cutoff:+--quality-cutoff "\\${par_quality_cutoff}"} \\\\ - \\${par_quality_cutoff_r2:+--quality-cutoff_r2 "\\${par_quality_cutoff_r2}"} \\\\ + \\${par_quality_cutoff_r2:+-Q "\\${par_quality_cutoff_r2}"} \\\\ \\${par_quality_base:+--quality-base "\\${par_quality_base}"} \\\\ \\${par_poly_a:+--poly-a} \\\\ \\${par_length:+--length "\\${par_length}"} \\\\ @@ -3854,14 +3926,35 @@ else ext="fasta" fi -if [ \\$mode = "se" ]; then +demultiplex_mode="\\$par_demultiplex_mode" +if [[ \\$mode == "se" ]]; then + if [[ "\\$demultiplex_mode" == "unique_dual" ]] || [[ "\\$demultiplex_mode" == "combinatorial_dual" ]]; then + echo "Demultiplexing dual indexes is not possible with single-end data." + exit 1 + fi + prefix="trimmed_" + if [[ ! -z "\\$demultiplex_mode" ]]; then + prefix="{name}_" + fi output_args=\\$(echo \\\\ - --output "\\$output_dir/{name}_001.\\$ext" \\\\ + --output "\\$output_dir/\\${prefix}001.\\$ext" \\\\ ) else + demultiplex_indicator_r1='{name}_' + demultiplex_indicator_r2=\\$demultiplex_indicator_r1 + if [[ "\\$demultiplex_mode" == "combinatorial_dual" ]]; then + demultiplex_indicator_r1='{name1}_{name2}_' + demultiplex_indicator_r2='{name1}_{name2}_' + fi + prefix_r1="trimmed_" + prefix_r2="trimmed_" + if [[ ! -z "\\$demultiplex_mode" ]]; then + prefix_r1=\\$demultiplex_indicator_r1 + prefix_r2=\\$demultiplex_indicator_r2 + fi output_args=\\$(echo \\\\ - --output "\\$output_dir/{name}_R1_001.\\$ext" \\\\ - --paired-output "\\$output_dir/{name}_R2_001.\\$ext" \\\\ + --output "\\$output_dir/\\${prefix_r1}R1_001.\\$ext" \\\\ + --paired-output "\\$output_dir/\\${prefix_r2}R2_001.\\$ext" \\\\ ) fi @@ -3973,7 +4066,11 @@ def vdsl3WorkflowFactory(Map args, Map meta, String rawScript) { val = val.join(par.multiple_sep) } if (par.direction == "output" && par.type == "file") { - val = val.replaceAll('\\$id', id).replaceAll('\\$key', key) + val = val + .replaceAll('\\$id', id) + .replaceAll('\\$\\{id\\}', id) + .replaceAll('\\$key', key) + .replaceAll('\\$\\{key\\}', key) } [parName, val] } @@ -4104,7 +4201,8 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def createParentStr = meta.config.allArguments .findAll { it.type == "file" && it.direction == "output" && it.create_parent } .collect { par -> - "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent \\\"\" + (args[\"${par.plainName}\"] instanceof String ? args[\"${par.plainName}\"] : args[\"${par.plainName}\"].join('\" \"')) + \"\\\"\" : \"\" }" + def contents = "args[\"${par.plainName}\"] instanceof List ? args[\"${par.plainName}\"].join('\" \"') : args[\"${par.plainName}\"]" + "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent '\" + escapeText(${contents}) + \"'\" : \"\" }" } .join("\n") @@ -4112,8 +4210,8 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def inputFileExports = meta.config.allArguments .findAll { it.type == "file" && it.direction.toLowerCase() == "input" } .collect { par -> - def viash_par_contents = "(viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName})" - "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}=\\\"\" + ${viash_par_contents} + \"\\\"\"}" + def contents = "viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName}" + "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}='\" + escapeText(${contents}) + \"'\"}" } // NOTE: if using docker, use /tmp instead of tmpDir! @@ -4150,6 +4248,7 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def procStr = """nextflow.enable.dsl=2 | + |def escapeText = { s -> s.toString().replaceAll("'", "'\\\"'\\\"'") } |process $procKey {$drctvStrs |input: | tuple val(id)$inputPaths, val(args), path(resourcesDir, stageAs: ".viash_meta_resources") @@ -4161,10 +4260,9 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { |$stub |\"\"\" |script:$assertStr - |def escapeText = { s -> s.toString().replaceAll('([`"])', '\\\\\\\\\$1') } |def parInject = args | .findAll{key, value -> value != null} - | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}=\\\"\${escapeText(value)}\\\""} + | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}='\${escapeText(value)}'"} | .join("\\n") |\"\"\" |# meta exports @@ -4249,7 +4347,7 @@ meta["defaults"] = [ "container" : { "registry" : "images.viash-hub.com", "image" : "vsh/biobox/cutadapt", - "tag" : "v0.1.0" + "tag" : "main" }, "tag" : "$id" }'''), diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/nextflow.config b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/nextflow.config similarity index 98% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/nextflow.config rename to target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/nextflow.config index 0b8b606..629e04b 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/nextflow.config +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/nextflow.config @@ -2,8 +2,9 @@ manifest { name = 'cutadapt' mainScript = 'main.nf' nextflowVersion = '!>=20.12.1-edge' - version = 'v0.1.0' + version = 'main' description = 'Cutadapt removes adapter sequences from high-throughput sequencing reads.\n' + author = 'Toni Verbeiren' } process.container = 'nextflow/bash:latest' diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/nextflow_schema.json b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/nextflow_schema.json similarity index 89% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/nextflow_schema.json rename to target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/nextflow_schema.json index 2438aca..2b7fb1b 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/nextflow_schema.json +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/nextflow_schema.json @@ -17,8 +17,8 @@ "adapter": { "type": "string", - "description": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter ligated to the 3\u0027 end (paired data:\nof the first read)", - "help_text": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter ligated to the 3\u0027 end (paired data:\nof the first read). The adapter and subsequent bases are\ntrimmed. If a \u0027$\u0027 character is appended (\u0027anchoring\u0027), the\nadapter is only found if it is a suffix of the read.\n" + "description": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter ligated to the 3\u0027 end (paired data:\nof the first read)", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter ligated to the 3\u0027 end (paired data:\nof the first read). The adapter and subsequent bases are\ntrimmed. If a \u0027$\u0027 character is appended (\u0027anchoring\u0027), the\nadapter is only found if it is a suffix of the read.\n" } @@ -27,8 +27,8 @@ "front": { "type": "string", - "description": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter ligated to the 5\u0027 end (paired data:\nof the first read)", - "help_text": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter ligated to the 5\u0027 end (paired data:\nof the first read). The adapter and any preceding bases\nare trimmed. Partial matches at the 5\u0027 end are allowed. If\na \u0027^\u0027 character is prepended (\u0027anchoring\u0027), the adapter is\nonly found if it is a prefix of the read.\n" + "description": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter ligated to the 5\u0027 end (paired data:\nof the first read)", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter ligated to the 5\u0027 end (paired data:\nof the first read). The adapter and any preceding bases\nare trimmed. Partial matches at the 5\u0027 end are allowed. If\na \u0027^\u0027 character is prepended (\u0027anchoring\u0027), the adapter is\nonly found if it is a prefix of the read.\n" } @@ -37,8 +37,8 @@ "anywhere": { "type": "string", - "description": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter that may be ligated to the 5\u0027 or 3\u0027\nend (paired data: of the first read)", - "help_text": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter that may be ligated to the 5\u0027 or 3\u0027\nend (paired data: of the first read). Both types of\nmatches as described under -a and -g are allowed. If the\nfirst base of the read is part of the match, the behavior\nis as with -g, otherwise as with -a. This option is mostly\nfor rescuing failed library preparations - do not use if\nyou know which end your adapter was ligated to!\n" + "description": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter that may be ligated to the 5\u0027 or 3\u0027\nend (paired data: of the first read)", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter that may be ligated to the 5\u0027 or 3\u0027\nend (paired data: of the first read). Both types of\nmatches as described under -a and -g are allowed. If the\nfirst base of the read is part of the match, the behavior\nis as with -g, otherwise as with -a. This option is mostly\nfor rescuing failed library preparations - do not use if\nyou know which end your adapter was ligated to!\n" } @@ -57,8 +57,8 @@ "adapter_fasta": { "type": "string", - "description": "Type: List of `file`, multiple_sep: `\":\"`. Fasta file containing sequences of an adapter ligated to the 3\u0027 end (paired data:\nof the first read)", - "help_text": "Type: List of `file`, multiple_sep: `\":\"`. Fasta file containing sequences of an adapter ligated to the 3\u0027 end (paired data:\nof the first read). The adapter and subsequent bases are\ntrimmed. If a \u0027$\u0027 character is appended (\u0027anchoring\u0027), the\nadapter is only found if it is a suffix of the read.\n" + "description": "Type: List of `file`, multiple_sep: `\";\"`. Fasta file containing sequences of an adapter ligated to the 3\u0027 end (paired data:\nof the first read)", + "help_text": "Type: List of `file`, multiple_sep: `\";\"`. Fasta file containing sequences of an adapter ligated to the 3\u0027 end (paired data:\nof the first read). The adapter and subsequent bases are\ntrimmed. If a \u0027$\u0027 character is appended (\u0027anchoring\u0027), the\nadapter is only found if it is a suffix of the read.\n" } @@ -97,8 +97,8 @@ "adapter_r2": { "type": "string", - "description": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter ligated to the 3\u0027 end (paired data:\nof the first read)", - "help_text": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter ligated to the 3\u0027 end (paired data:\nof the first read). The adapter and subsequent bases are\ntrimmed. If a \u0027$\u0027 character is appended (\u0027anchoring\u0027), the\nadapter is only found if it is a suffix of the read.\n" + "description": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter ligated to the 3\u0027 end (paired data:\nof the first read)", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter ligated to the 3\u0027 end (paired data:\nof the first read). The adapter and subsequent bases are\ntrimmed. If a \u0027$\u0027 character is appended (\u0027anchoring\u0027), the\nadapter is only found if it is a suffix of the read.\n" } @@ -107,8 +107,8 @@ "front_r2": { "type": "string", - "description": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter ligated to the 5\u0027 end (paired data:\nof the first read)", - "help_text": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter ligated to the 5\u0027 end (paired data:\nof the first read). The adapter and any preceding bases\nare trimmed. Partial matches at the 5\u0027 end are allowed. If\na \u0027^\u0027 character is prepended (\u0027anchoring\u0027), the adapter is\nonly found if it is a prefix of the read.\n" + "description": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter ligated to the 5\u0027 end (paired data:\nof the first read)", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter ligated to the 5\u0027 end (paired data:\nof the first read). The adapter and any preceding bases\nare trimmed. Partial matches at the 5\u0027 end are allowed. If\na \u0027^\u0027 character is prepended (\u0027anchoring\u0027), the adapter is\nonly found if it is a prefix of the read.\n" } @@ -117,8 +117,8 @@ "anywhere_r2": { "type": "string", - "description": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter that may be ligated to the 5\u0027 or 3\u0027\nend (paired data: of the first read)", - "help_text": "Type: List of `string`, multiple_sep: `\":\"`. Sequence of an adapter that may be ligated to the 5\u0027 or 3\u0027\nend (paired data: of the first read). Both types of\nmatches as described under -a and -g are allowed. If the\nfirst base of the read is part of the match, the behavior\nis as with -g, otherwise as with -a. This option is mostly\nfor rescuing failed library preparations - do not use if\nyou know which end your adapter was ligated to!\n" + "description": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter that may be ligated to the 5\u0027 or 3\u0027\nend (paired data: of the first read)", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. Sequence of an adapter that may be ligated to the 5\u0027 or 3\u0027\nend (paired data: of the first read). Both types of\nmatches as described under -a and -g are allowed. If the\nfirst base of the read is part of the match, the behavior\nis as with -g, otherwise as with -a. This option is mostly\nfor rescuing failed library preparations - do not use if\nyou know which end your adapter was ligated to!\n" } @@ -180,7 +180,7 @@ "description": "Type: `boolean_true`, default: `false`. Treat adapters given with -a/-A etc", "help_text": "Type: `boolean_true`, default: `false`. Treat adapters given with -a/-A etc. as pairs. Either both\nor none are removed from each read pair.\n" , - "default": "False" + "default":false } @@ -203,7 +203,7 @@ "description": "Type: `boolean_true`, default: `false`. Read and/or write interleaved paired-end reads", "help_text": "Type: `boolean_true`, default: `false`. Read and/or write interleaved paired-end reads.\n" , - "default": "False" + "default":false } @@ -251,10 +251,10 @@ "no_indels": { "type": "boolean", - "description": "Type: `boolean_false`, default: `true`. Allow only mismatches in alignments", - "help_text": "Type: `boolean_false`, default: `true`. Allow only mismatches in alignments.\n" + "description": "Type: `boolean_true`, default: `false`. Allow only mismatches in alignments", + "help_text": "Type: `boolean_true`, default: `false`. Allow only mismatches in alignments.\n" , - "default": "True" + "default":false } @@ -285,7 +285,7 @@ "description": "Type: `boolean_true`, default: `false`. Interpret IUPAC wildcards in reads", "help_text": "Type: `boolean_true`, default: `false`. Interpret IUPAC wildcards in reads.\n" , - "default": "False" + "default":false } @@ -293,10 +293,10 @@ "no_match_adapter_wildcards": { "type": "boolean", - "description": "Type: `boolean_false`, default: `true`. Do not interpret IUPAC wildcards in adapters", - "help_text": "Type: `boolean_false`, default: `true`. Do not interpret IUPAC wildcards in adapters.\n" + "description": "Type: `boolean_true`, default: `false`. Do not interpret IUPAC wildcards in adapters", + "help_text": "Type: `boolean_true`, default: `false`. Do not interpret IUPAC wildcards in adapters.\n" , - "default": "True" + "default":false } @@ -319,7 +319,29 @@ "description": "Type: `boolean_true`, default: `false`. Check both the read and its reverse complement for adapter\nmatches", "help_text": "Type: `boolean_true`, default: `false`. Check both the read and its reverse complement for adapter\nmatches. If match is on reverse-complemented version,\noutput that one.\n" , - "default": "False" + "default":false + } + + +} +}, + + + "demultiplexing options" : { + "title": "Demultiplexing options", + "type": "object", + "description": "No description", + "properties": { + + + "demultiplex_mode": { + "type": + "string", + "description": "Type: `string`, choices: ``single`, `unique_dual`, `combinatorial_dual``. Enable demultiplexing and set the mode for it", + "help_text": "Type: `string`, choices: ``single`, `unique_dual`, `combinatorial_dual``. Enable demultiplexing and set the mode for it.\nWith mode \u0027unique_dual\u0027, adapters from the first and second read are used,\nand the indexes from the reads are only used in pairs. This implies\n--pair_adapters.\nEnabling mode \u0027combinatorial_dual\u0027 allows all combinations of the sets of indexes\non R1 and R2. It is necessary to write each read pair to an output\nfile depending on the adapters found on both R1 and R2.\nMode \u0027single\u0027, uses indexes or barcodes located at the 5\u0027\nend of the R1 read (single). \n", + "enum": ["single", "unique_dual", "combinatorial_dual"] + + } @@ -337,8 +359,8 @@ "cut": { "type": "string", - "description": "Type: List of `integer`, multiple_sep: `\":\"`. Remove LEN bases from each read (or R1 if paired; use --cut_r2\noption for R2)", - "help_text": "Type: List of `integer`, multiple_sep: `\":\"`. Remove LEN bases from each read (or R1 if paired; use --cut_r2\noption for R2). If LEN is positive, remove bases from the\nbeginning. If LEN is negative, remove bases from the end.\nCan be used twice if LENs have different signs. Applied\n*before* adapter trimming.\n" + "description": "Type: List of `integer`, multiple_sep: `\";\"`. Remove LEN bases from each read (or R1 if paired; use --cut_r2\noption for R2)", + "help_text": "Type: List of `integer`, multiple_sep: `\";\"`. Remove LEN bases from each read (or R1 if paired; use --cut_r2\noption for R2). If LEN is positive, remove bases from the\nbeginning. If LEN is negative, remove bases from the end.\nCan be used twice if LENs have different signs. Applied\n*before* adapter trimming.\n" } @@ -347,8 +369,8 @@ "cut_r2": { "type": "string", - "description": "Type: List of `integer`, multiple_sep: `\":\"`. Remove LEN bases from each read (for R2)", - "help_text": "Type: List of `integer`, multiple_sep: `\":\"`. Remove LEN bases from each read (for R2). If LEN is positive, remove bases from the\nbeginning. If LEN is negative, remove bases from the end.\nCan be used twice if LENs have different signs. Applied\n*before* adapter trimming.\n" + "description": "Type: List of `integer`, multiple_sep: `\";\"`. Remove LEN bases from each read (for R2)", + "help_text": "Type: List of `integer`, multiple_sep: `\";\"`. Remove LEN bases from each read (for R2). If LEN is positive, remove bases from the\nbeginning. If LEN is negative, remove bases from the end.\nCan be used twice if LENs have different signs. Applied\n*before* adapter trimming.\n" } @@ -400,7 +422,7 @@ "description": "Type: `boolean_true`, default: `false`. Trim poly-A tails", "help_text": "Type: `boolean_true`, default: `false`. Trim poly-A tails" , - "default": "False" + "default":false } @@ -421,7 +443,7 @@ "description": "Type: `boolean_true`, default: `false`. Trim N\u0027s on ends of reads", "help_text": "Type: `boolean_true`, default: `false`. Trim N\u0027s on ends of reads." , - "default": "False" + "default":false } @@ -482,7 +504,7 @@ "description": "Type: `boolean_true`, default: `false`. Change negative quality values to zero", "help_text": "Type: `boolean_true`, default: `false`. Change negative quality values to zero." , - "default": "False" + "default":false } @@ -553,7 +575,7 @@ "description": "Type: `boolean_true`, default: `false`. Discard reads that contain an adapter", "help_text": "Type: `boolean_true`, default: `false`. Discard reads that contain an adapter. Use also -O to\navoid discarding too many randomly matching reads.\n" , - "default": "False" + "default":false } @@ -564,7 +586,7 @@ "description": "Type: `boolean_true`, default: `false`. Discard reads that do not contain an adapter", "help_text": "Type: `boolean_true`, default: `false`. Discard reads that do not contain an adapter.\n" , - "default": "False" + "default":false } @@ -575,7 +597,7 @@ "description": "Type: `boolean_true`, default: `false`. Discard reads that did not pass CASAVA filtering (header\nhas :Y:)", "help_text": "Type: `boolean_true`, default: `false`. Discard reads that did not pass CASAVA filtering (header\nhas :Y:).\n" , - "default": "False" + "default":false } @@ -608,7 +630,7 @@ "description": "Type: `boolean_true`, default: `false`. Write report in JSON format to this file", "help_text": "Type: `boolean_true`, default: `false`. Write report in JSON format to this file.\n" , - "default": "False" + "default":false } @@ -616,10 +638,10 @@ "output": { "type": "string", - "description": "Type: List of `file`, required, default: `$id.$key.output_*.fast[a,q]`, example: `fastq/*_001.fast[a,q]`, multiple_sep: `\":\"`. Glob pattern for matching the expected output files", - "help_text": "Type: List of `file`, required, default: `$id.$key.output_*.fast[a,q]`, example: `fastq/*_001.fast[a,q]`, multiple_sep: `\":\"`. Glob pattern for matching the expected output files.\nShould include `$output_dir`.\n" + "description": "Type: List of `file`, required, default: `$id.$key.output_*.fast[a,q]`, example: `fastq/*_001.fast[a,q]`, multiple_sep: `\";\"`. Glob pattern for matching the expected output files", + "help_text": "Type: List of `file`, required, default: `$id.$key.output_*.fast[a,q]`, example: `fastq/*_001.fast[a,q]`, multiple_sep: `\";\"`. Glob pattern for matching the expected output files.\nShould include `$output_dir`.\n" , - "default": "$id.$key.output_*.fast[a,q]" + "default":"$id.$key.output_*.fast[a,q]" } @@ -630,7 +652,7 @@ "description": "Type: `boolean_true`, default: `false`. Output FASTA to standard output even on FASTQ input", "help_text": "Type: `boolean_true`, default: `false`. Output FASTA to standard output even on FASTQ input.\n" , - "default": "False" + "default":false } @@ -641,7 +663,7 @@ "description": "Type: `boolean_true`, default: `false`. Write information about each read and its adapter matches\ninto info", "help_text": "Type: `boolean_true`, default: `false`. Write information about each read and its adapter matches\ninto info.txt in the output directory.\nSee the documentation for the file format.\n" , - "default": "False" + "default":false } @@ -662,7 +684,7 @@ "description": "Type: `boolean_true`, default: `false`. Print debug information", "help_text": "Type: `boolean_true`, default: `false`. Print debug information" , - "default": "False" + "default":false } @@ -726,6 +748,10 @@ "$ref": "#/definitions/input parameters" }, + { + "$ref": "#/definitions/demultiplexing options" + }, + { "$ref": "#/definitions/read modifications" }, diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/.config.vsh.yaml b/target/dependencies/vsh/vsh/biobox/main/nextflow/falco/.config.vsh.yaml similarity index 93% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/.config.vsh.yaml rename to target/dependencies/vsh/vsh/biobox/main/nextflow/falco/.config.vsh.yaml index c7e812b..1040200 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/.config.vsh.yaml +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/falco/.config.vsh.yaml @@ -1,5 +1,18 @@ name: "falco" -version: "v0.1.0" +version: "main" +authors: +- name: "Toni Verbeiren" + roles: + - "author" + - "maintainer" + info: + links: + github: "tverbeiren" + linkedin: "verbeiren" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist and CEO" argument_groups: - name: "Input arguments" arguments: @@ -88,7 +101,7 @@ argument_groups: info: null direction: "input" - type: "boolean_true" - name: "--reverse_complliment" + name: "--reverse_complement" alternatives: - "-r" description: "[Falco only] The input is a \nreverse-complement. All modules will\ @@ -274,7 +287,7 @@ engines: id: "docker" image: "debian:trixie-slim" target_registry: "images.viash-hub.com" - target_tag: "v0.1.0" + target_tag: "main" namespace_separator: "/" setup: - type: "apt" @@ -303,22 +316,23 @@ build_info: engine: "docker|native" output: "target/nextflow/falco" executable: "target/nextflow/falco/main.nf" - viash_version: "0.9.0-RC6" - git_commit: "b84b29747d0635f2ac83ea63b496be9a9edb6724" - git_remote: "https://github.com/viash-hub/biobox" + viash_version: "0.9.0" + git_commit: "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b" + git_remote: "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox" + git_tag: "v0.2.0-27-g952ff08" package_config: name: "biobox" - version: "v0.1.0" + version: "main" description: "A collection of bioinformatics tools for working with sequence data.\n" info: null - viash_version: "0.9.0-RC6" + viash_version: "0.9.0" source: "src" target: "target" config_mods: - ".requirements.commands := ['ps']\n" - ".engines += { type: \"native\" }" - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'" - - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" + - ".engines[.type == 'docker'].target_tag := 'main'" keywords: - "bioinformatics" - "modules" diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/main.nf b/target/dependencies/vsh/vsh/biobox/main/nextflow/falco/main.nf similarity index 97% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/main.nf rename to target/dependencies/vsh/vsh/biobox/main/nextflow/falco/main.nf index d0389df..25db12d 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/main.nf +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/falco/main.nf @@ -1,13 +1,16 @@ -// falco v0.1.0 +// falco main // -// This wrapper script is auto-generated by viash 0.9.0-RC6 and is thus a -// derivative work thereof. This software comes with ABSOLUTELY NO WARRANTY from -// Data Intuitive. +// This wrapper script is auto-generated by viash 0.9.0 and is thus a derivative +// work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data +// Intuitive. // // The component may contain files which fall under a different license. The // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Toni Verbeiren (author, maintainer) //////////////////////////// // VDSL3 helper functions // @@ -760,8 +763,11 @@ def runEach(Map args) { def fromState_ = args.fromState def toState_ = args.toState def filter_ = args.filter + def runIf_ = args.runIf def id_ = args.id + assert !runIf_ || runIf_ instanceof Closure: "runEach: must pass a Closure to runIf." + workflow runEachWf { take: input_ch main: @@ -783,7 +789,20 @@ def runEach(Map args) { [new_id] + tup.drop(1) } : filter_ch - def data_ch = id_ch | map{tup -> + def chPassthrough = null + def chRun = null + if (runIf_) { + def idRunIfBranch = id_ch.branch{ tup -> + run: runIf_(tup[0], tup[1], comp_) + passthrough: true + } + chPassthrough = idRunIfBranch.passthrough + chRun = idRunIfBranch.run + } else { + chRun = id_ch + chPassthrough = Channel.empty() + } + def data_ch = chRun | map{tup -> def new_data = tup[1] if (fromState_ instanceof Map) { new_data = fromState_.collectEntries{ key0, key1 -> @@ -821,8 +840,11 @@ def runEach(Map args) { [tup[0], new_state] + tup.drop(3) } : out_ch + + def return_ch = post_ch + | concat(chPassthrough) - post_ch + return_ch } // mix all results @@ -1598,8 +1620,8 @@ def findStates(Map params, Map config) { // construct renameMap if (args.rename_keys) { def renameMap = args.rename_keys.collectEntries{renameString -> - def split = renameString.split(";") - assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey,newKey:oldKey'" + def split = renameString.split(":") + assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey', or 'newKey:oldKey;newKey:oldKey' in case of multiple values" split } @@ -1709,7 +1731,9 @@ def publishStates(Map args) { def yamlFilename = yamlTemplate_ .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) // TODO: do the pathnames in state_ match up with the outputFilenames_? @@ -1780,7 +1804,9 @@ def publishStatesByConfig(Map args) { def yamlTemplate = params.containsKey("output_state") ? params.output_state : '$id.$key.state.yaml' def yamlFilename = yamlTemplate .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) def yamlDir = java.nio.file.Paths.get(yamlFilename).getParent() // the processed state is a list of [key, value, inputPath, outputFilename] tuples, where @@ -1822,7 +1848,9 @@ def publishStatesByConfig(Map args) { // instantiate the template def filename = filenameTemplate .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) if (par.multiple) { // if the parameter is multiple: true, the filename // should contain a wildcard '*' that is replaced with @@ -2626,30 +2654,31 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { tuple } - def chModifiedFiltered = workflowArgs.filter ? - chModified | filter{workflowArgs.filter(it)} : - chModified def chRun = null def chPassthrough = null if (workflowArgs.runIf) { - def runIfBranch = chModifiedFiltered.branch{ tup -> + def runIfBranch = chModified.branch{ tup -> run: workflowArgs.runIf(tup[0], tup[1]) passthrough: true } chRun = runIfBranch.run chPassthrough = runIfBranch.passthrough } else { - chRun = chModifiedFiltered + chRun = chModified chPassthrough = Channel.empty() } + def chRunFiltered = workflowArgs.filter ? + chRun | filter{workflowArgs.filter(it)} : + chRun + def chArgs = workflowArgs.fromState ? - chRun | map{ + chRunFiltered | map{ def new_data = workflowArgs.fromState(it.take(2)) [it[0], new_data] } : - chRun | map {tup -> tup.take(2)} + chRunFiltered | map {tup -> tup.take(2)} // fill in defaults def chArgsWithDefaults = chArgs @@ -2720,7 +2749,7 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { // | view{"chInitialOutput: ${it.take(3)}"} // join the output [prev_id, new_id, output] with the previous state [prev_id, state, ...] - def chNewState = safeJoin(chInitialOutput, chModifiedFiltered, key_) + def chNewState = safeJoin(chInitialOutput, chRunFiltered, key_) // input tuple format: [join_id, id, output, prev_state, ...] // output tuple format: [join_id, id, new_state, ...] | map{ tup -> @@ -2779,7 +2808,29 @@ meta = [ "resources_dir": moduleDir.toRealPath().normalize(), "config": processConfig(readJsonBlob('''{ "name" : "falco", - "version" : "v0.1.0", + "version" : "main", + "authors" : [ + { + "name" : "Toni Verbeiren", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "links" : { + "github" : "tverbeiren", + "linkedin" : "verbeiren" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist and CEO" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Input arguments", @@ -2868,7 +2919,7 @@ meta = [ }, { "type" : "boolean_true", - "name" : "--reverse_complliment", + "name" : "--reverse_complement", "alternatives" : [ "-r" ], @@ -3080,7 +3131,7 @@ meta = [ "id" : "docker", "image" : "debian:trixie-slim", "target_registry" : "images.viash-hub.com", - "target_tag" : "v0.1.0", + "target_tag" : "main", "namespace_separator" : "/", "setup" : [ { @@ -3118,22 +3169,23 @@ meta = [ "runner" : "nextflow", "engine" : "docker|native", "output" : "target/nextflow/falco", - "viash_version" : "0.9.0-RC6", - "git_commit" : "b84b29747d0635f2ac83ea63b496be9a9edb6724", - "git_remote" : "https://github.com/viash-hub/biobox" + "viash_version" : "0.9.0", + "git_commit" : "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b", + "git_remote" : "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox", + "git_tag" : "v0.2.0-27-g952ff08" }, "package_config" : { "name" : "biobox", - "version" : "v0.1.0", + "version" : "main", "description" : "A collection of bioinformatics tools for working with sequence data.\n", - "viash_version" : "0.9.0-RC6", + "viash_version" : "0.9.0", "source" : "src", "target" : "target", "config_mods" : [ ".requirements.commands := ['ps']\n", ".engines += { type: \\"native\\" }", ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'", - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" + ".engines[.type == 'docker'].target_tag := 'main'" ], "keywords" : [ "bioinformatics", @@ -3168,7 +3220,7 @@ $( if [ ! -z ${VIASH_PAR_ADAPTERS+x} ]; then echo "${VIASH_PAR_ADAPTERS}" | sed $( if [ ! -z ${VIASH_PAR_LIMITS+x} ]; then echo "${VIASH_PAR_LIMITS}" | sed "s#'#'\\"'\\"'#g;s#.*#par_limits='&'#" ; else echo "# par_limits="; fi ) $( if [ ! -z ${VIASH_PAR_SUBSAMPLE+x} ]; then echo "${VIASH_PAR_SUBSAMPLE}" | sed "s#'#'\\"'\\"'#g;s#.*#par_subsample='&'#" ; else echo "# par_subsample="; fi ) $( if [ ! -z ${VIASH_PAR_BISULFITE+x} ]; then echo "${VIASH_PAR_BISULFITE}" | sed "s#'#'\\"'\\"'#g;s#.*#par_bisulfite='&'#" ; else echo "# par_bisulfite="; fi ) -$( if [ ! -z ${VIASH_PAR_REVERSE_COMPLLIMENT+x} ]; then echo "${VIASH_PAR_REVERSE_COMPLLIMENT}" | sed "s#'#'\\"'\\"'#g;s#.*#par_reverse_complliment='&'#" ; else echo "# par_reverse_complliment="; fi ) +$( if [ ! -z ${VIASH_PAR_REVERSE_COMPLEMENT+x} ]; then echo "${VIASH_PAR_REVERSE_COMPLEMENT}" | sed "s#'#'\\"'\\"'#g;s#.*#par_reverse_complement='&'#" ; else echo "# par_reverse_complement="; fi ) $( if [ ! -z ${VIASH_PAR_OUTDIR+x} ]; then echo "${VIASH_PAR_OUTDIR}" | sed "s#'#'\\"'\\"'#g;s#.*#par_outdir='&'#" ; else echo "# par_outdir="; fi ) $( if [ ! -z ${VIASH_PAR_FORMAT+x} ]; then echo "${VIASH_PAR_FORMAT}" | sed "s#'#'\\"'\\"'#g;s#.*#par_format='&'#" ; else echo "# par_format="; fi ) $( if [ ! -z ${VIASH_PAR_DATA_FILENAME+x} ]; then echo "${VIASH_PAR_DATA_FILENAME}" | sed "s#'#'\\"'\\"'#g;s#.*#par_data_filename='&'#" ; else echo "# par_data_filename="; fi ) @@ -3200,7 +3252,7 @@ set -eo pipefail [[ "\\$par_nogroup" == "false" ]] && unset par_nogroup [[ "\\$par_bisulfite" == "false" ]] && unset par_bisulfite -[[ "\\$par_reverse_compliment" == "false" ]] && unset par_reverse_compliment +[[ "\\$par_reverse_complement" == "false" ]] && unset par_reverse_complement IFS=";" read -ra input <<< \\$par_input @@ -3211,7 +3263,7 @@ IFS=";" read -ra input <<< \\$par_input \\${par_limits:+--limits "\\$par_limits"} \\\\ \\${par_subsample:+-subsample \\$par_subsample} \\\\ \\${par_bisulfite:+-bisulfite} \\\\ - \\${par_reverse_compliment:+-reverse-compliment} \\\\ + \\${par_reverse_complement:+-reverse-complement} \\\\ \\${par_outdir:+--outdir "\\$par_outdir"} \\\\ \\${par_format:+--format "\\$par_format"} \\\\ \\${par_data_filename:+-data-filename "\\$par_data_filename"} \\\\ @@ -3298,7 +3350,11 @@ def vdsl3WorkflowFactory(Map args, Map meta, String rawScript) { val = val.join(par.multiple_sep) } if (par.direction == "output" && par.type == "file") { - val = val.replaceAll('\\$id', id).replaceAll('\\$key', key) + val = val + .replaceAll('\\$id', id) + .replaceAll('\\$\\{id\\}', id) + .replaceAll('\\$key', key) + .replaceAll('\\$\\{key\\}', key) } [parName, val] } @@ -3429,7 +3485,8 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def createParentStr = meta.config.allArguments .findAll { it.type == "file" && it.direction == "output" && it.create_parent } .collect { par -> - "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent \\\"\" + (args[\"${par.plainName}\"] instanceof String ? args[\"${par.plainName}\"] : args[\"${par.plainName}\"].join('\" \"')) + \"\\\"\" : \"\" }" + def contents = "args[\"${par.plainName}\"] instanceof List ? args[\"${par.plainName}\"].join('\" \"') : args[\"${par.plainName}\"]" + "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent '\" + escapeText(${contents}) + \"'\" : \"\" }" } .join("\n") @@ -3437,8 +3494,8 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def inputFileExports = meta.config.allArguments .findAll { it.type == "file" && it.direction.toLowerCase() == "input" } .collect { par -> - def viash_par_contents = "(viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName})" - "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}=\\\"\" + ${viash_par_contents} + \"\\\"\"}" + def contents = "viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName}" + "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}='\" + escapeText(${contents}) + \"'\"}" } // NOTE: if using docker, use /tmp instead of tmpDir! @@ -3475,6 +3532,7 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def procStr = """nextflow.enable.dsl=2 | + |def escapeText = { s -> s.toString().replaceAll("'", "'\\\"'\\\"'") } |process $procKey {$drctvStrs |input: | tuple val(id)$inputPaths, val(args), path(resourcesDir, stageAs: ".viash_meta_resources") @@ -3486,10 +3544,9 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { |$stub |\"\"\" |script:$assertStr - |def escapeText = { s -> s.toString().replaceAll('([`"])', '\\\\\\\\\$1') } |def parInject = args | .findAll{key, value -> value != null} - | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}=\\\"\${escapeText(value)}\\\""} + | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}='\${escapeText(value)}'"} | .join("\\n") |\"\"\" |# meta exports @@ -3574,7 +3631,7 @@ meta["defaults"] = [ "container" : { "registry" : "images.viash-hub.com", "image" : "vsh/biobox/falco", - "tag" : "v0.1.0" + "tag" : "main" }, "tag" : "$id" }'''), diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/nextflow.config b/target/dependencies/vsh/vsh/biobox/main/nextflow/falco/nextflow.config similarity index 98% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/nextflow.config rename to target/dependencies/vsh/vsh/biobox/main/nextflow/falco/nextflow.config index 3ac4103..b338beb 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/nextflow.config +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/falco/nextflow.config @@ -2,8 +2,9 @@ manifest { name = 'falco' mainScript = 'main.nf' nextflowVersion = '!>=20.12.1-edge' - version = 'v0.1.0' + version = 'main' description = 'A C++ drop-in replacement of FastQC to assess the quality of sequence read data' + author = 'Toni Verbeiren' } process.container = 'nextflow/bash:latest' diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/nextflow_schema.json b/target/dependencies/vsh/vsh/biobox/main/nextflow/falco/nextflow_schema.json similarity index 95% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/nextflow_schema.json rename to target/dependencies/vsh/vsh/biobox/main/nextflow/falco/nextflow_schema.json index 71b5872..8d40e41 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/nextflow_schema.json +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/falco/nextflow_schema.json @@ -17,8 +17,8 @@ "input": { "type": "string", - "description": "Type: List of `file`, required, example: `input1.fastq;input2.fastq`, multiple_sep: `\":\"`. input fastq files", - "help_text": "Type: List of `file`, required, example: `input1.fastq;input2.fastq`, multiple_sep: `\":\"`. input fastq files" + "description": "Type: List of `file`, required, example: `input1.fastq;input2.fastq`, multiple_sep: `\";\"`. input fastq files", + "help_text": "Type: List of `file`, required, example: `input1.fastq;input2.fastq`, multiple_sep: `\";\"`. input fastq files" } @@ -40,7 +40,7 @@ "description": "Type: `boolean_true`, default: `false`. Disable grouping of bases for reads \u003e50bp", "help_text": "Type: `boolean_true`, default: `false`. Disable grouping of bases for reads \u003e50bp. \nAll reports will show data for every base in \nthe read. WARNING: When using this option, \nyour plots may end up a ridiculous size. You \nhave been warned!\n" , - "default": "False" + "default":false } @@ -91,18 +91,18 @@ "description": "Type: `boolean_true`, default: `false`. [Falco only] reads are whole genome \nbisulfite sequencing, and more Ts and fewer \nCs are therefore expected and will be \naccounted for in base content", "help_text": "Type: `boolean_true`, default: `false`. [Falco only] reads are whole genome \nbisulfite sequencing, and more Ts and fewer \nCs are therefore expected and will be \naccounted for in base content.\n" , - "default": "False" + "default":false } , - "reverse_complliment": { + "reverse_complement": { "type": "boolean", "description": "Type: `boolean_true`, default: `false`. [Falco only] The input is a \nreverse-complement", "help_text": "Type: `boolean_true`, default: `false`. [Falco only] The input is a \nreverse-complement. All modules will be \ntested by swapping A/T and C/G\n" , - "default": "False" + "default":false } @@ -123,7 +123,7 @@ "description": "Type: `file`, required, default: `$id.$key.outdir.outdir`, example: `output`. Create all output files in the specified \noutput directory", "help_text": "Type: `file`, required, default: `$id.$key.outdir.outdir`, example: `output`. Create all output files in the specified \noutput directory. FALCO-SPECIFIC: If the \ndirectory does not exists, the program will \ncreate it.\n" , - "default": "$id.$key.outdir.outdir" + "default":"$id.$key.outdir.outdir" } @@ -146,7 +146,7 @@ "description": "Type: `file`, default: `$id.$key.data_filename.data_filename`. [Falco only] Specify filename for FastQC \ndata output (TXT)", "help_text": "Type: `file`, default: `$id.$key.data_filename.data_filename`. [Falco only] Specify filename for FastQC \ndata output (TXT). If not specified, it will \nbe called fastq_data.txt in either the input \nfile\u0027s directory or the one specified in the \n--output flag. Only available when running \nfalco with a single input.\n" , - "default": "$id.$key.data_filename.data_filename" + "default":"$id.$key.data_filename.data_filename" } @@ -157,7 +157,7 @@ "description": "Type: `file`, default: `$id.$key.report_filename.report_filename`. [Falco only] Specify filename for FastQC \nreport output (HTML)", "help_text": "Type: `file`, default: `$id.$key.report_filename.report_filename`. [Falco only] Specify filename for FastQC \nreport output (HTML). If not specified, it \nwill be called fastq_report.html in either \nthe input file\u0027s directory or the one \nspecified in the --output flag. Only \navailable when running falco with a single \ninput.\n" , - "default": "$id.$key.report_filename.report_filename" + "default":"$id.$key.report_filename.report_filename" } @@ -168,7 +168,7 @@ "description": "Type: `file`, default: `$id.$key.summary_filename.summary_filename`. [Falco only] Specify filename for the short \nsummary output (TXT)", "help_text": "Type: `file`, default: `$id.$key.summary_filename.summary_filename`. [Falco only] Specify filename for the short \nsummary output (TXT). If not specified, it \nwill be called fastq_report.html in either \nthe input file\u0027s directory or the one \nspecified in the --output flag. Only \navailable when running falco with a single \ninput.\n" , - "default": "$id.$key.summary_filename.summary_filename" + "default":"$id.$key.summary_filename.summary_filename" } diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/.config.vsh.yaml b/target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/.config.vsh.yaml similarity index 93% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/.config.vsh.yaml rename to target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/.config.vsh.yaml index fcf4762..3475e44 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/.config.vsh.yaml +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/.config.vsh.yaml @@ -1,5 +1,19 @@ name: "multiqc" -version: "v0.1.0" +version: "main" +authors: +- name: "Dorien Roosen" + roles: + - "author" + - "maintainer" + info: + links: + email: "dorien@data-intuitive.com" + github: "dorien-er" + linkedin: "dorien-roosen" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" argument_groups: - name: "Input" arguments: @@ -63,39 +77,43 @@ argument_groups: description: "Use only these module" info: null example: - - "fastqc,cutadapt" + - "fastqc" + - "cutadapt" required: false direction: "input" multiple: true - multiple_sep: "," + multiple_sep: ";" - type: "string" name: "--exclude_modules" description: "Do not use only these modules" info: null example: - - "fastqc,cutadapt" + - "fastqc" + - "cutadapt" required: false direction: "input" multiple: true - multiple_sep: "," + multiple_sep: ";" - type: "string" name: "--ignore_analysis" info: null example: - - "run_one/*,run_two/*" + - "run_one/*" + - "run_two/*" required: false direction: "input" multiple: true - multiple_sep: "," + multiple_sep: ";" - type: "string" name: "--ignore_samples" info: null example: - - "sample_1*,sample_3*" + - "sample_1*" + - "sample_3*" required: false direction: "input" multiple: true - multiple_sep: "," + multiple_sep: ";" - type: "boolean_true" name: "--ignore_symlinks" description: "Ignore symlinked directories and files" @@ -415,7 +433,7 @@ engines: id: "docker" image: "quay.io/biocontainers/multiqc:1.21--pyhdfd78af_0" target_registry: "images.viash-hub.com" - target_tag: "v0.1.0" + target_tag: "main" namespace_separator: "/" setup: - type: "docker" @@ -437,22 +455,23 @@ build_info: engine: "docker|native" output: "target/nextflow/multiqc" executable: "target/nextflow/multiqc/main.nf" - viash_version: "0.9.0-RC6" - git_commit: "b84b29747d0635f2ac83ea63b496be9a9edb6724" - git_remote: "https://github.com/viash-hub/biobox" + viash_version: "0.9.0" + git_commit: "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b" + git_remote: "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox" + git_tag: "v0.2.0-27-g952ff08" package_config: name: "biobox" - version: "v0.1.0" + version: "main" description: "A collection of bioinformatics tools for working with sequence data.\n" info: null - viash_version: "0.9.0-RC6" + viash_version: "0.9.0" source: "src" target: "target" config_mods: - ".requirements.commands := ['ps']\n" - ".engines += { type: \"native\" }" - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'" - - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" + - ".engines[.type == 'docker'].target_tag := 'main'" keywords: - "bioinformatics" - "modules" diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/main.nf b/target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/main.nf similarity index 97% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/main.nf rename to target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/main.nf index d7f771d..71ef4c3 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/main.nf +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/main.nf @@ -1,13 +1,16 @@ -// multiqc v0.1.0 +// multiqc main // -// This wrapper script is auto-generated by viash 0.9.0-RC6 and is thus a -// derivative work thereof. This software comes with ABSOLUTELY NO WARRANTY from -// Data Intuitive. +// This wrapper script is auto-generated by viash 0.9.0 and is thus a derivative +// work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data +// Intuitive. // // The component may contain files which fall under a different license. The // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dorien Roosen (author, maintainer) //////////////////////////// // VDSL3 helper functions // @@ -760,8 +763,11 @@ def runEach(Map args) { def fromState_ = args.fromState def toState_ = args.toState def filter_ = args.filter + def runIf_ = args.runIf def id_ = args.id + assert !runIf_ || runIf_ instanceof Closure: "runEach: must pass a Closure to runIf." + workflow runEachWf { take: input_ch main: @@ -783,7 +789,20 @@ def runEach(Map args) { [new_id] + tup.drop(1) } : filter_ch - def data_ch = id_ch | map{tup -> + def chPassthrough = null + def chRun = null + if (runIf_) { + def idRunIfBranch = id_ch.branch{ tup -> + run: runIf_(tup[0], tup[1], comp_) + passthrough: true + } + chPassthrough = idRunIfBranch.passthrough + chRun = idRunIfBranch.run + } else { + chRun = id_ch + chPassthrough = Channel.empty() + } + def data_ch = chRun | map{tup -> def new_data = tup[1] if (fromState_ instanceof Map) { new_data = fromState_.collectEntries{ key0, key1 -> @@ -821,8 +840,11 @@ def runEach(Map args) { [tup[0], new_state] + tup.drop(3) } : out_ch + + def return_ch = post_ch + | concat(chPassthrough) - post_ch + return_ch } // mix all results @@ -1598,8 +1620,8 @@ def findStates(Map params, Map config) { // construct renameMap if (args.rename_keys) { def renameMap = args.rename_keys.collectEntries{renameString -> - def split = renameString.split(";") - assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey,newKey:oldKey'" + def split = renameString.split(":") + assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey', or 'newKey:oldKey;newKey:oldKey' in case of multiple values" split } @@ -1709,7 +1731,9 @@ def publishStates(Map args) { def yamlFilename = yamlTemplate_ .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) // TODO: do the pathnames in state_ match up with the outputFilenames_? @@ -1780,7 +1804,9 @@ def publishStatesByConfig(Map args) { def yamlTemplate = params.containsKey("output_state") ? params.output_state : '$id.$key.state.yaml' def yamlFilename = yamlTemplate .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) def yamlDir = java.nio.file.Paths.get(yamlFilename).getParent() // the processed state is a list of [key, value, inputPath, outputFilename] tuples, where @@ -1822,7 +1848,9 @@ def publishStatesByConfig(Map args) { // instantiate the template def filename = filenameTemplate .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) if (par.multiple) { // if the parameter is multiple: true, the filename // should contain a wildcard '*' that is replaced with @@ -2626,30 +2654,31 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { tuple } - def chModifiedFiltered = workflowArgs.filter ? - chModified | filter{workflowArgs.filter(it)} : - chModified def chRun = null def chPassthrough = null if (workflowArgs.runIf) { - def runIfBranch = chModifiedFiltered.branch{ tup -> + def runIfBranch = chModified.branch{ tup -> run: workflowArgs.runIf(tup[0], tup[1]) passthrough: true } chRun = runIfBranch.run chPassthrough = runIfBranch.passthrough } else { - chRun = chModifiedFiltered + chRun = chModified chPassthrough = Channel.empty() } + def chRunFiltered = workflowArgs.filter ? + chRun | filter{workflowArgs.filter(it)} : + chRun + def chArgs = workflowArgs.fromState ? - chRun | map{ + chRunFiltered | map{ def new_data = workflowArgs.fromState(it.take(2)) [it[0], new_data] } : - chRun | map {tup -> tup.take(2)} + chRunFiltered | map {tup -> tup.take(2)} // fill in defaults def chArgsWithDefaults = chArgs @@ -2720,7 +2749,7 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { // | view{"chInitialOutput: ${it.take(3)}"} // join the output [prev_id, new_id, output] with the previous state [prev_id, state, ...] - def chNewState = safeJoin(chInitialOutput, chModifiedFiltered, key_) + def chNewState = safeJoin(chInitialOutput, chRunFiltered, key_) // input tuple format: [join_id, id, output, prev_state, ...] // output tuple format: [join_id, id, new_state, ...] | map{ tup -> @@ -2779,7 +2808,30 @@ meta = [ "resources_dir": moduleDir.toRealPath().normalize(), "config": processConfig(readJsonBlob('''{ "name" : "multiqc", - "version" : "v0.1.0", + "version" : "main", + "authors" : [ + { + "name" : "Dorien Roosen", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "links" : { + "email" : "dorien@data-intuitive.com", + "github" : "dorien-er", + "linkedin" : "dorien-roosen" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Input", @@ -2855,46 +2907,50 @@ meta = [ "name" : "--include_modules", "description" : "Use only these module", "example" : [ - "fastqc,cutadapt" + "fastqc", + "cutadapt" ], "required" : false, "direction" : "input", "multiple" : true, - "multiple_sep" : "," + "multiple_sep" : ";" }, { "type" : "string", "name" : "--exclude_modules", "description" : "Do not use only these modules", "example" : [ - "fastqc,cutadapt" + "fastqc", + "cutadapt" ], "required" : false, "direction" : "input", "multiple" : true, - "multiple_sep" : "," + "multiple_sep" : ";" }, { "type" : "string", "name" : "--ignore_analysis", "example" : [ - "run_one/*,run_two/*" + "run_one/*", + "run_two/*" ], "required" : false, "direction" : "input", "multiple" : true, - "multiple_sep" : "," + "multiple_sep" : ";" }, { "type" : "string", "name" : "--ignore_samples", "example" : [ - "sample_1*,sample_3*" + "sample_1*", + "sample_3*" ], "required" : false, "direction" : "input", "multiple" : true, - "multiple_sep" : "," + "multiple_sep" : ";" }, { "type" : "boolean_true", @@ -3279,7 +3335,7 @@ meta = [ "id" : "docker", "image" : "quay.io/biocontainers/multiqc:1.21--pyhdfd78af_0", "target_registry" : "images.viash-hub.com", - "target_tag" : "v0.1.0", + "target_tag" : "main", "namespace_separator" : "/", "setup" : [ { @@ -3309,22 +3365,23 @@ meta = [ "runner" : "nextflow", "engine" : "docker|native", "output" : "target/nextflow/multiqc", - "viash_version" : "0.9.0-RC6", - "git_commit" : "b84b29747d0635f2ac83ea63b496be9a9edb6724", - "git_remote" : "https://github.com/viash-hub/biobox" + "viash_version" : "0.9.0", + "git_commit" : "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b", + "git_remote" : "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox", + "git_tag" : "v0.2.0-27-g952ff08" }, "package_config" : { "name" : "biobox", - "version" : "v0.1.0", + "version" : "main", "description" : "A collection of bioinformatics tools for working with sequence data.\n", - "viash_version" : "0.9.0-RC6", + "viash_version" : "0.9.0", "source" : "src", "target" : "target", "config_mods" : [ ".requirements.commands := ['ps']\n", ".engines += { type: \\"native\\" }", ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'", - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" + ".engines[.type == 'docker'].target_tag := 'main'" ], "keywords" : [ "bioinformatics", @@ -3411,26 +3468,32 @@ $( if [ ! -z ${VIASH_META_MEMORY_PIB+x} ]; then echo "${VIASH_META_MEMORY_PIB}" #!/bin/bash # disable flags -[[ "\\$par_ignore_symlinks" == "false" ]] && unset par_ignore_symlinks -[[ "\\$par_dirs" == "false" ]] && unset par_dirs -[[ "\\$par_full_names" == "false" ]] && unset par_full_names -[[ "\\$par_fn_as_s_name" == "false" ]] && unset par_fn_as_s_name -[[ "\\$par_profile_runtime" == "false" ]] && unset par_profile_runtime -[[ "\\$par_verbose" == "false" ]] && unset par_verbose -[[ "\\$par_quiet" == "false" ]] && unset par_quiet -[[ "\\$par_strict" == "false" ]] && unset par_strict -[[ "\\$par_development" == "false" ]] && unset par_development -[[ "\\$par_require_logs" == "false" ]] && unset par_require_logs -[[ "\\$par_no_megaqc_upload" == "false" ]] && unset par_no_megaqc_upload -[[ "\\$par_no_ansi" == "false" ]] && unset par_no_ansi -[[ "\\$par_flat" == "false" ]] && unset par_flat -[[ "\\$par_interactive" == "false" ]] && unset par_interactive -[[ "\\$par_static_plot_export" == "false" ]] && unset par_static_plot_export -[[ "\\$par_data_dir" == "false" ]] && unset par_data_dir -[[ "\\$par_no_data_dir" == "false" ]] && unset par_no_data_dir -[[ "\\$par_zip_data_dir" == "false" ]] && unset par_zip_data_dir -[[ "\\$par_pdf" == "false" ]] && unset par_pdf +unset_if_false=( + par_ignore_symlinks + par_dirs + par_full_names + par_fn_as_s_name + par_profile_runtime + par_verbose + par_quiet + par_strict + par_development + par_require_logs + par_no_megaqc_upload + par_no_ansi + par_flat + par_interactive + par_static_plot_export + par_data_dir + par_no_data_dir + par_zip_data_dir + par_pdf +) +for par in \\${unset_if_false[@]}; do + test_val="\\${!par}" + [[ "\\$test_val" == "false" ]] && unset \\$par +done # handle inputs out_dir=\\$(dirname "\\$par_output_report") @@ -3448,7 +3511,7 @@ IFS=";" read -ra inputs <<< \\$par_input if [[ -n "\\$par_include_modules" ]]; then include_modules="" - IFS="," read -ra incl_modules <<< \\$par_include_modules + IFS=";" read -ra incl_modules <<< \\$par_include_modules for i in "\\${incl_modules[@]}"; do include_modules+="--include \\$i " done @@ -3457,7 +3520,7 @@ fi if [[ -n "\\$par_exclude_modules" ]]; then exclude_modules="" - IFS="," read -ra excl_modules <<< \\$par_exclude_modules + IFS=";" read -ra excl_modules <<< \\$par_exclude_modules for i in "\\${excl_modules[@]}"; do exclude_modules+="--exclude \\$i" done @@ -3466,7 +3529,7 @@ fi if [[ -n "\\$par_ignore_analysis" ]]; then ignore="" - IFS="," read -ra ignore_analysis <<< \\$par_ignore_analysis + IFS=";" read -ra ignore_analysis <<< \\$par_ignore_analysis for i in "\\${ignore_analysis[@]}"; do ignore+="--ignore \\$i " done @@ -3475,7 +3538,7 @@ fi if [[ -n "\\$par_ignore_samples" ]]; then ignore_samples="" - IFS="," read -ra ign_samples <<< \\$par_ignore_samples + IFS=";" read -ra ign_samples <<< \\$par_ignore_samples for i in "\\${ign_samples[@]}"; do ignore_samples+="--ignore-samples \\$i" done @@ -3618,7 +3681,11 @@ def vdsl3WorkflowFactory(Map args, Map meta, String rawScript) { val = val.join(par.multiple_sep) } if (par.direction == "output" && par.type == "file") { - val = val.replaceAll('\\$id', id).replaceAll('\\$key', key) + val = val + .replaceAll('\\$id', id) + .replaceAll('\\$\\{id\\}', id) + .replaceAll('\\$key', key) + .replaceAll('\\$\\{key\\}', key) } [parName, val] } @@ -3749,7 +3816,8 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def createParentStr = meta.config.allArguments .findAll { it.type == "file" && it.direction == "output" && it.create_parent } .collect { par -> - "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent \\\"\" + (args[\"${par.plainName}\"] instanceof String ? args[\"${par.plainName}\"] : args[\"${par.plainName}\"].join('\" \"')) + \"\\\"\" : \"\" }" + def contents = "args[\"${par.plainName}\"] instanceof List ? args[\"${par.plainName}\"].join('\" \"') : args[\"${par.plainName}\"]" + "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent '\" + escapeText(${contents}) + \"'\" : \"\" }" } .join("\n") @@ -3757,8 +3825,8 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def inputFileExports = meta.config.allArguments .findAll { it.type == "file" && it.direction.toLowerCase() == "input" } .collect { par -> - def viash_par_contents = "(viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName})" - "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}=\\\"\" + ${viash_par_contents} + \"\\\"\"}" + def contents = "viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName}" + "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}='\" + escapeText(${contents}) + \"'\"}" } // NOTE: if using docker, use /tmp instead of tmpDir! @@ -3795,6 +3863,7 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def procStr = """nextflow.enable.dsl=2 | + |def escapeText = { s -> s.toString().replaceAll("'", "'\\\"'\\\"'") } |process $procKey {$drctvStrs |input: | tuple val(id)$inputPaths, val(args), path(resourcesDir, stageAs: ".viash_meta_resources") @@ -3806,10 +3875,9 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { |$stub |\"\"\" |script:$assertStr - |def escapeText = { s -> s.toString().replaceAll('([`"])', '\\\\\\\\\$1') } |def parInject = args | .findAll{key, value -> value != null} - | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}=\\\"\${escapeText(value)}\\\""} + | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}='\${escapeText(value)}'"} | .join("\\n") |\"\"\" |# meta exports @@ -3894,7 +3962,7 @@ meta["defaults"] = [ "container" : { "registry" : "images.viash-hub.com", "image" : "vsh/biobox/multiqc", - "tag" : "v0.1.0" + "tag" : "main" }, "tag" : "$id" }'''), diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/nextflow.config b/target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/nextflow.config similarity index 98% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/nextflow.config rename to target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/nextflow.config index 2443ee9..7dff292 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/nextflow.config +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/nextflow.config @@ -2,8 +2,9 @@ manifest { name = 'multiqc' mainScript = 'main.nf' nextflowVersion = '!>=20.12.1-edge' - version = 'v0.1.0' + version = 'main' description = 'MultiQC aggregates results from bioinformatics analyses across many samples into a single report.\nIt searches a given directory for analysis logs and compiles a HTML report. It\'s a general use tool, perfect for summarising the output from numerous bioinformatics tools.\n' + author = 'Dorien Roosen' } process.container = 'nextflow/bash:latest' diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/nextflow_schema.json b/target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/nextflow_schema.json similarity index 92% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/nextflow_schema.json rename to target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/nextflow_schema.json index daab1d2..6a3bd5c 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/nextflow_schema.json +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/nextflow_schema.json @@ -17,8 +17,8 @@ "input": { "type": "string", - "description": "Type: List of `file`, required, example: `data/results/`, multiple_sep: `\":\"`. File paths to be searched for analysis results to be included in the report", - "help_text": "Type: List of `file`, required, example: `data/results/`, multiple_sep: `\":\"`. File paths to be searched for analysis results to be included in the report.\n" + "description": "Type: List of `file`, required, example: `data/results`, multiple_sep: `\";\"`. File paths to be searched for analysis results to be included in the report", + "help_text": "Type: List of `file`, required, example: `data/results`, multiple_sep: `\";\"`. File paths to be searched for analysis results to be included in the report.\n" } @@ -40,7 +40,7 @@ "description": "Type: `file`, default: `$id.$key.output_report.html`, example: `multiqc_report.html`. Filepath of the generated report", "help_text": "Type: `file`, default: `$id.$key.output_report.html`, example: `multiqc_report.html`. Filepath of the generated report.\n" , - "default": "$id.$key.output_report.html" + "default":"$id.$key.output_report.html" } @@ -51,7 +51,7 @@ "description": "Type: `file`, default: `$id.$key.output_data.output_data`, example: `multiqc_data`. Output directory for parsed data files", "help_text": "Type: `file`, default: `$id.$key.output_data.output_data`, example: `multiqc_data`. Output directory for parsed data files. If not provided, parsed data will not be published.\n" , - "default": "$id.$key.output_data.output_data" + "default":"$id.$key.output_data.output_data" } @@ -62,7 +62,7 @@ "description": "Type: `file`, default: `$id.$key.output_plots.output_plots`, example: `multiqc_plots`. Output directory for generated plots", "help_text": "Type: `file`, default: `$id.$key.output_plots.output_plots`, example: `multiqc_plots`. Output directory for generated plots. If not provided, plots will not be published.\n" , - "default": "$id.$key.output_plots.output_plots" + "default":"$id.$key.output_plots.output_plots" } @@ -80,8 +80,8 @@ "include_modules": { "type": "string", - "description": "Type: List of `string`, example: `fastqc,cutadapt`, multiple_sep: `\",\"`. Use only these module", - "help_text": "Type: List of `string`, example: `fastqc,cutadapt`, multiple_sep: `\",\"`. Use only these module" + "description": "Type: List of `string`, example: `fastqc;cutadapt`, multiple_sep: `\";\"`. Use only these module", + "help_text": "Type: List of `string`, example: `fastqc;cutadapt`, multiple_sep: `\";\"`. Use only these module" } @@ -90,8 +90,8 @@ "exclude_modules": { "type": "string", - "description": "Type: List of `string`, example: `fastqc,cutadapt`, multiple_sep: `\",\"`. Do not use only these modules", - "help_text": "Type: List of `string`, example: `fastqc,cutadapt`, multiple_sep: `\",\"`. Do not use only these modules" + "description": "Type: List of `string`, example: `fastqc;cutadapt`, multiple_sep: `\";\"`. Do not use only these modules", + "help_text": "Type: List of `string`, example: `fastqc;cutadapt`, multiple_sep: `\";\"`. Do not use only these modules" } @@ -100,8 +100,8 @@ "ignore_analysis": { "type": "string", - "description": "Type: List of `string`, example: `run_one/*,run_two/*`, multiple_sep: `\",\"`. ", - "help_text": "Type: List of `string`, example: `run_one/*,run_two/*`, multiple_sep: `\",\"`. " + "description": "Type: List of `string`, example: `run_one/*;run_two/*`, multiple_sep: `\";\"`. ", + "help_text": "Type: List of `string`, example: `run_one/*;run_two/*`, multiple_sep: `\";\"`. " } @@ -110,8 +110,8 @@ "ignore_samples": { "type": "string", - "description": "Type: List of `string`, example: `sample_1*,sample_3*`, multiple_sep: `\",\"`. ", - "help_text": "Type: List of `string`, example: `sample_1*,sample_3*`, multiple_sep: `\",\"`. " + "description": "Type: List of `string`, example: `sample_1*;sample_3*`, multiple_sep: `\";\"`. ", + "help_text": "Type: List of `string`, example: `sample_1*;sample_3*`, multiple_sep: `\";\"`. " } @@ -123,7 +123,7 @@ "description": "Type: `boolean_true`, default: `false`. Ignore symlinked directories and files", "help_text": "Type: `boolean_true`, default: `false`. Ignore symlinked directories and files" , - "default": "False" + "default":false } @@ -144,7 +144,7 @@ "description": "Type: `boolean_true`, default: `false`. Prepend directory to sample names to avoid clashing filenames", "help_text": "Type: `boolean_true`, default: `false`. Prepend directory to sample names to avoid clashing filenames" , - "default": "False" + "default":false } @@ -165,7 +165,7 @@ "description": "Type: `boolean_true`, default: `false`. Do not clean the sample names (leave as full file name)", "help_text": "Type: `boolean_true`, default: `false`. Do not clean the sample names (leave as full file name)" , - "default": "False" + "default":false } @@ -176,7 +176,7 @@ "description": "Type: `boolean_true`, default: `false`. Use the log filename as the sample name", "help_text": "Type: `boolean_true`, default: `false`. Use the log filename as the sample name" , - "default": "False" + "default":false } @@ -269,7 +269,7 @@ "description": "Type: `boolean_true`, default: `false`. Add analysis of how long MultiQC takes to run to the report\n", "help_text": "Type: `boolean_true`, default: `false`. Add analysis of how long MultiQC takes to run to the report\n" , - "default": "False" + "default":false } @@ -290,7 +290,7 @@ "description": "Type: `boolean_true`, default: `false`. Increase output verbosity", "help_text": "Type: `boolean_true`, default: `false`. Increase output verbosity.\n" , - "default": "False" + "default":false } @@ -301,7 +301,7 @@ "description": "Type: `boolean_true`, default: `false`. Only show log warnings\n", "help_text": "Type: `boolean_true`, default: `false`. Only show log warnings\n" , - "default": "False" + "default":false } @@ -312,7 +312,7 @@ "description": "Type: `boolean_true`, default: `false`. Don\u0027t catch exceptions, run additional code checks to help development", "help_text": "Type: `boolean_true`, default: `false`. Don\u0027t catch exceptions, run additional code checks to help development.\n" , - "default": "False" + "default":false } @@ -323,7 +323,7 @@ "description": "Type: `boolean_true`, default: `false`. Development mode", "help_text": "Type: `boolean_true`, default: `false`. Development mode. Do not compress and minimise JS, export uncompressed plot data.\n" , - "default": "False" + "default":false } @@ -334,7 +334,7 @@ "description": "Type: `boolean_true`, default: `false`. Require all explicitly requested modules to have log files", "help_text": "Type: `boolean_true`, default: `false`. Require all explicitly requested modules to have log files. If not, MultiQC will exit with an error.\n" , - "default": "False" + "default":false } @@ -345,7 +345,7 @@ "description": "Type: `boolean_true`, default: `false`. Don\u0027t upload generated report to MegaQC, even if MegaQC options are found", "help_text": "Type: `boolean_true`, default: `false`. Don\u0027t upload generated report to MegaQC, even if MegaQC options are found.\n" , - "default": "False" + "default":false } @@ -356,7 +356,7 @@ "description": "Type: `boolean_true`, default: `false`. Disable coloured log output", "help_text": "Type: `boolean_true`, default: `false`. Disable coloured log output.\n" , - "default": "False" + "default":false } @@ -387,7 +387,7 @@ "description": "Type: `boolean_true`, default: `false`. Use only flat plots (static images)", "help_text": "Type: `boolean_true`, default: `false`. Use only flat plots (static images).\n" , - "default": "False" + "default":false } @@ -398,7 +398,7 @@ "description": "Type: `boolean_true`, default: `false`. Use only interactive plots (in-browser Javascript)", "help_text": "Type: `boolean_true`, default: `false`. Use only interactive plots (in-browser Javascript).\n" , - "default": "False" + "default":false } @@ -409,7 +409,7 @@ "description": "Type: `boolean_true`, default: `false`. Force the parsed data directory to be created", "help_text": "Type: `boolean_true`, default: `false`. Force the parsed data directory to be created.\n" , - "default": "False" + "default":false } @@ -420,7 +420,7 @@ "description": "Type: `boolean_true`, default: `false`. Prevent the parsed data directory from being created", "help_text": "Type: `boolean_true`, default: `false`. Prevent the parsed data directory from being created.\n" , - "default": "False" + "default":false } @@ -431,7 +431,7 @@ "description": "Type: `boolean_true`, default: `false`. Compress the data directory", "help_text": "Type: `boolean_true`, default: `false`. Compress the data directory.\n" , - "default": "False" + "default":false } @@ -454,7 +454,7 @@ "description": "Type: `boolean_true`, default: `false`. Creates PDF report with the \u0027simple\u0027 template", "help_text": "Type: `boolean_true`, default: `false`. Creates PDF report with the \u0027simple\u0027 template. Requires Pandoc to be installed.\n" , - "default": "False" + "default":false } diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/.config.vsh.yaml b/target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/.config.vsh.yaml similarity index 87% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/.config.vsh.yaml rename to target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/.config.vsh.yaml index c9523df..208326c 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/.config.vsh.yaml +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/.config.vsh.yaml @@ -1,6 +1,20 @@ name: "samtools_stats" namespace: "samtools" -version: "v0.1.0" +version: "main" +authors: +- name: "Emma Rousseau" + roles: + - "author" + - "maintainer" + info: + links: + email: "emma@data-intuitive.com" + github: "emmarousseau" + linkedin: "emmarousseau1" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Bioinformatician" argument_groups: - name: "Inputs" arguments: @@ -38,12 +52,16 @@ argument_groups: name: "--coverage" alternatives: - "-c" - description: "Coverage distribution min,max,step [1,1000,1].\n" + description: "Coverage distribution min;max;step. Default: [1, 1000, 1].\n" info: null + example: + - 1 + - 1000 + - 1 required: false direction: "input" multiple: true - multiple_sep: "," + multiple_sep: ";" - type: "boolean_true" name: "--remove_dups" alternatives: @@ -62,9 +80,10 @@ argument_groups: name: "--required_flag" alternatives: - "-f" - description: "Required flag, 0 for unset. See also `samtools flags`.\n" + description: "Required flag, 0 for unset. See also `samtools flags`. Default:\ + \ `\"0\"`.\n" info: null - default: + example: - "0" required: false direction: "input" @@ -74,9 +93,10 @@ argument_groups: name: "--filtering_flag" alternatives: - "-F" - description: "Filtering flag, 0 for unset. See also `samtools flags`.\n" + description: "Filtering flag, 0 for unset. See also `samtools flags`. Default:\ + \ `0`.\n" info: null - default: + example: - "0" required: false direction: "input" @@ -85,9 +105,9 @@ argument_groups: - type: "double" name: "--GC_depth" description: "The size of GC-depth bins (decreasing bin size increases memory\ - \ requirement).\n" + \ requirement). Default: `20000`.\n" info: null - default: + example: - 20000.0 required: false direction: "input" @@ -97,9 +117,9 @@ argument_groups: name: "--insert_size" alternatives: - "-i" - description: "Maximum insert size.\n" + description: "Maximum insert size. Default: `8000`.\n" info: null - default: + example: - 8000 required: false direction: "input" @@ -119,9 +139,10 @@ argument_groups: name: "--read_length" alternatives: - "-l" - description: "Include in the statistics only reads with the given read length.\n" + description: "Include in the statistics only reads with the given read length.\ + \ Default: `-1`.\n" info: null - default: + example: - -1 required: false direction: "input" @@ -131,9 +152,9 @@ argument_groups: name: "--most_inserts" alternatives: - "-m" - description: "Report only the main part of inserts.\n" + description: "Report only the main part of inserts. Default: `0.99`.\n" info: null - default: + example: - 0.99 required: false direction: "input" @@ -154,9 +175,9 @@ argument_groups: name: "--trim_quality" alternatives: - "-q" - description: "The BWA trimming parameter.\n" + description: "The BWA trimming parameter. Default: `0`.\n" info: null - default: + example: - 0 required: false direction: "input" @@ -218,9 +239,9 @@ argument_groups: alternatives: - "-g" description: "Only bases with coverage above this value will be included in the\ - \ target percentage computation.\n" + \ target percentage computation. Default: `0`.\n" info: null - default: + example: - 0 required: false direction: "input" @@ -253,7 +274,7 @@ argument_groups: - "-o" description: "Output file.\n" info: null - default: + example: - "out.txt" must_exist: true create_parent: true @@ -362,7 +383,7 @@ engines: id: "docker" image: "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1" target_registry: "images.viash-hub.com" - target_tag: "v0.1.0" + target_tag: "main" namespace_separator: "/" setup: - type: "docker" @@ -379,22 +400,23 @@ build_info: engine: "docker|native" output: "target/nextflow/samtools/samtools_stats" executable: "target/nextflow/samtools/samtools_stats/main.nf" - viash_version: "0.9.0-RC6" - git_commit: "b84b29747d0635f2ac83ea63b496be9a9edb6724" - git_remote: "https://github.com/viash-hub/biobox" + viash_version: "0.9.0" + git_commit: "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b" + git_remote: "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox" + git_tag: "v0.2.0-27-g952ff08" package_config: name: "biobox" - version: "v0.1.0" + version: "main" description: "A collection of bioinformatics tools for working with sequence data.\n" info: null - viash_version: "0.9.0-RC6" + viash_version: "0.9.0" source: "src" target: "target" config_mods: - ".requirements.commands := ['ps']\n" - ".engines += { type: \"native\" }" - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'" - - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" + - ".engines[.type == 'docker'].target_tag := 'main'" keywords: - "bioinformatics" - "modules" diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/main.nf b/target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/main.nf similarity index 96% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/main.nf rename to target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/main.nf index 167148f..958eac0 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/main.nf +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/main.nf @@ -1,13 +1,16 @@ -// samtools_stats v0.1.0 +// samtools_stats main // -// This wrapper script is auto-generated by viash 0.9.0-RC6 and is thus a -// derivative work thereof. This software comes with ABSOLUTELY NO WARRANTY from -// Data Intuitive. +// This wrapper script is auto-generated by viash 0.9.0 and is thus a derivative +// work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data +// Intuitive. // // The component may contain files which fall under a different license. The // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Emma Rousseau (author, maintainer) //////////////////////////// // VDSL3 helper functions // @@ -760,8 +763,11 @@ def runEach(Map args) { def fromState_ = args.fromState def toState_ = args.toState def filter_ = args.filter + def runIf_ = args.runIf def id_ = args.id + assert !runIf_ || runIf_ instanceof Closure: "runEach: must pass a Closure to runIf." + workflow runEachWf { take: input_ch main: @@ -783,7 +789,20 @@ def runEach(Map args) { [new_id] + tup.drop(1) } : filter_ch - def data_ch = id_ch | map{tup -> + def chPassthrough = null + def chRun = null + if (runIf_) { + def idRunIfBranch = id_ch.branch{ tup -> + run: runIf_(tup[0], tup[1], comp_) + passthrough: true + } + chPassthrough = idRunIfBranch.passthrough + chRun = idRunIfBranch.run + } else { + chRun = id_ch + chPassthrough = Channel.empty() + } + def data_ch = chRun | map{tup -> def new_data = tup[1] if (fromState_ instanceof Map) { new_data = fromState_.collectEntries{ key0, key1 -> @@ -821,8 +840,11 @@ def runEach(Map args) { [tup[0], new_state] + tup.drop(3) } : out_ch + + def return_ch = post_ch + | concat(chPassthrough) - post_ch + return_ch } // mix all results @@ -1598,8 +1620,8 @@ def findStates(Map params, Map config) { // construct renameMap if (args.rename_keys) { def renameMap = args.rename_keys.collectEntries{renameString -> - def split = renameString.split(";") - assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey,newKey:oldKey'" + def split = renameString.split(":") + assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey', or 'newKey:oldKey;newKey:oldKey' in case of multiple values" split } @@ -1709,7 +1731,9 @@ def publishStates(Map args) { def yamlFilename = yamlTemplate_ .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) // TODO: do the pathnames in state_ match up with the outputFilenames_? @@ -1780,7 +1804,9 @@ def publishStatesByConfig(Map args) { def yamlTemplate = params.containsKey("output_state") ? params.output_state : '$id.$key.state.yaml' def yamlFilename = yamlTemplate .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) def yamlDir = java.nio.file.Paths.get(yamlFilename).getParent() // the processed state is a list of [key, value, inputPath, outputFilename] tuples, where @@ -1822,7 +1848,9 @@ def publishStatesByConfig(Map args) { // instantiate the template def filename = filenameTemplate .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) if (par.multiple) { // if the parameter is multiple: true, the filename // should contain a wildcard '*' that is replaced with @@ -2626,30 +2654,31 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { tuple } - def chModifiedFiltered = workflowArgs.filter ? - chModified | filter{workflowArgs.filter(it)} : - chModified def chRun = null def chPassthrough = null if (workflowArgs.runIf) { - def runIfBranch = chModifiedFiltered.branch{ tup -> + def runIfBranch = chModified.branch{ tup -> run: workflowArgs.runIf(tup[0], tup[1]) passthrough: true } chRun = runIfBranch.run chPassthrough = runIfBranch.passthrough } else { - chRun = chModifiedFiltered + chRun = chModified chPassthrough = Channel.empty() } + def chRunFiltered = workflowArgs.filter ? + chRun | filter{workflowArgs.filter(it)} : + chRun + def chArgs = workflowArgs.fromState ? - chRun | map{ + chRunFiltered | map{ def new_data = workflowArgs.fromState(it.take(2)) [it[0], new_data] } : - chRun | map {tup -> tup.take(2)} + chRunFiltered | map {tup -> tup.take(2)} // fill in defaults def chArgsWithDefaults = chArgs @@ -2720,7 +2749,7 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { // | view{"chInitialOutput: ${it.take(3)}"} // join the output [prev_id, new_id, output] with the previous state [prev_id, state, ...] - def chNewState = safeJoin(chInitialOutput, chModifiedFiltered, key_) + def chNewState = safeJoin(chInitialOutput, chRunFiltered, key_) // input tuple format: [join_id, id, output, prev_state, ...] // output tuple format: [join_id, id, new_state, ...] | map{ tup -> @@ -2780,7 +2809,30 @@ meta = [ "config": processConfig(readJsonBlob('''{ "name" : "samtools_stats", "namespace" : "samtools", - "version" : "v0.1.0", + "version" : "main", + "authors" : [ + { + "name" : "Emma Rousseau", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "links" : { + "email" : "emma@data-intuitive.com", + "github" : "emmarousseau", + "linkedin" : "emmarousseau1" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Bioinformatician" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Inputs", @@ -2824,11 +2876,16 @@ meta = [ "alternatives" : [ "-c" ], - "description" : "Coverage distribution min,max,step [1,1000,1].\n", + "description" : "Coverage distribution min;max;step. Default: [1, 1000, 1].\n", + "example" : [ + 1, + 1000, + 1 + ], "required" : false, "direction" : "input", "multiple" : true, - "multiple_sep" : "," + "multiple_sep" : ";" }, { "type" : "boolean_true", @@ -2854,8 +2911,8 @@ meta = [ "alternatives" : [ "-f" ], - "description" : "Required flag, 0 for unset. See also `samtools flags`.\n", - "default" : [ + "description" : "Required flag, 0 for unset. See also `samtools flags`. Default: `\\"0\\"`.\n", + "example" : [ "0" ], "required" : false, @@ -2869,8 +2926,8 @@ meta = [ "alternatives" : [ "-F" ], - "description" : "Filtering flag, 0 for unset. See also `samtools flags`.\n", - "default" : [ + "description" : "Filtering flag, 0 for unset. See also `samtools flags`. Default: `0`.\n", + "example" : [ "0" ], "required" : false, @@ -2881,8 +2938,8 @@ meta = [ { "type" : "double", "name" : "--GC_depth", - "description" : "The size of GC-depth bins (decreasing bin size increases memory requirement).\n", - "default" : [ + "description" : "The size of GC-depth bins (decreasing bin size increases memory requirement). Default: `20000`.\n", + "example" : [ 20000.0 ], "required" : false, @@ -2896,8 +2953,8 @@ meta = [ "alternatives" : [ "-i" ], - "description" : "Maximum insert size.\n", - "default" : [ + "description" : "Maximum insert size. Default: `8000`.\n", + "example" : [ 8000 ], "required" : false, @@ -2923,8 +2980,8 @@ meta = [ "alternatives" : [ "-l" ], - "description" : "Include in the statistics only reads with the given read length.\n", - "default" : [ + "description" : "Include in the statistics only reads with the given read length. Default: `-1`.\n", + "example" : [ -1 ], "required" : false, @@ -2938,8 +2995,8 @@ meta = [ "alternatives" : [ "-m" ], - "description" : "Report only the main part of inserts.\n", - "default" : [ + "description" : "Report only the main part of inserts. Default: `0.99`.\n", + "example" : [ 0.99 ], "required" : false, @@ -2965,8 +3022,8 @@ meta = [ "alternatives" : [ "-q" ], - "description" : "The BWA trimming parameter.\n", - "default" : [ + "description" : "The BWA trimming parameter. Default: `0`.\n", + "example" : [ 0 ], "required" : false, @@ -3038,8 +3095,8 @@ meta = [ "alternatives" : [ "-g" ], - "description" : "Only bases with coverage above this value will be included in the target percentage computation.\n", - "default" : [ + "description" : "Only bases with coverage above this value will be included in the target percentage computation. Default: `0`.\n", + "example" : [ 0 ], "required" : false, @@ -3079,7 +3136,7 @@ meta = [ "-o" ], "description" : "Output file.\n", - "default" : [ + "example" : [ "out.txt" ], "must_exist" : true, @@ -3216,7 +3273,7 @@ meta = [ "id" : "docker", "image" : "quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1", "target_registry" : "images.viash-hub.com", - "target_tag" : "v0.1.0", + "target_tag" : "main", "namespace_separator" : "/", "setup" : [ { @@ -3237,22 +3294,23 @@ meta = [ "runner" : "nextflow", "engine" : "docker|native", "output" : "target/nextflow/samtools/samtools_stats", - "viash_version" : "0.9.0-RC6", - "git_commit" : "b84b29747d0635f2ac83ea63b496be9a9edb6724", - "git_remote" : "https://github.com/viash-hub/biobox" + "viash_version" : "0.9.0", + "git_commit" : "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b", + "git_remote" : "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox", + "git_tag" : "v0.2.0-27-g952ff08" }, "package_config" : { "name" : "biobox", - "version" : "v0.1.0", + "version" : "main", "description" : "A collection of bioinformatics tools for working with sequence data.\n", - "viash_version" : "0.9.0-RC6", + "viash_version" : "0.9.0", "source" : "src", "target" : "target", "config_mods" : [ ".requirements.commands := ['ps']\n", ".engines += { type: \\"native\\" }", ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'", - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" + ".engines[.type == 'docker'].target_tag := 'main'" ], "keywords" : [ "bioinformatics", @@ -3334,6 +3392,9 @@ set -e [[ "\\$par_sparse" == "false" ]] && unset par_sparse [[ "\\$par_remove_overlaps" == "false" ]] && unset par_remove_overlaps +# change the coverage input from X;X;X to X,X,X +par_coverage=\\$(echo "\\$par_coverage" | tr ';' ',') + samtools stats \\\\ \\${par_coverage:+-c "\\$par_coverage"} \\\\ \\${par_remove_dups:+-d} \\\\ @@ -3438,7 +3499,11 @@ def vdsl3WorkflowFactory(Map args, Map meta, String rawScript) { val = val.join(par.multiple_sep) } if (par.direction == "output" && par.type == "file") { - val = val.replaceAll('\\$id', id).replaceAll('\\$key', key) + val = val + .replaceAll('\\$id', id) + .replaceAll('\\$\\{id\\}', id) + .replaceAll('\\$key', key) + .replaceAll('\\$\\{key\\}', key) } [parName, val] } @@ -3569,7 +3634,8 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def createParentStr = meta.config.allArguments .findAll { it.type == "file" && it.direction == "output" && it.create_parent } .collect { par -> - "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent \\\"\" + (args[\"${par.plainName}\"] instanceof String ? args[\"${par.plainName}\"] : args[\"${par.plainName}\"].join('\" \"')) + \"\\\"\" : \"\" }" + def contents = "args[\"${par.plainName}\"] instanceof List ? args[\"${par.plainName}\"].join('\" \"') : args[\"${par.plainName}\"]" + "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent '\" + escapeText(${contents}) + \"'\" : \"\" }" } .join("\n") @@ -3577,8 +3643,8 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def inputFileExports = meta.config.allArguments .findAll { it.type == "file" && it.direction.toLowerCase() == "input" } .collect { par -> - def viash_par_contents = "(viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName})" - "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}=\\\"\" + ${viash_par_contents} + \"\\\"\"}" + def contents = "viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName}" + "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}='\" + escapeText(${contents}) + \"'\"}" } // NOTE: if using docker, use /tmp instead of tmpDir! @@ -3615,6 +3681,7 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def procStr = """nextflow.enable.dsl=2 | + |def escapeText = { s -> s.toString().replaceAll("'", "'\\\"'\\\"'") } |process $procKey {$drctvStrs |input: | tuple val(id)$inputPaths, val(args), path(resourcesDir, stageAs: ".viash_meta_resources") @@ -3626,10 +3693,9 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { |$stub |\"\"\" |script:$assertStr - |def escapeText = { s -> s.toString().replaceAll('([`"])', '\\\\\\\\\$1') } |def parInject = args | .findAll{key, value -> value != null} - | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}=\\\"\${escapeText(value)}\\\""} + | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}='\${escapeText(value)}'"} | .join("\\n") |\"\"\" |# meta exports @@ -3714,7 +3780,7 @@ meta["defaults"] = [ "container" : { "registry" : "images.viash-hub.com", "image" : "vsh/biobox/samtools/samtools_stats", - "tag" : "v0.1.0" + "tag" : "main" }, "tag" : "$id" }'''), diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/nextflow.config b/target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/nextflow.config similarity index 98% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/nextflow.config rename to target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/nextflow.config index d746263..733a57c 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/nextflow.config +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/nextflow.config @@ -2,8 +2,9 @@ manifest { name = 'samtools/samtools_stats' mainScript = 'main.nf' nextflowVersion = '!>=20.12.1-edge' - version = 'v0.1.0' + version = 'main' description = 'Reports alignment summary statistics for a BAM file.' + author = 'Emma Rousseau' } process.container = 'nextflow/bash:latest' diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/nextflow_schema.json b/target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/nextflow_schema.json similarity index 81% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/nextflow_schema.json rename to target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/nextflow_schema.json index ceb3b49..4e161ad 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/nextflow_schema.json +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/nextflow_schema.json @@ -47,8 +47,8 @@ "coverage": { "type": "string", - "description": "Type: List of `integer`, multiple_sep: `\",\"`. Coverage distribution min,max,step [1,1000,1]", - "help_text": "Type: List of `integer`, multiple_sep: `\",\"`. Coverage distribution min,max,step [1,1000,1].\n" + "description": "Type: List of `integer`, example: `1;1000;1`, multiple_sep: `\";\"`. Coverage distribution min;max;step", + "help_text": "Type: List of `integer`, example: `1;1000;1`, multiple_sep: `\";\"`. Coverage distribution min;max;step. Default: [1, 1000, 1].\n" } @@ -60,7 +60,7 @@ "description": "Type: `boolean_true`, default: `false`. Exclude from statistics reads marked as duplicates", "help_text": "Type: `boolean_true`, default: `false`. Exclude from statistics reads marked as duplicates.\n" , - "default": "False" + "default":false } @@ -71,7 +71,7 @@ "description": "Type: `boolean_true`, default: `false`. Use a customized index file", "help_text": "Type: `boolean_true`, default: `false`. Use a customized index file.\n" , - "default": "False" + "default":false } @@ -79,10 +79,9 @@ "required_flag": { "type": "string", - "description": "Type: `string`, default: `0`. Required flag, 0 for unset", - "help_text": "Type: `string`, default: `0`. Required flag, 0 for unset. See also `samtools flags`.\n" - , - "default": "0" + "description": "Type: `string`, example: `0`. Required flag, 0 for unset", + "help_text": "Type: `string`, example: `0`. Required flag, 0 for unset. See also `samtools flags`. Default: `\"0\"`.\n" + } @@ -90,10 +89,9 @@ "filtering_flag": { "type": "string", - "description": "Type: `string`, default: `0`. Filtering flag, 0 for unset", - "help_text": "Type: `string`, default: `0`. Filtering flag, 0 for unset. See also `samtools flags`.\n" - , - "default": "0" + "description": "Type: `string`, example: `0`. Filtering flag, 0 for unset", + "help_text": "Type: `string`, example: `0`. Filtering flag, 0 for unset. See also `samtools flags`. Default: `0`.\n" + } @@ -101,10 +99,9 @@ "GC_depth": { "type": "number", - "description": "Type: `double`, default: `20000.0`. The size of GC-depth bins (decreasing bin size increases memory requirement)", - "help_text": "Type: `double`, default: `20000.0`. The size of GC-depth bins (decreasing bin size increases memory requirement).\n" - , - "default": "20000.0" + "description": "Type: `double`, example: `20000.0`. The size of GC-depth bins (decreasing bin size increases memory requirement)", + "help_text": "Type: `double`, example: `20000.0`. The size of GC-depth bins (decreasing bin size increases memory requirement). Default: `20000`.\n" + } @@ -112,10 +109,9 @@ "insert_size": { "type": "integer", - "description": "Type: `integer`, default: `8000`. Maximum insert size", - "help_text": "Type: `integer`, default: `8000`. Maximum insert size.\n" - , - "default": "8000" + "description": "Type: `integer`, example: `8000`. Maximum insert size", + "help_text": "Type: `integer`, example: `8000`. Maximum insert size. Default: `8000`.\n" + } @@ -133,10 +129,9 @@ "read_length": { "type": "integer", - "description": "Type: `integer`, default: `-1`. Include in the statistics only reads with the given read length", - "help_text": "Type: `integer`, default: `-1`. Include in the statistics only reads with the given read length.\n" - , - "default": "-1" + "description": "Type: `integer`, example: `-1`. Include in the statistics only reads with the given read length", + "help_text": "Type: `integer`, example: `-1`. Include in the statistics only reads with the given read length. Default: `-1`.\n" + } @@ -144,10 +139,9 @@ "most_inserts": { "type": "number", - "description": "Type: `double`, default: `0.99`. Report only the main part of inserts", - "help_text": "Type: `double`, default: `0.99`. Report only the main part of inserts.\n" - , - "default": "0.99" + "description": "Type: `double`, example: `0.99`. Report only the main part of inserts", + "help_text": "Type: `double`, example: `0.99`. Report only the main part of inserts. Default: `0.99`.\n" + } @@ -165,10 +159,9 @@ "trim_quality": { "type": "integer", - "description": "Type: `integer`, default: `0`. The BWA trimming parameter", - "help_text": "Type: `integer`, default: `0`. The BWA trimming parameter.\n" - , - "default": "0" + "description": "Type: `integer`, example: `0`. The BWA trimming parameter", + "help_text": "Type: `integer`, example: `0`. The BWA trimming parameter. Default: `0`.\n" + } @@ -209,7 +202,7 @@ "description": "Type: `boolean_true`, default: `false`. Suppress outputting IS rows where there are no insertions", "help_text": "Type: `boolean_true`, default: `false`. Suppress outputting IS rows where there are no insertions.\n" , - "default": "False" + "default":false } @@ -220,7 +213,7 @@ "description": "Type: `boolean_true`, default: `false`. Remove overlaps of paired-end reads from coverage and base count computations", "help_text": "Type: `boolean_true`, default: `false`. Remove overlaps of paired-end reads from coverage and base count computations.\n" , - "default": "False" + "default":false } @@ -228,10 +221,9 @@ "cov_threshold": { "type": "integer", - "description": "Type: `integer`, default: `0`. Only bases with coverage above this value will be included in the target percentage computation", - "help_text": "Type: `integer`, default: `0`. Only bases with coverage above this value will be included in the target percentage computation.\n" - , - "default": "0" + "description": "Type: `integer`, example: `0`. Only bases with coverage above this value will be included in the target percentage computation", + "help_text": "Type: `integer`, example: `0`. Only bases with coverage above this value will be included in the target percentage computation. Default: `0`.\n" + } @@ -269,10 +261,10 @@ "output": { "type": "string", - "description": "Type: `file`, required, default: `$id.$key.output.txt`. Output file", - "help_text": "Type: `file`, required, default: `$id.$key.output.txt`. Output file.\n" + "description": "Type: `file`, required, default: `$id.$key.output.txt`, example: `out.txt`. Output file", + "help_text": "Type: `file`, required, default: `$id.$key.output.txt`, example: `out.txt`. Output file.\n" , - "default": "$id.$key.output.txt" + "default":"$id.$key.output.txt" } diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/.config.vsh.yaml b/target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/.config.vsh.yaml similarity index 63% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/.config.vsh.yaml rename to target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/.config.vsh.yaml index 41253ce..86213b4 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/.config.vsh.yaml +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/.config.vsh.yaml @@ -1,13 +1,48 @@ name: "star_align_reads" namespace: "star" -version: "v0.1.0" +version: "main" +authors: +- name: "Angela Oliveira Pisco" + roles: + - "author" + info: + role: "Contributor" + links: + github: "aopisco" + orcid: "0000-0003-0142-2355" + linkedin: "aopisco" + organizations: + - name: "Insitro" + href: "https://insitro.com" + role: "Director of Computational Biology" + - name: "Open Problems" + href: "https://openproblems.bio" + role: "Core Member" +- name: "Robrecht Cannoodt" + roles: + - "author" + - "maintainer" + info: + links: + email: "robrecht@data-intuitive.com" + github: "rcannood" + orcid: "0000-0003-3641-729X" + linkedin: "robrechtcannoodt" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Science Engineer" + - name: "Open Problems" + href: "https://openproblems.bio" + role: "Core Member" argument_groups: - name: "Run Parameters" arguments: - type: "integer" - name: "--runRNGseed" + name: "--run_rng_seed" description: "random number generator seed." - info: null + info: + orig_name: "--runRNGseed" example: - 777 required: false @@ -17,10 +52,11 @@ argument_groups: - name: "Genome Parameters" arguments: - type: "file" - name: "--genomeDir" + name: "--genome_dir" description: "path to the directory where genome files are stored (for --runMode\ \ alignReads) or will be generated (for --runMode generateGenome)" - info: null + info: + orig_name: "--genomeDir" example: - "./GenomeDir" must_exist: true @@ -30,7 +66,7 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--genomeLoad" + name: "--genome_load" description: "mode of shared memory usage for the genome files. Only used with\ \ --runMode alignReads.\n\n- LoadAndKeep ... load genome into shared and\ \ keep it in memory after run\n- LoadAndRemove ... load genome into shared\ @@ -39,7 +75,8 @@ argument_groups: \ ... do not map anything, just remove loaded genome from memory\n- NoSharedMemory\ \ ... do not use shared memory, each job will have its own private copy of\ \ the genome" - info: null + info: + orig_name: "--genomeLoad" example: - "NoSharedMemory" required: false @@ -47,13 +84,14 @@ argument_groups: multiple: false multiple_sep: ";" - type: "file" - name: "--genomeFastaFiles" + name: "--genome_fasta_files" description: "path(s) to the fasta files with the genome sequences, separated\ \ by spaces. These files should be plain text FASTA files, they *cannot* be\ \ zipped.\n\nRequired for the genome generation (--runMode genomeGenerate).\ \ Can also be used in the mapping (--runMode alignReads) to add extra (new)\ \ sequences to the genome (e.g. spike-ins)." - info: null + info: + orig_name: "--genomeFastaFiles" must_exist: true create_parent: true required: false @@ -61,10 +99,11 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--genomeFileSizes" + name: "--genome_file_sizes" description: "genome files exact sizes in bytes. Typically, this should not be\ \ defined by the user." - info: null + info: + orig_name: "--genomeFileSizes" example: - 0 required: false @@ -72,21 +111,23 @@ argument_groups: multiple: true multiple_sep: ";" - type: "string" - name: "--genomeTransformOutput" + name: "--genome_transform_output" description: "which output to transform back to original genome\n\n- SAM ...\ \ SAM/BAM alignments\n- SJ ... splice junctions (SJ.out.tab)\n- Quant \ - \ ... quantifications (from --quantMode option)\n- None ... no transformation\ + \ ... quantifications (from --quant_mode option)\n- None ... no transformation\ \ of the output" - info: null + info: + orig_name: "--genomeTransformOutput" required: false direction: "input" multiple: true multiple_sep: ";" - type: "string" - name: "--genomeChrSetMitochondrial" + name: "--genome_chr_set_mitochondrial" description: "names of the mitochondrial chromosomes. Presently only used for\ \ STARsolo statistics output/" - info: null + info: + orig_name: "--genomeChrSetMitochondrial" example: - "chrM" - "M" @@ -98,19 +139,21 @@ argument_groups: - name: "Splice Junctions Database" arguments: - type: "string" - name: "--sjdbFileChrStartEnd" + name: "--sjdb_file_chr_start_end" description: "path to the files with genomic coordinates (chr start \ \ end strand) for the splice junction introns. Multiple files can be supplied\ \ and will be concatenated." - info: null + info: + orig_name: "--sjdbFileChrStartEnd" required: false direction: "input" multiple: true multiple_sep: ";" - type: "file" - name: "--sjdbGTFfile" + name: "--sjdb_gtf_file" description: "path to the GTF file with annotations" - info: null + info: + orig_name: "--sjdbGTFfile" must_exist: true create_parent: true required: false @@ -118,18 +161,20 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--sjdbGTFchrPrefix" + name: "--sjdb_gtf_chr_prefix" description: "prefix for chromosome names in a GTF file (e.g. 'chr' for using\ \ ENSMEBL annotations with UCSC genomes)" - info: null + info: + orig_name: "--sjdbGTFchrPrefix" required: false direction: "input" multiple: false multiple_sep: ";" - type: "string" - name: "--sjdbGTFfeatureExon" + name: "--sjdb_gtf_feature_exon" description: "feature type in GTF file to be used as exons for building transcripts" - info: null + info: + orig_name: "--sjdbGTFfeatureExon" example: - "exon" required: false @@ -137,10 +182,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--sjdbGTFtagExonParentTranscript" + name: "--sjdb_gtf_tag_exon_parent_transcript" description: "GTF attribute name for parent transcript ID (default \"transcript_id\"\ \ works for GTF files)" - info: null + info: + orig_name: "--sjdbGTFtagExonParentTranscript" example: - "transcript_id" required: false @@ -148,10 +194,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--sjdbGTFtagExonParentGene" + name: "--sjdb_gtf_tag_exon_parent_gene" description: "GTF attribute name for parent gene ID (default \"gene_id\" works\ \ for GTF files)" - info: null + info: + orig_name: "--sjdbGTFtagExonParentGene" example: - "gene_id" required: false @@ -159,9 +206,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--sjdbGTFtagExonParentGeneName" + name: "--sjdb_gtf_tag_exon_parent_gene_name" description: "GTF attribute name for parent gene name" - info: null + info: + orig_name: "--sjdbGTFtagExonParentGeneName" example: - "gene_name" required: false @@ -169,9 +217,10 @@ argument_groups: multiple: true multiple_sep: ";" - type: "string" - name: "--sjdbGTFtagExonParentGeneType" + name: "--sjdb_gtf_tag_exon_parent_gene_type" description: "GTF attribute name for parent gene type" - info: null + info: + orig_name: "--sjdbGTFtagExonParentGeneType" example: - "gene_type" - "gene_biotype" @@ -180,10 +229,11 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--sjdbOverhang" + name: "--sjdb_overhang" description: "length of the donor/acceptor sequence on each side of the junctions,\ \ ideally = (mate_length - 1)" - info: null + info: + orig_name: "--sjdbOverhang" example: - 100 required: false @@ -191,9 +241,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--sjdbScore" + name: "--sjdb_score" description: "extra alignment score for alignments that cross database junctions" - info: null + info: + orig_name: "--sjdbScore" example: - 2 required: false @@ -201,12 +252,13 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--sjdbInsertSave" + name: "--sjdb_insert_save" description: "which files to save when sjdb junctions are inserted on the fly\ \ at the mapping step\n\n- Basic ... only small junction / transcript files\n\ - All ... all files including big Genome, SA and SAindex - this will create\ \ a complete genome directory" - info: null + info: + orig_name: "--sjdbInsertSave" example: - "Basic" required: false @@ -216,10 +268,11 @@ argument_groups: - name: "Variation parameters" arguments: - type: "string" - name: "--varVCFfile" + name: "--var_vcf_file" description: "path to the VCF file that contains variation data. The 10th column\ \ should contain the genotype information, e.g. 0/1" - info: null + info: + orig_name: "--varVCFfile" required: false direction: "input" multiple: false @@ -227,12 +280,13 @@ argument_groups: - name: "Read Parameters" arguments: - type: "string" - name: "--readFilesType" + name: "--read_files_type" description: "format of input read files\n\n- Fastx ... FASTA or FASTQ\n\ - - SAM SE ... SAM or BAM single-end reads; for BAM use --readFilesCommand\ + - SAM SE ... SAM or BAM single-end reads; for BAM use --read_files_command\ \ samtools view\n- SAM PE ... SAM or BAM paired-end reads; for BAM use\ - \ --readFilesCommand samtools view" - info: null + \ --read_files_command samtools view" + info: + orig_name: "--readFilesType" example: - "Fastx" required: false @@ -240,11 +294,12 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--readFilesSAMattrKeep" - description: "for --readFilesType SAM SE/PE, which SAM tags to keep in the output\ + name: "--read_files_sam_attr_keep" + description: "for --read_files_type SAM SE/PE, which SAM tags to keep in the output\ \ BAM, e.g.: --readFilesSAMtagsKeep RG PL\n\n- All ... keep all tags\n-\ \ None ... do not keep any tags" - info: null + info: + orig_name: "--readFilesSAMattrKeep" example: - "All" required: false @@ -252,7 +307,7 @@ argument_groups: multiple: true multiple_sep: ";" - type: "file" - name: "--readFilesManifest" + name: "--read_files_manifest" description: "path to the \"manifest\" file with the names of read files. The\ \ manifest file should contain 3 tab-separated columns:\n\npaired-end reads:\ \ read1_file_name $tab$ read2_file_name $tab$ read_group_line.\nsingle-end reads:\ @@ -261,7 +316,8 @@ argument_groups: \ ID:, it can only contain one ID field, and ID: will be added to it.\nIf read_group_line\ \ starts with ID:, it can contain several fields separated by $tab$, and all\ \ fields will be be copied verbatim into SAM @RG header line." - info: null + info: + orig_name: "--readFilesManifest" must_exist: true create_parent: true required: false @@ -269,29 +325,32 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--readFilesPrefix" + name: "--read_files_prefix" description: "prefix for the read files names, i.e. it will be added in front\ \ of the strings in --readFilesIn" - info: null + info: + orig_name: "--readFilesPrefix" required: false direction: "input" multiple: false multiple_sep: ";" - type: "string" - name: "--readFilesCommand" + name: "--read_files_command" description: "command line to execute for each of the input file. This command\ \ should generate FASTA or FASTQ text and send it to stdout\n\nFor example:\ \ zcat - to uncompress .gz files, bzcat - to uncompress .bz2 files, etc." - info: null + info: + orig_name: "--readFilesCommand" required: false direction: "input" multiple: true multiple_sep: ";" - type: "integer" - name: "--readMapNumber" + name: "--read_map_number" description: "number of reads to map from the beginning of the file\n\n-1: map\ \ all reads" - info: null + info: + orig_name: "--readMapNumber" example: - -1 required: false @@ -299,10 +358,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--readMatesLengthsIn" + name: "--read_mates_lengths_in" description: "Equal/NotEqual - lengths of names,sequences,qualities for both mates\ \ are the same / not the same. NotEqual is safe in all situations." - info: null + info: + orig_name: "--readMatesLengthsIn" example: - "NotEqual" required: false @@ -310,10 +370,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--readNameSeparator" + name: "--read_name_separator" description: "character(s) separating the part of the read names that will be\ \ trimmed in output (read name after space is always trimmed)" - info: null + info: + orig_name: "--readNameSeparator" example: - "/" required: false @@ -321,10 +382,11 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--readQualityScoreBase" + name: "--read_quality_score_base" description: "number to be subtracted from the ASCII code to get Phred quality\ \ score" - info: null + info: + orig_name: "--readQualityScoreBase" example: - 33 required: false @@ -334,13 +396,14 @@ argument_groups: - name: "Read Clipping" arguments: - type: "string" - name: "--clipAdapterType" + name: "--clip_adapter_type" description: "adapter clipping type\n\n- Hamming ... adapter clipping based on\ \ Hamming distance, with the number of mismatches controlled by --clip5pAdapterMMp\n\ - CellRanger4 ... 5p and 3p adapter clipping similar to CellRanger4. Utilizes\ \ Opal package by Martin Sosic: https://github.com/Martinsos/opal\n- None ...\ \ no adapter clipping, all other clip* parameters are disregarded" - info: null + info: + orig_name: "--clipAdapterType" example: - "Hamming" required: false @@ -348,10 +411,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--clip3pNbases" + name: "--clip3p_nbases" description: "number(s) of bases to clip from 3p of each mate. If one value is\ \ given, it will be assumed the same for both mates." - info: null + info: + orig_name: "--clip3pNbases" example: - 0 required: false @@ -359,20 +423,22 @@ argument_groups: multiple: true multiple_sep: ";" - type: "string" - name: "--clip3pAdapterSeq" + name: "--clip3p_adapter_seq" description: "adapter sequences to clip from 3p of each mate. If one value is\ \ given, it will be assumed the same for both mates.\n\n- polyA ... polyA sequence\ \ with the length equal to read length" - info: null + info: + orig_name: "--clip3pAdapterSeq" required: false direction: "input" multiple: true multiple_sep: ";" - type: "double" - name: "--clip3pAdapterMMp" + name: "--clip3p_adapter_mm_p" description: "max proportion of mismatches for 3p adapter clipping for each mate.\ \ If one value is given, it will be assumed the same for both mates." - info: null + info: + orig_name: "--clip3pAdapterMMp" example: - 0.1 required: false @@ -380,10 +446,11 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--clip3pAfterAdapterNbases" + name: "--clip3p_after_adapter_nbases" description: "number of bases to clip from 3p of each mate after the adapter clipping.\ \ If one value is given, it will be assumed the same for both mates." - info: null + info: + orig_name: "--clip3pAfterAdapterNbases" example: - 0 required: false @@ -391,10 +458,11 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--clip5pNbases" + name: "--clip5p_nbases" description: "number(s) of bases to clip from 5p of each mate. If one value is\ \ given, it will be assumed the same for both mates." - info: null + info: + orig_name: "--clip5pNbases" example: - 0 required: false @@ -404,9 +472,10 @@ argument_groups: - name: "Limits" arguments: - type: "long" - name: "--limitGenomeGenerateRAM" + name: "--limit_genome_generate_ram" description: "maximum available RAM (bytes) for genome generation" - info: null + info: + orig_name: "--limitGenomeGenerateRAM" example: - 31000000000 required: false @@ -414,9 +483,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "long" - name: "--limitIObufferSize" + name: "--limit_io_buffer_size" description: "max available buffers size (bytes) for input/output, per thread" - info: null + info: + orig_name: "--limitIObufferSize" example: - 30000000 - 50000000 @@ -425,10 +495,11 @@ argument_groups: multiple: true multiple_sep: ";" - type: "long" - name: "--limitOutSAMoneReadBytes" + name: "--limit_out_sam_one_read_bytes" description: "max size of the SAM record (bytes) for one read. Recommended value:\ \ >(2*(LengthMate1+LengthMate2+100)*outFilterMultimapNmax" - info: null + info: + orig_name: "--limitOutSAMoneReadBytes" example: - 100000 required: false @@ -436,9 +507,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--limitOutSJoneRead" + name: "--limit_out_sj_one_read" description: "max number of junctions for one read (including all multi-mappers)" - info: null + info: + orig_name: "--limitOutSJoneRead" example: - 1000 required: false @@ -446,9 +518,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--limitOutSJcollapsed" + name: "--limit_out_sj_collapsed" description: "max number of collapsed junctions" - info: null + info: + orig_name: "--limitOutSJcollapsed" example: - 1000000 required: false @@ -456,11 +529,12 @@ argument_groups: multiple: false multiple_sep: ";" - type: "long" - name: "--limitBAMsortRAM" + name: "--limit_bam_sort_ram" description: "maximum available RAM (bytes) for sorting BAM. If =0, it will be\ - \ set to the genome index size. 0 value can only be used with --genomeLoad NoSharedMemory\ - \ option." - info: null + \ set to the genome index size. 0 value can only be used with --genome_load\ + \ NoSharedMemory option." + info: + orig_name: "--limitBAMsortRAM" example: - 0 required: false @@ -468,11 +542,12 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--limitSjdbInsertNsj" + name: "--limit_sjdb_insert_nsj" description: "maximum number of junctions to be inserted to the genome on the\ \ fly at the mapping stage, including those from annotations and those detected\ \ in the 1st step of the 2-pass run" - info: null + info: + orig_name: "--limitSjdbInsertNsj" example: - 1000000 required: false @@ -480,9 +555,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--limitNreadsSoft" + name: "--limit_nreads_soft" description: "soft limit on the number of reads" - info: null + info: + orig_name: "--limitNreadsSoft" example: - -1 required: false @@ -492,25 +568,27 @@ argument_groups: - name: "Output: general" arguments: - type: "string" - name: "--outTmpKeep" + name: "--out_tmp_keep" description: "whether to keep the temporary files after STAR runs is finished\n\ \n- None ... remove all temporary files\n- All ... keep all files" - info: null + info: + orig_name: "--outTmpKeep" required: false direction: "input" multiple: false multiple_sep: ";" - type: "string" - name: "--outStd" + name: "--out_std" description: "which output will be directed to stdout (standard out)\n\n- Log\ \ ... log messages\n- SAM ... alignments\ \ in SAM format (which normally are output to Aligned.out.sam file), normal\ \ standard output will go into Log.std.out\n- BAM_Unsorted ... alignments\ - \ in BAM format, unsorted. Requires --outSAMtype BAM Unsorted\n- BAM_SortedByCoordinate\ - \ ... alignments in BAM format, sorted by coordinate. Requires --outSAMtype\ + \ in BAM format, unsorted. Requires --out_sam_type BAM Unsorted\n- BAM_SortedByCoordinate\ + \ ... alignments in BAM format, sorted by coordinate. Requires --out_sam_type\ \ BAM SortedByCoordinate\n- BAM_Quant ... alignments to transcriptome\ - \ in BAM format, unsorted. Requires --quantMode TranscriptomeSAM" - info: null + \ in BAM format, unsorted. Requires --quant_mode TranscriptomeSAM" + info: + orig_name: "--outStd" example: - "Log" required: false @@ -518,20 +596,22 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--outReadsUnmapped" + name: "--out_reads_unmapped" description: "output of unmapped and partially mapped (i.e. mapped only one mate\ \ of a paired end read) reads in separate file(s).\n\n- None ... no output\n\ - Fastx ... output in separate fasta/fastq files, Unmapped.out.mate1/2" - info: null + info: + orig_name: "--outReadsUnmapped" required: false direction: "input" multiple: false multiple_sep: ";" - type: "integer" - name: "--outQSconversionAdd" + name: "--out_qs_conversion_add" description: "add this number to the quality score (e.g. to convert from Illumina\ \ to Sanger, use -31)" - info: null + info: + orig_name: "--outQSconversionAdd" example: - 0 required: false @@ -539,13 +619,14 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--outMultimapperOrder" + name: "--out_multimapper_order" description: "order of multimapping alignments in the output files\n\n- Old_2.4\ \ ... quasi-random order used before 2.5.0\n- Random \ \ ... random order of alignments for each multi-mapper. Read mates (pairs)\ \ are always adjacent, all alignment for each read stay together. This option\ \ will become default in the future releases." - info: null + info: + orig_name: "--outMultimapperOrder" example: - "Old_2.4" required: false @@ -555,13 +636,14 @@ argument_groups: - name: "Output: SAM and BAM" arguments: - type: "string" - name: "--outSAMtype" + name: "--out_sam_type" description: "type of SAM/BAM output\n\n1st word:\n- BAM ... output BAM without\ \ sorting\n- SAM ... output SAM without sorting\n- None ... no SAM/BAM output\n\ 2nd, 3rd:\n- Unsorted ... standard unsorted\n- SortedByCoordinate\ \ ... sorted by coordinate. This option will allocate extra memory for sorting\ - \ which can be specified by --limitBAMsortRAM." - info: null + \ which can be specified by --limit_bam_sort_ram." + info: + orig_name: "--outSAMtype" example: - "SAM" required: false @@ -569,10 +651,11 @@ argument_groups: multiple: true multiple_sep: ";" - type: "string" - name: "--outSAMmode" + name: "--out_sam_mode" description: "mode of SAM output\n\n- None ... no SAM output\n- Full ... full\ \ SAM output\n- NoQS ... full SAM but without quality scores" - info: null + info: + orig_name: "--outSAMmode" example: - "Full" required: false @@ -580,24 +663,25 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--outSAMstrandField" + name: "--out_sam_strand_field" description: "Cufflinks-like strand field flag\n\n- None ... not used\n\ - intronMotif ... strand derived from the intron motif. This option changes\ \ the output alignments: reads with inconsistent and/or non-canonical introns\ \ are filtered out." - info: null + info: + orig_name: "--outSAMstrandField" required: false direction: "input" multiple: false multiple_sep: ";" - type: "string" - name: "--outSAMattributes" + name: "--out_sam_attributes" description: "a string of desired SAM attributes, in the order desired for the\ \ output SAM. Tags can be listed in any combination/order.\n\n***Presets:\n\ - None ... no attributes\n- Standard ... NH HI AS nM\n- All \ \ ... NH HI AS nM NM MD jM jI MC ch\n***Alignment:\n- NH ... number\ \ of loci the reads maps to: =1 for unique mappers, >1 for multimappers. Standard\ - \ SAM tag.\n- HI ... multiple alignment index, starts with --outSAMattrIHstart\ + \ SAM tag.\n- HI ... multiple alignment index, starts with --out_sam_attr_ih_start\ \ (=1 by default). Standard SAM tag.\n- AS ... local alignment score,\ \ +1/-1 for matches/mismateches, score* penalties for indels and gaps. For PE\ \ reads, total score for two mates. Stadnard SAM tag.\n- nM ... number\ @@ -609,27 +693,28 @@ argument_groups: \ 1: GT/AG, 2: CT/AC, 3: GC/AG, 4: CT/GC, 5: AT/AC, 6: GT/AT. If splice junctions\ \ database is used, and a junction is annotated, 20 is added to its motif value.\n\ - jI ... start and end of introns for all junctions (1-based).\n- XS\ - \ ... alignment strand according to --outSAMstrandField.\n- MC \ - \ ... mate's CIGAR string. Standard SAM tag.\n- ch ... marks all\ - \ segment of all chimeric alingments for --chimOutType WithinBAM output.\n-\ - \ cN ... number of bases clipped from the read ends: 5' and 3'\n***Variation:\n\ + \ ... alignment strand according to --out_sam_strand_field.\n- MC \ + \ ... mate's CIGAR string. Standard SAM tag.\n- ch ... marks\ + \ all segment of all chimeric alingments for --chim_out_type WithinBAM output.\n\ + - cN ... number of bases clipped from the read ends: 5' and 3'\n***Variation:\n\ - vA ... variant allele\n- vG ... genomic coordinate of the\ \ variant overlapped by the read.\n- vW ... 1 - alignment passes WASP\ \ filtering; 2,3,4,5,6,7 - alignment does not pass WASP filtering. Requires\ - \ --waspOutputMode SAMtag.\n- ha ... haplotype (1/2) when mapping to\ - \ the diploid genome. Requires genome generated with --genomeTransformType Diploid\ - \ .\n***STARsolo:\n- CR CY UR UY ... sequences and quality scores of cell barcodes\ - \ and UMIs for the solo* demultiplexing.\n- GX GN ... gene ID and gene\ - \ name for unique-gene reads.\n- gx gn ... gene IDs and gene names for\ - \ unique- and multi-gene reads.\n- CB UB ... error-corrected cell barcodes\ - \ and UMIs for solo* demultiplexing. Requires --outSAMtype BAM SortedByCoordinate.\n\ - - sM ... assessment of CB and UMI.\n- sS ... sequence of the\ - \ entire barcode (CB,UMI,adapter).\n- sQ ... quality of the entire\ - \ barcode.\n- sF ... type of feature overlap and number of features\ - \ for each alignment\n***Unsupported/undocumented:\n- rB ... alignment\ - \ block read/genomic coordinates.\n- vR ... read coordinate of the\ - \ variant." - info: null + \ --wasp_output_mode SAMtag.\n- ha ... haplotype (1/2) when mapping\ + \ to the diploid genome. Requires genome generated with --genomeTransformType\ + \ Diploid .\n***STARsolo:\n- CR CY UR UY ... sequences and quality scores of\ + \ cell barcodes and UMIs for the solo* demultiplexing.\n- GX GN ... gene\ + \ ID and gene name for unique-gene reads.\n- gx gn ... gene IDs and gene\ + \ names for unique- and multi-gene reads.\n- CB UB ... error-corrected\ + \ cell barcodes and UMIs for solo* demultiplexing. Requires --out_sam_type BAM\ + \ SortedByCoordinate.\n- sM ... assessment of CB and UMI.\n- sS \ + \ ... sequence of the entire barcode (CB,UMI,adapter).\n- sQ \ + \ ... quality of the entire barcode.\n- sF ... type of feature overlap\ + \ and number of features for each alignment\n***Unsupported/undocumented:\n\ + - rB ... alignment block read/genomic coordinates.\n- vR ...\ + \ read coordinate of the variant." + info: + orig_name: "--outSAMattributes" example: - "Standard" required: false @@ -637,10 +722,11 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--outSAMattrIHstart" + name: "--out_sam_attr_ih_start" description: "start value for the IH attribute. 0 may be required by some downstream\ \ software, such as Cufflinks or StringTie." - info: null + info: + orig_name: "--outSAMattrIHstart" example: - 1 required: false @@ -648,24 +734,26 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--outSAMunmapped" + name: "--out_sam_unmapped" description: "output of unmapped reads in the SAM format\n\n1st word:\n- None\ \ ... no output\n- Within ... output unmapped reads within the main SAM file\ \ (i.e. Aligned.out.sam)\n2nd word:\n- KeepPairs ... record unmapped mate for\ \ each alignment, and, in case of unsorted output, keep it adjacent to its mapped\ \ mate. Only affects multi-mapping reads." - info: null + info: + orig_name: "--outSAMunmapped" required: false direction: "input" multiple: true multiple_sep: ";" - type: "string" - name: "--outSAMorder" + name: "--out_sam_order" description: "type of sorting for the SAM output\n\nPaired: one mate after the\ \ other for all paired alignments\nPairedKeepInputOrder: one mate after the\ \ other for all paired alignments, the order is kept the same as in the input\ \ FASTQ files" - info: null + info: + orig_name: "--outSAMorder" example: - "Paired" required: false @@ -673,12 +761,13 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--outSAMprimaryFlag" + name: "--out_sam_primary_flag" description: "which alignments are considered primary - all others will be marked\ \ with 0x100 bit in the FLAG\n\n- OneBestScore ... only one alignment with the\ \ best score is primary\n- AllBestScore ... all alignments with the best score\ \ are primary" - info: null + info: + orig_name: "--outSAMprimaryFlag" example: - "OneBestScore" required: false @@ -686,11 +775,12 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--outSAMreadID" + name: "--out_sam_read_id" description: "read ID record type\n\n- Standard ... first word (until space) from\ \ the FASTx read ID line, removing /1,/2 from the end\n- Number ... read number\ \ (index) in the FASTx file" - info: null + info: + orig_name: "--outSAMreadID" example: - "Standard" required: false @@ -698,9 +788,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outSAMmapqUnique" + name: "--out_sam_mapq_unique" description: "0 to 255: the MAPQ value for unique mappers" - info: null + info: + orig_name: "--outSAMmapqUnique" example: - 255 required: false @@ -708,12 +799,13 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outSAMflagOR" + name: "--out_sam_flag_or" description: "0 to 65535: sam FLAG will be bitwise OR'd with this value, i.e.\ \ FLAG=FLAG | outSAMflagOR. This is applied after all flags have been set by\ \ STAR, and after outSAMflagAND. Can be used to set specific bits that are not\ \ set otherwise." - info: null + info: + orig_name: "--outSAMflagOR" example: - 0 required: false @@ -721,12 +813,13 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outSAMflagAND" + name: "--out_sam_flag_and" description: "0 to 65535: sam FLAG will be bitwise AND'd with this value, i.e.\ \ FLAG=FLAG & outSAMflagOR. This is applied after all flags have been set by\ \ STAR, but before outSAMflagOR. Can be used to unset specific bits that are\ \ not set otherwise." - info: null + info: + orig_name: "--outSAMflagAND" example: - 65535 required: false @@ -734,62 +827,68 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--outSAMattrRGline" + name: "--out_sam_attr_rg_line" description: "SAM/BAM read group line. The first word contains the read group\ - \ identifier and must start with \"ID:\", e.g. --outSAMattrRGline ID:xxx CN:yy\ - \ \"DS:z z z\".\n\nxxx will be added as RG tag to each output alignment. Any\ - \ spaces in the tag values have to be double quoted.\nComma separated RG lines\ - \ correspons to different (comma separated) input files in --readFilesIn. Commas\ - \ have to be surrounded by spaces, e.g.\n--outSAMattrRGline ID:xxx , ID:zzz\ - \ \"DS:z z\" , ID:yyy DS:yyyy" - info: null + \ identifier and must start with \"ID:\", e.g. --out_sam_attr_rg_line ID:xxx\ + \ CN:yy \"DS:z z z\".\n\nxxx will be added as RG tag to each output alignment.\ + \ Any spaces in the tag values have to be double quoted.\nComma separated RG\ + \ lines correspons to different (comma separated) input files in --readFilesIn.\ + \ Commas have to be surrounded by spaces, e.g.\n--out_sam_attr_rg_line ID:xxx\ + \ , ID:zzz \"DS:z z\" , ID:yyy DS:yyyy" + info: + orig_name: "--outSAMattrRGline" required: false direction: "input" multiple: true multiple_sep: ";" - type: "string" - name: "--outSAMheaderHD" + name: "--out_sam_header_hd" description: "@HD (header) line of the SAM header" - info: null + info: + orig_name: "--outSAMheaderHD" required: false direction: "input" multiple: true multiple_sep: ";" - type: "string" - name: "--outSAMheaderPG" + name: "--out_sam_header_pg" description: "extra @PG (software) line of the SAM header (in addition to STAR)" - info: null + info: + orig_name: "--outSAMheaderPG" required: false direction: "input" multiple: true multiple_sep: ";" - type: "string" - name: "--outSAMheaderCommentFile" + name: "--out_sam_header_comment_file" description: "path to the file with @CO (comment) lines of the SAM header" - info: null + info: + orig_name: "--outSAMheaderCommentFile" required: false direction: "input" multiple: false multiple_sep: ";" - type: "string" - name: "--outSAMfilter" + name: "--out_sam_filter" description: "filter the output into main SAM/BAM files\n\n- KeepOnlyAddedReferences\ \ ... only keep the reads for which all alignments are to the extra reference\ - \ sequences added with --genomeFastaFiles at the mapping stage.\n- KeepAllAddedReferences\ - \ ... keep all alignments to the extra reference sequences added with --genomeFastaFiles\ + \ sequences added with --genome_fasta_files at the mapping stage.\n- KeepAllAddedReferences\ + \ ... keep all alignments to the extra reference sequences added with --genome_fasta_files\ \ at the mapping stage." - info: null + info: + orig_name: "--outSAMfilter" required: false direction: "input" multiple: true multiple_sep: ";" - type: "integer" - name: "--outSAMmultNmax" + name: "--out_sam_mult_nmax" description: "max number of multiple alignments for a read that will be output\ \ to the SAM/BAM files. Note that if this value is not equal to -1, the top\ - \ scoring alignment will be output first\n\n- -1 ... all alignments (up to --outFilterMultimapNmax)\ + \ scoring alignment will be output first\n\n- -1 ... all alignments (up to --out_filter_multimap_nmax)\ \ will be output" - info: null + info: + orig_name: "--outSAMmultNmax" example: - -1 required: false @@ -797,13 +896,14 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outSAMtlen" + name: "--out_sam_tlen" description: "calculation method for the TLEN field in the SAM/BAM files\n\n-\ \ 1 ... leftmost base of the (+)strand mate to rightmost base of the (-)mate.\ \ (+)sign for the (+)strand mate\n- 2 ... leftmost base of any mate to rightmost\ \ base of any mate. (+)sign for the mate with the leftmost base. This is different\ \ from 1 for overlapping mates with protruding ends" - info: null + info: + orig_name: "--outSAMtlen" example: - 1 required: false @@ -811,10 +911,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outBAMcompression" + name: "--out_bam_compression" description: "-1 to 10 BAM compression level, -1=default compression (6?), 0=no\ \ compression, 10=maximum compression" - info: null + info: + orig_name: "--outBAMcompression" example: - 1 required: false @@ -822,9 +923,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outBAMsortingThreadN" + name: "--out_bam_sorting_thread_n" description: ">=0: number of threads for BAM sorting. 0 will default to min(6,--runThreadN)." - info: null + info: + orig_name: "--outBAMsortingThreadN" example: - 0 required: false @@ -832,9 +934,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outBAMsortingBinsN" + name: "--out_bam_sorting_bins_n" description: ">0: number of genome bins for coordinate-sorting" - info: null + info: + orig_name: "--outBAMsortingBinsN" example: - 50 required: false @@ -844,23 +947,25 @@ argument_groups: - name: "BAM processing" arguments: - type: "string" - name: "--bamRemoveDuplicatesType" + name: "--bam_remove_duplicates_type" description: "mark duplicates in the BAM file, for now only works with (i) sorted\ \ BAM fed with inputBAMfile, and (ii) for paired-end alignments only\n\n- -\ \ ... no duplicate removal/marking\n- UniqueIdentical\ \ ... mark all multimappers, and duplicate unique mappers. The coordinates,\ \ FLAG, CIGAR must be identical\n- UniqueIdenticalNotMulti ... mark duplicate\ \ unique mappers but not multimappers." - info: null + info: + orig_name: "--bamRemoveDuplicatesType" required: false direction: "input" multiple: false multiple_sep: ";" - type: "integer" - name: "--bamRemoveDuplicatesMate2basesN" + name: "--bam_remove_duplicates_mate2bases_n" description: "number of bases from the 5' of mate 2 to use in collapsing (e.g.\ \ for RAMPAGE)" - info: null + info: + orig_name: "--bamRemoveDuplicatesMate2basesN" example: - 0 required: false @@ -870,23 +975,25 @@ argument_groups: - name: "Output Wiggle" arguments: - type: "string" - name: "--outWigType" + name: "--out_wig_type" description: "type of signal output, e.g. \"bedGraph\" OR \"bedGraph read1_5p\"\ - . Requires sorted BAM: --outSAMtype BAM SortedByCoordinate .\n\n1st word:\n\ + . Requires sorted BAM: --out_sam_type BAM SortedByCoordinate .\n\n1st word:\n\ - None ... no signal output\n- bedGraph ... bedGraph format\n- wiggle\ \ ... wiggle format\n2nd word:\n- read1_5p ... signal from only 5' of\ \ the 1st read, useful for CAGE/RAMPAGE etc\n- read2 ... signal from only\ \ 2nd read" - info: null + info: + orig_name: "--outWigType" required: false direction: "input" multiple: true multiple_sep: ";" - type: "string" - name: "--outWigStrand" + name: "--out_wig_strand" description: "strandedness of wiggle/bedGraph output\n\n- Stranded ... separate\ \ strands, str1 and str2\n- Unstranded ... collapsed strands" - info: null + info: + orig_name: "--outWigStrand" example: - "Stranded" required: false @@ -894,19 +1001,21 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--outWigReferencesPrefix" + name: "--out_wig_references_prefix" description: "prefix matching reference names to include in the output wiggle\ \ file, e.g. \"chr\", default \"-\" - include all references" - info: null + info: + orig_name: "--outWigReferencesPrefix" required: false direction: "input" multiple: false multiple_sep: ";" - type: "string" - name: "--outWigNorm" + name: "--out_wig_norm" description: "type of normalization for the signal\n\n- RPM ... reads per million\ \ of mapped reads\n- None ... no normalization, \"raw\" counts" - info: null + info: + orig_name: "--outWigNorm" example: - "RPM" required: false @@ -916,11 +1025,12 @@ argument_groups: - name: "Output Filtering" arguments: - type: "string" - name: "--outFilterType" + name: "--out_filter_type" description: "type of filtering\n\n- Normal ... standard filtering using only\ \ current alignment\n- BySJout ... keep only those reads that contain junctions\ \ that passed filtering into SJ.out.tab" - info: null + info: + orig_name: "--outFilterType" example: - "Normal" required: false @@ -928,9 +1038,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outFilterMultimapScoreRange" + name: "--out_filter_multimap_score_range" description: "the score range below the maximum score for multimapping alignments" - info: null + info: + orig_name: "--outFilterMultimapScoreRange" example: - 1 required: false @@ -938,12 +1049,13 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outFilterMultimapNmax" + name: "--out_filter_multimap_nmax" description: "maximum number of loci the read is allowed to map to. Alignments\ \ (all of them) will be output only if the read maps to no more loci than this\ \ value.\n\nOtherwise no alignments will be output, and the read will be counted\ \ as \"mapped to too many loci\" in the Log.final.out ." - info: null + info: + orig_name: "--outFilterMultimapNmax" example: - 10 required: false @@ -951,10 +1063,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outFilterMismatchNmax" + name: "--out_filter_mismatch_nmax" description: "alignment will be output only if it has no more mismatches than\ \ this value." - info: null + info: + orig_name: "--outFilterMismatchNmax" example: - 10 required: false @@ -962,10 +1075,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "double" - name: "--outFilterMismatchNoverLmax" + name: "--out_filter_mismatch_nover_lmax" description: "alignment will be output only if its ratio of mismatches to *mapped*\ \ length is less than or equal to this value." - info: null + info: + orig_name: "--outFilterMismatchNoverLmax" example: - 0.3 required: false @@ -973,10 +1087,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "double" - name: "--outFilterMismatchNoverReadLmax" + name: "--out_filter_mismatch_nover_read_lmax" description: "alignment will be output only if its ratio of mismatches to *read*\ \ length is less than or equal to this value." - info: null + info: + orig_name: "--outFilterMismatchNoverReadLmax" example: - 1.0 required: false @@ -984,10 +1099,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outFilterScoreMin" + name: "--out_filter_score_min" description: "alignment will be output only if its score is higher than or equal\ \ to this value." - info: null + info: + orig_name: "--outFilterScoreMin" example: - 0 required: false @@ -995,10 +1111,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "double" - name: "--outFilterScoreMinOverLread" + name: "--out_filter_score_min_over_lread" description: "same as outFilterScoreMin, but normalized to read length (sum of\ \ mates' lengths for paired-end reads)" - info: null + info: + orig_name: "--outFilterScoreMinOverLread" example: - 0.66 required: false @@ -1006,10 +1123,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outFilterMatchNmin" + name: "--out_filter_match_nmin" description: "alignment will be output only if the number of matched bases is\ \ higher than or equal to this value." - info: null + info: + orig_name: "--outFilterMatchNmin" example: - 0 required: false @@ -1017,10 +1135,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "double" - name: "--outFilterMatchNminOverLread" + name: "--out_filter_match_nmin_over_lread" description: "sam as outFilterMatchNmin, but normalized to the read length (sum\ \ of mates' lengths for paired-end reads)." - info: null + info: + orig_name: "--outFilterMatchNminOverLread" example: - 0.66 required: false @@ -1028,24 +1147,26 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--outFilterIntronMotifs" + name: "--out_filter_intron_motifs" description: "filter alignment using their motifs\n\n- None \ \ ... no filtering\n- RemoveNoncanonical ... filter out\ \ alignments that contain non-canonical junctions\n- RemoveNoncanonicalUnannotated\ \ ... filter out alignments that contain non-canonical unannotated junctions\ \ when using annotated splice junctions database. The annotated non-canonical\ \ junctions will be kept." - info: null + info: + orig_name: "--outFilterIntronMotifs" required: false direction: "input" multiple: false multiple_sep: ";" - type: "string" - name: "--outFilterIntronStrands" + name: "--out_filter_intron_strands" description: "filter alignments\n\n- RemoveInconsistentStrands ... remove\ \ alignments that have junctions with inconsistent strands\n- None \ \ ... no filtering" - info: null + info: + orig_name: "--outFilterIntronStrands" example: - "RemoveInconsistentStrands" required: false @@ -1055,10 +1176,11 @@ argument_groups: - name: "Output splice junctions (SJ.out.tab)" arguments: - type: "string" - name: "--outSJtype" + name: "--out_sj_type" description: "type of splice junction output\n\n- Standard ... standard SJ.out.tab\ \ output\n- None ... no splice junction output" - info: null + info: + orig_name: "--outSJtype" example: - "Standard" required: false @@ -1068,11 +1190,12 @@ argument_groups: - name: "Output Filtering: Splice Junctions" arguments: - type: "string" - name: "--outSJfilterReads" + name: "--out_sj_filter_reads" description: "which reads to consider for collapsed splice junctions output\n\n\ - All ... all reads, unique- and multi-mappers\n- Unique ... uniquely mapping\ \ reads only" - info: null + info: + orig_name: "--outSJfilterReads" example: - "All" required: false @@ -1080,12 +1203,13 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--outSJfilterOverhangMin" + name: "--out_sj_filter_overhang_min" description: "minimum overhang length for splice junctions on both sides for:\ \ (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif,\ \ (4) AT/AC and GT/AT motif. -1 means no output for that motif\n\ndoes not apply\ \ to annotated junctions" - info: null + info: + orig_name: "--outSJfilterOverhangMin" example: - 30 - 12 @@ -1096,13 +1220,14 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--outSJfilterCountUniqueMin" + name: "--out_sj_filter_count_unique_min" description: "minimum uniquely mapping read count per junction for: (1) non-canonical\ \ motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and\ \ GT/AT motif. -1 means no output for that motif\n\nJunctions are output if\ \ one of outSJfilterCountUniqueMin OR outSJfilterCountTotalMin conditions are\ \ satisfied\ndoes not apply to annotated junctions" - info: null + info: + orig_name: "--outSJfilterCountUniqueMin" example: - 3 - 1 @@ -1113,13 +1238,14 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--outSJfilterCountTotalMin" + name: "--out_sj_filter_count_total_min" description: "minimum total (multi-mapping+unique) read count per junction for:\ \ (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif,\ \ (4) AT/AC and GT/AT motif. -1 means no output for that motif\n\nJunctions\ \ are output if one of outSJfilterCountUniqueMin OR outSJfilterCountTotalMin\ \ conditions are satisfied\ndoes not apply to annotated junctions" - info: null + info: + orig_name: "--outSJfilterCountTotalMin" example: - 3 - 1 @@ -1130,10 +1256,11 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--outSJfilterDistToOtherSJmin" + name: "--out_sj_filter_dist_to_other_sj_min" description: "minimum allowed distance to other junctions' donor/acceptor\n\n\ does not apply to annotated junctions" - info: null + info: + orig_name: "--outSJfilterDistToOtherSJmin" example: - 10 - 0 @@ -1144,12 +1271,13 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--outSJfilterIntronMaxVsReadN" + name: "--out_sj_filter_intron_max_vs_read_n" description: "maximum gap allowed for junctions supported by 1,2,3,,,N reads\n\ \ni.e. by default junctions supported by 1 read can have gaps <=50000b, by 2\ \ reads: <=100000b, by 3 reads: <=200000. by >=4 reads any gap <=alignIntronMax\n\ does not apply to annotated junctions" - info: null + info: + orig_name: "--outSJfilterIntronMaxVsReadN" example: - 50000 - 100000 @@ -1161,9 +1289,10 @@ argument_groups: - name: "Scoring" arguments: - type: "integer" - name: "--scoreGap" + name: "--score_gap" description: "splice junction penalty (independent on intron motif)" - info: null + info: + orig_name: "--scoreGap" example: - 0 required: false @@ -1171,9 +1300,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--scoreGapNoncan" + name: "--score_gap_noncan" description: "non-canonical junction penalty (in addition to scoreGap)" - info: null + info: + orig_name: "--scoreGapNoncan" example: - -8 required: false @@ -1181,9 +1311,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--scoreGapGCAG" + name: "--score_gap_gcag" description: "GC/AG and CT/GC junction penalty (in addition to scoreGap)" - info: null + info: + orig_name: "--scoreGapGCAG" example: - -4 required: false @@ -1191,9 +1322,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--scoreGapATAC" + name: "--score_gap_atac" description: "AT/AC and GT/AT junction penalty (in addition to scoreGap)" - info: null + info: + orig_name: "--scoreGapATAC" example: - -8 required: false @@ -1201,10 +1333,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--scoreGenomicLengthLog2scale" + name: "--score_genomic_length_log2scale" description: "extra score logarithmically scaled with genomic length of the alignment:\ \ scoreGenomicLengthLog2scale*log2(genomicLength)" - info: null + info: + orig_name: "--scoreGenomicLengthLog2scale" example: - 0 required: false @@ -1212,9 +1345,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--scoreDelOpen" + name: "--score_del_open" description: "deletion open penalty" - info: null + info: + orig_name: "--scoreDelOpen" example: - -2 required: false @@ -1222,9 +1356,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--scoreDelBase" + name: "--score_del_base" description: "deletion extension penalty per base (in addition to scoreDelOpen)" - info: null + info: + orig_name: "--scoreDelBase" example: - -2 required: false @@ -1232,9 +1367,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--scoreInsOpen" + name: "--score_ins_open" description: "insertion open penalty" - info: null + info: + orig_name: "--scoreInsOpen" example: - -2 required: false @@ -1242,9 +1378,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--scoreInsBase" + name: "--score_ins_base" description: "insertion extension penalty per base (in addition to scoreInsOpen)" - info: null + info: + orig_name: "--scoreInsBase" example: - -2 required: false @@ -1252,10 +1389,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--scoreStitchSJshift" + name: "--score_stitch_sj_shift" description: "maximum score reduction while searching for SJ boundaries in the\ \ stitching step" - info: null + info: + orig_name: "--scoreStitchSJshift" example: - 1 required: false @@ -1265,10 +1403,11 @@ argument_groups: - name: "Alignments and Seeding" arguments: - type: "integer" - name: "--seedSearchStartLmax" + name: "--seed_search_start_lmax" description: "defines the search start point through the read - the read is split\ \ into pieces no longer than this value" - info: null + info: + orig_name: "--seedSearchStartLmax" example: - 50 required: false @@ -1276,10 +1415,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "double" - name: "--seedSearchStartLmaxOverLread" + name: "--seed_search_start_lmax_over_lread" description: "seedSearchStartLmax normalized to read length (sum of mates' lengths\ \ for paired-end reads)" - info: null + info: + orig_name: "--seedSearchStartLmaxOverLread" example: - 1.0 required: false @@ -1287,10 +1427,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--seedSearchLmax" + name: "--seed_search_lmax" description: "defines the maximum length of the seeds, if =0 seed length is not\ \ limited" - info: null + info: + orig_name: "--seedSearchLmax" example: - 0 required: false @@ -1298,10 +1439,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--seedMultimapNmax" + name: "--seed_multimap_nmax" description: "only pieces that map fewer than this value are utilized in the stitching\ \ procedure" - info: null + info: + orig_name: "--seedMultimapNmax" example: - 10000 required: false @@ -1309,9 +1451,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--seedPerReadNmax" + name: "--seed_per_read_nmax" description: "max number of seeds per read" - info: null + info: + orig_name: "--seedPerReadNmax" example: - 1000 required: false @@ -1319,9 +1462,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--seedPerWindowNmax" + name: "--seed_per_window_nmax" description: "max number of seeds per window" - info: null + info: + orig_name: "--seedPerWindowNmax" example: - 50 required: false @@ -1329,9 +1473,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--seedNoneLociPerWindow" + name: "--seed_none_loci_per_window" description: "max number of one seed loci per window" - info: null + info: + orig_name: "--seedNoneLociPerWindow" example: - 10 required: false @@ -1339,9 +1484,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--seedSplitMin" + name: "--seed_split_min" description: "min length of the seed sequences split by Ns or mate gap" - info: null + info: + orig_name: "--seedSplitMin" example: - 12 required: false @@ -1349,9 +1495,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--seedMapMin" + name: "--seed_map_min" description: "min length of seeds to be mapped" - info: null + info: + orig_name: "--seedMapMin" example: - 5 required: false @@ -1359,10 +1506,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--alignIntronMin" + name: "--align_intron_min" description: "minimum intron size, genomic gap is considered intron if its length>=alignIntronMin,\ \ otherwise it is considered Deletion" - info: null + info: + orig_name: "--alignIntronMin" example: - 21 required: false @@ -1370,10 +1518,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--alignIntronMax" + name: "--align_intron_max" description: "maximum intron size, if 0, max intron size will be determined by\ \ (2^winBinNbits)*winAnchorDistNbins" - info: null + info: + orig_name: "--alignIntronMax" example: - 0 required: false @@ -1381,10 +1530,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--alignMatesGapMax" + name: "--align_mates_gap_max" description: "maximum gap between two mates, if 0, max intron gap will be determined\ \ by (2^winBinNbits)*winAnchorDistNbins" - info: null + info: + orig_name: "--alignMatesGapMax" example: - 0 required: false @@ -1392,9 +1542,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--alignSJoverhangMin" + name: "--align_sj_overhang_min" description: "minimum overhang (i.e. block size) for spliced alignments" - info: null + info: + orig_name: "--alignSJoverhangMin" example: - 5 required: false @@ -1402,11 +1553,12 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--alignSJstitchMismatchNmax" + name: "--align_sj_stitch_mismatch_nmax" description: "maximum number of mismatches for stitching of the splice junctions\ \ (-1: no limit).\n\n(1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3)\ \ GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif." - info: null + info: + orig_name: "--alignSJstitchMismatchNmax" example: - 0 - -1 @@ -1417,10 +1569,11 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--alignSJDBoverhangMin" + name: "--align_sjdb_overhang_min" description: "minimum overhang (i.e. block size) for annotated (sjdb) spliced\ \ alignments" - info: null + info: + orig_name: "--alignSJDBoverhangMin" example: - 3 required: false @@ -1428,9 +1581,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--alignSplicedMateMapLmin" + name: "--align_spliced_mate_map_lmin" description: "minimum mapped length for a read mate that is spliced" - info: null + info: + orig_name: "--alignSplicedMateMapLmin" example: - 0 required: false @@ -1438,9 +1592,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "double" - name: "--alignSplicedMateMapLminOverLmate" + name: "--align_spliced_mate_map_lmin_over_lmate" description: "alignSplicedMateMapLmin normalized to mate length" - info: null + info: + orig_name: "--alignSplicedMateMapLminOverLmate" example: - 0.66 required: false @@ -1448,9 +1603,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--alignWindowsPerReadNmax" + name: "--align_windows_per_read_nmax" description: "max number of windows per read" - info: null + info: + orig_name: "--alignWindowsPerReadNmax" example: - 10000 required: false @@ -1458,9 +1614,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--alignTranscriptsPerWindowNmax" + name: "--align_transcripts_per_window_nmax" description: "max number of transcripts per window" - info: null + info: + orig_name: "--alignTranscriptsPerWindowNmax" example: - 100 required: false @@ -1468,9 +1625,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--alignTranscriptsPerReadNmax" + name: "--align_transcripts_per_read_nmax" description: "max number of different alignments per read to consider" - info: null + info: + orig_name: "--alignTranscriptsPerReadNmax" example: - 10000 required: false @@ -1478,14 +1636,15 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--alignEndsType" + name: "--align_ends_type" description: "type of read ends alignment\n\n- Local ... standard\ \ local alignment with soft-clipping allowed\n- EndToEnd ... force\ \ end-to-end read alignment, do not soft-clip\n- Extend5pOfRead1 ... fully\ \ extend only the 5p of the read1, all other ends: local alignment\n- Extend5pOfReads12\ \ ... fully extend only the 5p of the both read1 and read2, all other ends:\ \ local alignment" - info: null + info: + orig_name: "--alignEndsType" example: - "Local" required: false @@ -1493,14 +1652,15 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--alignEndsProtrude" + name: "--align_ends_protrude" description: "allow protrusion of alignment ends, i.e. start (end) of the +strand\ \ mate downstream of the start (end) of the -strand mate\n\n1st word: int: maximum\ \ number of protrusion bases allowed\n2nd word: string:\n- \ \ ConcordantPair ... report alignments with non-zero protrusion as concordant\ \ pairs\n- DiscordantPair ... report alignments with non-zero\ \ protrusion as discordant pairs" - info: null + info: + orig_name: "--alignEndsProtrude" example: - "0 ConcordantPair" required: false @@ -1508,10 +1668,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--alignSoftClipAtReferenceEnds" + name: "--align_soft_clip_at_reference_ends" description: "allow the soft-clipping of the alignments past the end of the chromosomes\n\ \n- Yes ... allow\n- No ... prohibit, useful for compatibility with Cufflinks" - info: null + info: + orig_name: "--alignSoftClipAtReferenceEnds" example: - "Yes" required: false @@ -1519,10 +1680,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--alignInsertionFlush" + name: "--align_insertion_flush" description: "how to flush ambiguous insertion positions\n\n- None ... insertions\ \ are not flushed\n- Right ... insertions are flushed to the right" - info: null + info: + orig_name: "--alignInsertionFlush" required: false direction: "input" multiple: false @@ -1530,11 +1692,12 @@ argument_groups: - name: "Paired-End reads" arguments: - type: "integer" - name: "--peOverlapNbasesMin" + name: "--pe_overlap_nbases_min" description: "minimum number of overlapping bases to trigger mates merging and\ \ realignment. Specify >0 value to switch on the \"merginf of overlapping mates\"\ \ algorithm." - info: null + info: + orig_name: "--peOverlapNbasesMin" example: - 0 required: false @@ -1542,9 +1705,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "double" - name: "--peOverlapMMp" + name: "--pe_overlap_mm_p" description: "maximum proportion of mismatched bases in the overlap area" - info: null + info: + orig_name: "--peOverlapMMp" example: - 0.01 required: false @@ -1554,9 +1718,10 @@ argument_groups: - name: "Windows, Anchors, Binning" arguments: - type: "integer" - name: "--winAnchorMultimapNmax" + name: "--win_anchor_multimap_nmax" description: "max number of loci anchors are allowed to map to" - info: null + info: + orig_name: "--winAnchorMultimapNmax" example: - 50 required: false @@ -1564,10 +1729,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--winBinNbits" + name: "--win_bin_nbits" description: "=log2(winBin), where winBin is the size of the bin for the windows/clustering,\ \ each window will occupy an integer number of bins." - info: null + info: + orig_name: "--winBinNbits" example: - 16 required: false @@ -1575,10 +1741,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--winAnchorDistNbins" + name: "--win_anchor_dist_nbins" description: "max number of bins between two anchors that allows aggregation of\ \ anchors into one window" - info: null + info: + orig_name: "--winAnchorDistNbins" example: - 9 required: false @@ -1586,10 +1753,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--winFlankNbins" + name: "--win_flank_nbins" description: "log2(winFlank), where win Flank is the size of the left and right\ \ flanking regions for each window" - info: null + info: + orig_name: "--winFlankNbins" example: - 4 required: false @@ -1597,10 +1765,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "double" - name: "--winReadCoverageRelativeMin" + name: "--win_read_coverage_relative_min" description: "minimum relative coverage of the read sequence by the seeds in a\ \ window, for STARlong algorithm only." - info: null + info: + orig_name: "--winReadCoverageRelativeMin" example: - 0.5 required: false @@ -1608,10 +1777,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--winReadCoverageBasesMin" + name: "--win_read_coverage_bases_min" description: "minimum number of bases covered by the seeds in a window , for STARlong\ \ algorithm only." - info: null + info: + orig_name: "--winReadCoverageBasesMin" example: - 0 required: false @@ -1621,14 +1791,15 @@ argument_groups: - name: "Chimeric Alignments" arguments: - type: "string" - name: "--chimOutType" + name: "--chim_out_type" description: "type of chimeric output\n\n- Junctions ... Chimeric.out.junction\n\ - SeparateSAMold ... output old SAM into separate Chimeric.out.sam file\n-\ \ WithinBAM ... output into main aligned BAM files (Aligned.*.bam)\n-\ \ WithinBAM HardClip ... (default) hard-clipping in the CIGAR for supplemental\ \ chimeric alignments (default if no 2nd word is present)\n- WithinBAM SoftClip\ \ ... soft-clipping in the CIGAR for supplemental chimeric alignments" - info: null + info: + orig_name: "--chimOutType" example: - "Junctions" required: false @@ -1636,9 +1807,10 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--chimSegmentMin" + name: "--chim_segment_min" description: "minimum length of chimeric segment length, if ==0, no chimeric output" - info: null + info: + orig_name: "--chimSegmentMin" example: - 0 required: false @@ -1646,9 +1818,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--chimScoreMin" + name: "--chim_score_min" description: "minimum total (summed) score of the chimeric segments" - info: null + info: + orig_name: "--chimScoreMin" example: - 0 required: false @@ -1656,10 +1829,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--chimScoreDropMax" + name: "--chim_score_drop_max" description: "max drop (difference) of chimeric score (the sum of scores of all\ \ chimeric segments) from the read length" - info: null + info: + orig_name: "--chimScoreDropMax" example: - 20 required: false @@ -1667,10 +1841,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--chimScoreSeparation" + name: "--chim_score_separation" description: "minimum difference (separation) between the best chimeric score\ \ and the next one" - info: null + info: + orig_name: "--chimScoreSeparation" example: - 10 required: false @@ -1678,9 +1853,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--chimScoreJunctionNonGTAG" + name: "--chim_score_junction_non_gtag" description: "penalty for a non-GT/AG chimeric junction" - info: null + info: + orig_name: "--chimScoreJunctionNonGTAG" example: - -1 required: false @@ -1688,9 +1864,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--chimJunctionOverhangMin" + name: "--chim_junction_overhang_min" description: "minimum overhang for a chimeric junction" - info: null + info: + orig_name: "--chimJunctionOverhangMin" example: - 20 required: false @@ -1698,9 +1875,10 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--chimSegmentReadGapMax" + name: "--chim_segment_read_gap_max" description: "maximum gap in the read sequence between chimeric segments" - info: null + info: + orig_name: "--chimSegmentReadGapMax" example: - 0 required: false @@ -1708,11 +1886,12 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--chimFilter" + name: "--chim_filter" description: "different filters for chimeric alignments\n\n- None ... no filtering\n\ - banGenomicN ... Ns are not allowed in the genome sequence around the chimeric\ \ junction" - info: null + info: + orig_name: "--chimFilter" example: - "banGenomicN" required: false @@ -1720,10 +1899,11 @@ argument_groups: multiple: true multiple_sep: ";" - type: "integer" - name: "--chimMainSegmentMultNmax" + name: "--chim_main_segment_mult_nmax" description: "maximum number of multi-alignments for the main chimeric segment.\ \ =1 will prohibit multimapping main segments." - info: null + info: + orig_name: "--chimMainSegmentMultNmax" example: - 10 required: false @@ -1731,10 +1911,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--chimMultimapNmax" + name: "--chim_multimap_nmax" description: "maximum number of chimeric multi-alignments\n\n- 0 ... use the old\ \ scheme for chimeric detection which only considered unique alignments" - info: null + info: + orig_name: "--chimMultimapNmax" example: - 0 required: false @@ -1742,10 +1923,11 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--chimMultimapScoreRange" + name: "--chim_multimap_score_range" description: "the score range for multi-mapping chimeras below the best chimeric\ - \ score. Only works with --chimMultimapNmax > 1" - info: null + \ score. Only works with --chim_multimap_nmax > 1" + info: + orig_name: "--chimMultimapScoreRange" example: - 1 required: false @@ -1753,11 +1935,12 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--chimNonchimScoreDropMin" + name: "--chim_nonchim_score_drop_min" description: "to trigger chimeric detection, the drop in the best non-chimeric\ \ alignment score with respect to the read length has to be greater than this\ \ value" - info: null + info: + orig_name: "--chimNonchimScoreDropMin" example: - 20 required: false @@ -1765,11 +1948,12 @@ argument_groups: multiple: false multiple_sep: ";" - type: "integer" - name: "--chimOutJunctionFormat" + name: "--chim_out_junction_format" description: "formatting type for the Chimeric.out.junction file\n\n- 0 ... no\ \ comment lines/headers\n- 1 ... comment lines at the end of the file: command\ \ line and Nreads: total, unique/multi-mapping" - info: null + info: + orig_name: "--chimOutJunctionFormat" example: - 0 required: false @@ -1779,21 +1963,23 @@ argument_groups: - name: "Quantification of Annotations" arguments: - type: "string" - name: "--quantMode" + name: "--quant_mode" description: "types of quantification requested\n\n- - ... none\n\ - TranscriptomeSAM ... output SAM/BAM alignments to transcriptome into a separate\ \ file\n- GeneCounts ... count reads per gene" - info: null + info: + orig_name: "--quantMode" required: false direction: "input" multiple: true multiple_sep: ";" - type: "integer" - name: "--quantTranscriptomeBAMcompression" + name: "--quant_transcriptome_bam_compression" description: "-2 to 10 transcriptome BAM compression level\n\n- -2 ... no BAM\ \ output\n- -1 ... default compression (6?)\n- 0 ... no compression\n- 10\ \ ... maximum compression" - info: null + info: + orig_name: "--quantTranscriptomeBAMcompression" example: - 1 required: false @@ -1801,13 +1987,14 @@ argument_groups: multiple: false multiple_sep: ";" - type: "string" - name: "--quantTranscriptomeSAMoutput" + name: "--quant_transcriptome_sam_output" description: "alignment filtering for TranscriptomeSAM output\n\n- BanSingleEnd_BanIndels_ExtendSoftclip\ \ ... prohibit indels and single-end alignments, extend softclips - compatible\ \ with RSEM\n- BanSingleEnd ... prohibit single-end alignments,\ \ allow indels and softclips\n- BanSingleEnd_ExtendSoftclip ... prohibit single-end\ \ alignments, extend softclips, allow indels" - info: null + info: + orig_name: "--quantTranscriptomeSAMoutput" example: - "BanSingleEnd_BanIndels_ExtendSoftclip" required: false @@ -1817,20 +2004,22 @@ argument_groups: - name: "2-pass Mapping" arguments: - type: "string" - name: "--twopassMode" + name: "--twopass_mode" description: "2-pass mapping mode.\n\n- None ... 1-pass mapping\n- Basic\ \ ... basic 2-pass mapping, with all 1st pass junctions inserted into\ \ the genome indices on the fly" - info: null + info: + orig_name: "--twopassMode" required: false direction: "input" multiple: false multiple_sep: ";" - type: "integer" - name: "--twopass1readsN" + name: "--twopass1reads_n" description: "number of reads to process for the 1st step. Use very large number\ \ (or default -1) to map all reads in the first step." - info: null + info: + orig_name: "--twopass1readsN" example: - -1 required: false @@ -1840,13 +2029,374 @@ argument_groups: - name: "WASP parameters" arguments: - type: "string" - name: "--waspOutputMode" + name: "--wasp_output_mode" description: "WASP allele-specific output type. This is re-implementation of the\ \ original WASP mappability filtering by Bryce van de Geijn, Graham McVicker,\ \ Yoav Gilad & Jonathan K Pritchard. Please cite the original WASP paper: Nature\ \ Methods 12, 1061-1063 (2015), https://www.nature.com/articles/nmeth.3582 .\n\ \n- SAMtag ... add WASP tags to the alignments that pass WASP filtering" - info: null + info: + orig_name: "--waspOutputMode" + required: false + direction: "input" + multiple: false + multiple_sep: ";" +- name: "STARsolo (single cell RNA-seq) parameters" + arguments: + - type: "string" + name: "--solo_type" + description: "type of single-cell RNA-seq\n\n- CB_UMI_Simple ... (a.k.a. Droplet)\ + \ one UMI and one Cell Barcode of fixed length in read2, e.g. Drop-seq and 10X\ + \ Chromium.\n- CB_UMI_Complex ... multiple Cell Barcodes of varying length,\ + \ one UMI of fixed length and one adapter sequence of fixed length are allowed\ + \ in read2 only (e.g. inDrop, ddSeq).\n- CB_samTagOut ... output Cell Barcode\ + \ as CR and/or CB SAm tag. No UMI counting. --readFilesIn cDNA_read1 [cDNA_read2\ + \ if paired-end] CellBarcode_read . Requires --out_sam_type BAM Unsorted [and/or\ + \ SortedByCoordinate]\n- SmartSeq ... Smart-seq: each cell in a separate\ + \ FASTQ (paired- or single-end), barcodes are corresponding read-groups, no\ + \ UMI sequences, alignments deduplicated according to alignment start and end\ + \ (after extending soft-clipped bases)" + info: + orig_name: "--soloType" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "string" + name: "--solo_cb_type" + description: "cell barcode type\n\nSequence: cell barcode is a sequence (standard\ + \ option)\nString: cell barcode is an arbitrary string" + info: + orig_name: "--soloCBtype" + example: + - "Sequence" + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "string" + name: "--solo_cb_whitelist" + description: "file(s) with whitelist(s) of cell barcodes. Only --solo_type CB_UMI_Complex\ + \ allows more than one whitelist file.\n\n- None ... no whitelist:\ + \ all cell barcodes are allowed" + info: + orig_name: "--soloCBwhitelist" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "integer" + name: "--solo_cb_start" + description: "cell barcode start base" + info: + orig_name: "--soloCBstart" + example: + - 1 + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "integer" + name: "--solo_cb_len" + description: "cell barcode length" + info: + orig_name: "--soloCBlen" + example: + - 16 + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "integer" + name: "--solo_umi_start" + description: "UMI start base" + info: + orig_name: "--soloUMIstart" + example: + - 17 + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "integer" + name: "--solo_umi_len" + description: "UMI length" + info: + orig_name: "--soloUMIlen" + example: + - 10 + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "integer" + name: "--solo_barcode_read_length" + description: "length of the barcode read\n\n- 1 ... equal to sum of soloCBlen+soloUMIlen\n\ + - 0 ... not defined, do not check" + info: + orig_name: "--soloBarcodeReadLength" + example: + - 1 + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "integer" + name: "--solo_barcode_mate" + description: "identifies which read mate contains the barcode (CB+UMI) sequence\n\ + \n- 0 ... barcode sequence is on separate read, which should always be the\ + \ last file in the --readFilesIn listed\n- 1 ... barcode sequence is a part\ + \ of mate 1\n- 2 ... barcode sequence is a part of mate 2" + info: + orig_name: "--soloBarcodeMate" + example: + - 0 + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "string" + name: "--solo_cb_position" + description: "position of Cell Barcode(s) on the barcode read.\n\nPresently only\ + \ works with --solo_type CB_UMI_Complex, and barcodes are assumed to be on Read2.\n\ + Format for each barcode: startAnchor_startPosition_endAnchor_endPosition\nstart(end)Anchor\ + \ defines the Anchor Base for the CB: 0: read start; 1: read end; 2: adapter\ + \ start; 3: adapter end\nstart(end)Position is the 0-based position with of\ + \ the CB start(end) with respect to the Anchor Base\nString for different barcodes\ + \ are separated by space.\nExample: inDrop (Zilionis et al, Nat. Protocols,\ + \ 2017):\n--solo_cb_position 0_0_2_-1 3_1_3_8" + info: + orig_name: "--soloCBposition" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "string" + name: "--solo_umi_position" + description: "position of the UMI on the barcode read, same as soloCBposition\n\ + \nExample: inDrop (Zilionis et al, Nat. Protocols, 2017):\n--solo_cb_position\ + \ 3_9_3_14" + info: + orig_name: "--soloUMIposition" + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "string" + name: "--solo_adapter_sequence" + description: "adapter sequence to anchor barcodes. Only one adapter sequence is\ + \ allowed." + info: + orig_name: "--soloAdapterSequence" + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "integer" + name: "--solo_adapter_mismatches_nmax" + description: "maximum number of mismatches allowed in adapter sequence." + info: + orig_name: "--soloAdapterMismatchesNmax" + example: + - 1 + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "string" + name: "--solo_cb_match_wl_type" + description: "matching the Cell Barcodes to the WhiteList\n\n- Exact \ + \ ... only exact matches allowed\n- 1MM \ + \ ... only one match in whitelist with 1 mismatched base allowed. Allowed\ + \ CBs have to have at least one read with exact match.\n- 1MM_multi \ + \ ... multiple matches in whitelist with 1 mismatched base allowed,\ + \ posterior probability calculation is used choose one of the matches.\nAllowed\ + \ CBs have to have at least one read with exact match. This option matches best\ + \ with CellRanger 2.2.0\n- 1MM_multi_pseudocounts ... same as 1MM_Multi,\ + \ but pseudocounts of 1 are added to all whitelist barcodes.\n- 1MM_multi_Nbase_pseudocounts\ + \ ... same as 1MM_multi_pseudocounts, multimatching to WL is allowed for\ + \ CBs with N-bases. This option matches best with CellRanger >= 3.0.0\n- EditDist_2\ + \ ... allow up to edit distance of 3 fpr each of the barcodes.\ + \ May include one deletion + one insertion. Only works with --solo_type CB_UMI_Complex.\ + \ Matches to multiple passlist barcdoes are not allowed. Similar to ParseBio\ + \ Split-seq pipeline." + info: + orig_name: "--soloCBmatchWLtype" + example: + - "1MM_multi" + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "string" + name: "--solo_input_sam_attr_barcode_seq" + description: "when inputting reads from a SAM file (--readsFileType SAM SE/PE),\ + \ these SAM attributes mark the barcode sequence (in proper order).\n\nFor instance,\ + \ for 10X CellRanger or STARsolo BAMs, use --solo_input_sam_attr_barcode_seq\ + \ CR UR .\nThis parameter is required when running STARsolo with input from\ + \ SAM." + info: + orig_name: "--soloInputSAMattrBarcodeSeq" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "string" + name: "--solo_input_sam_attr_barcode_qual" + description: "when inputting reads from a SAM file (--readsFileType SAM SE/PE),\ + \ these SAM attributes mark the barcode qualities (in proper order).\n\nFor\ + \ instance, for 10X CellRanger or STARsolo BAMs, use --solo_input_sam_attr_barcode_qual\ + \ CY UY .\nIf this parameter is '-' (default), the quality 'H' will be assigned\ + \ to all bases." + info: + orig_name: "--soloInputSAMattrBarcodeQual" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "string" + name: "--solo_strand" + description: "strandedness of the solo libraries:\n\n- Unstranded ... no strand\ + \ information\n- Forward ... read strand same as the original RNA molecule\n\ + - Reverse ... read strand opposite to the original RNA molecule" + info: + orig_name: "--soloStrand" + example: + - "Forward" + required: false + direction: "input" + multiple: false + multiple_sep: ";" + - type: "string" + name: "--solo_features" + description: "genomic features for which the UMI counts per Cell Barcode are collected\n\ + \n- Gene ... genes: reads match the gene transcript\n- SJ \ + \ ... splice junctions: reported in SJ.out.tab\n- GeneFull ...\ + \ full gene (pre-mRNA): count all reads overlapping genes' exons and introns\n\ + - GeneFull_ExonOverIntron ... full gene (pre-mRNA): count all reads overlapping\ + \ genes' exons and introns: prioritize 100% overlap with exons\n- GeneFull_Ex50pAS\ + \ ... full gene (pre-RNA): count all reads overlapping genes' exons and\ + \ introns: prioritize >50% overlap with exons. Do not count reads with 100%\ + \ exonic overlap in the antisense direction." + info: + orig_name: "--soloFeatures" + example: + - "Gene" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "string" + name: "--solo_multi_mappers" + description: "counting method for reads mapping to multiple genes\n\n- Unique\ + \ ... count only reads that map to unique genes\n- Uniform ... uniformly\ + \ distribute multi-genic UMIs to all genes\n- Rescue ... distribute UMIs\ + \ proportionally to unique+uniform counts (~ first iteration of EM)\n- PropUnique\ + \ ... distribute UMIs proportionally to unique mappers, if present, and uniformly\ + \ if not.\n- EM ... multi-gene UMIs are distributed using Expectation\ + \ Maximization algorithm" + info: + orig_name: "--soloMultiMappers" + example: + - "Unique" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "string" + name: "--solo_umi_dedup" + description: "type of UMI deduplication (collapsing) algorithm\n\n- 1MM_All \ + \ ... all UMIs with 1 mismatch distance to each other are\ + \ collapsed (i.e. counted once).\n- 1MM_Directional_UMItools ... follows\ + \ the \"directional\" method from the UMI-tools by Smith, Heger and Sudbery\ + \ (Genome Research 2017).\n- 1MM_Directional ... same as 1MM_Directional_UMItools,\ + \ but with more stringent criteria for duplicate UMIs\n- Exact \ + \ ... only exactly matching UMIs are collapsed.\n- NoDedup \ + \ ... no deduplication of UMIs, count all reads.\n- 1MM_CR \ + \ ... CellRanger2-4 algorithm for 1MM UMI collapsing." + info: + orig_name: "--soloUMIdedup" + example: + - "1MM_All" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "string" + name: "--solo_umi_filtering" + description: "type of UMI filtering (for reads uniquely mapping to genes)\n\n\ + - - ... basic filtering: remove UMIs with N and homopolymers\ + \ (similar to CellRanger 2.2.0).\n- MultiGeneUMI ... basic + remove lower-count\ + \ UMIs that map to more than one gene.\n- MultiGeneUMI_All ... basic + remove\ + \ all UMIs that map to more than one gene.\n- MultiGeneUMI_CR ... basic +\ + \ remove lower-count UMIs that map to more than one gene, matching CellRanger\ + \ > 3.0.0 .\nOnly works with --solo_umi_dedup 1MM_CR" + info: + orig_name: "--soloUMIfiltering" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "string" + name: "--solo_out_file_names" + description: "file names for STARsolo output:\n\nfile_name_prefix gene_names\ + \ barcode_sequences cell_feature_count_matrix" + info: + orig_name: "--soloOutFileNames" + example: + - "Solo.out/" + - "features.tsv" + - "barcodes.tsv" + - "matrix.mtx" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "string" + name: "--solo_cell_filter" + description: "cell filtering type and parameters\n\n- None ... do not\ + \ output filtered cells\n- TopCells ... only report top cells by UMI\ + \ count, followed by the exact number of cells\n- CellRanger2.2 ... simple\ + \ filtering of CellRanger 2.2.\nCan be followed by numbers: number of expected\ + \ cells, robust maximum percentile for UMI count, maximum to minimum ratio for\ + \ UMI count\nThe harcoded values are from CellRanger: nExpectedCells=3000; \ + \ maxPercentile=0.99; maxMinRatio=10\n- EmptyDrops_CR ... EmptyDrops filtering\ + \ in CellRanger flavor. Please cite the original EmptyDrops paper: A.T.L Lun\ + \ et al, Genome Biology, 20, 63 (2019): https://genomebiology.biomedcentral.com/articles/10.1186/s13059-019-1662-y\n\ + Can be followed by 10 numeric parameters: nExpectedCells maxPercentile \ + \ maxMinRatio indMin indMax umiMin umiMinFracMedian candMaxN FDR\ + \ simN\nThe harcoded values are from CellRanger: 3000 \ + \ 0.99 10 45000 90000 500 0.01 20000\ + \ 0.01 10000" + info: + orig_name: "--soloCellFilter" + example: + - "CellRanger2.2" + - "3000" + - "0.99" + - "10" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "string" + name: "--solo_out_format_features_gene_field3" + description: "field 3 in the Gene features.tsv file. If \"-\", then no 3rd field\ + \ is output." + info: + orig_name: "--soloOutFormatFeaturesGeneField3" + example: + - "Gene Expression" + required: false + direction: "input" + multiple: true + multiple_sep: ";" + - type: "string" + name: "--solo_cell_read_stats" + description: "Output reads statistics for each CB\n\n- Standard ... standard\ + \ output" + info: + orig_name: "--soloCellReadStats" required: false direction: "input" multiple: false @@ -1966,6 +2516,19 @@ argument_groups: direction: "output" multiple: false multiple_sep: ";" + - type: "file" + name: "--reads_aligned_to_transcriptome" + description: "The output file containing the alignments to transcriptome in BAM\ + \ formats. This file is generated when --quantMode is set to TranscriptomeSAM." + info: null + example: + - "transcriptome_aligned.bam" + must_exist: true + create_parent: true + required: false + direction: "output" + multiple: false + multiple_sep: ";" resources: - type: "python_script" path: "script.py" @@ -2061,7 +2624,7 @@ engines: id: "docker" image: "python:3.12-slim" target_registry: "images.viash-hub.com" - target_tag: "v0.1.0" + target_tag: "main" namespace_separator: "/" setup: - type: "apt" @@ -2081,6 +2644,11 @@ engines: env: - "STAR_VERSION 2.7.11b" - "PACKAGES gcc g++ make wget zlib1g-dev unzip xxd" + - type: "python" + user: false + packages: + - "pyyaml" + upgrade: true - type: "docker" run: - "STAR --version | sed 's#\\(.*\\)#star: \"\\1\"#' > /var/software_versions.txt\n" @@ -2094,22 +2662,23 @@ build_info: engine: "docker|native" output: "target/nextflow/star/star_align_reads" executable: "target/nextflow/star/star_align_reads/main.nf" - viash_version: "0.9.0-RC6" - git_commit: "b84b29747d0635f2ac83ea63b496be9a9edb6724" - git_remote: "https://github.com/viash-hub/biobox" + viash_version: "0.9.0" + git_commit: "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b" + git_remote: "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox" + git_tag: "v0.2.0-27-g952ff08" package_config: name: "biobox" - version: "v0.1.0" + version: "main" description: "A collection of bioinformatics tools for working with sequence data.\n" info: null - viash_version: "0.9.0-RC6" + viash_version: "0.9.0" source: "src" target: "target" config_mods: - ".requirements.commands := ['ps']\n" - ".engines += { type: \"native\" }" - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'" - - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" + - ".engines[.type == 'docker'].target_tag := 'main'" keywords: - "bioinformatics" - "modules" diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/main.nf b/target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/main.nf similarity index 71% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/main.nf rename to target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/main.nf index 10b0c96..97daee4 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/main.nf +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/main.nf @@ -1,13 +1,17 @@ -// star_align_reads v0.1.0 +// star_align_reads main // -// This wrapper script is auto-generated by viash 0.9.0-RC6 and is thus a -// derivative work thereof. This software comes with ABSOLUTELY NO WARRANTY from -// Data Intuitive. +// This wrapper script is auto-generated by viash 0.9.0 and is thus a derivative +// work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data +// Intuitive. // // The component may contain files which fall under a different license. The // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Angela Oliveira Pisco (author) +// * Robrecht Cannoodt (author, maintainer) //////////////////////////// // VDSL3 helper functions // @@ -760,8 +764,11 @@ def runEach(Map args) { def fromState_ = args.fromState def toState_ = args.toState def filter_ = args.filter + def runIf_ = args.runIf def id_ = args.id + assert !runIf_ || runIf_ instanceof Closure: "runEach: must pass a Closure to runIf." + workflow runEachWf { take: input_ch main: @@ -783,7 +790,20 @@ def runEach(Map args) { [new_id] + tup.drop(1) } : filter_ch - def data_ch = id_ch | map{tup -> + def chPassthrough = null + def chRun = null + if (runIf_) { + def idRunIfBranch = id_ch.branch{ tup -> + run: runIf_(tup[0], tup[1], comp_) + passthrough: true + } + chPassthrough = idRunIfBranch.passthrough + chRun = idRunIfBranch.run + } else { + chRun = id_ch + chPassthrough = Channel.empty() + } + def data_ch = chRun | map{tup -> def new_data = tup[1] if (fromState_ instanceof Map) { new_data = fromState_.collectEntries{ key0, key1 -> @@ -821,8 +841,11 @@ def runEach(Map args) { [tup[0], new_state] + tup.drop(3) } : out_ch + + def return_ch = post_ch + | concat(chPassthrough) - post_ch + return_ch } // mix all results @@ -1598,8 +1621,8 @@ def findStates(Map params, Map config) { // construct renameMap if (args.rename_keys) { def renameMap = args.rename_keys.collectEntries{renameString -> - def split = renameString.split(";") - assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey,newKey:oldKey'" + def split = renameString.split(":") + assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey', or 'newKey:oldKey;newKey:oldKey' in case of multiple values" split } @@ -1709,7 +1732,9 @@ def publishStates(Map args) { def yamlFilename = yamlTemplate_ .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) // TODO: do the pathnames in state_ match up with the outputFilenames_? @@ -1780,7 +1805,9 @@ def publishStatesByConfig(Map args) { def yamlTemplate = params.containsKey("output_state") ? params.output_state : '$id.$key.state.yaml' def yamlFilename = yamlTemplate .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) def yamlDir = java.nio.file.Paths.get(yamlFilename).getParent() // the processed state is a list of [key, value, inputPath, outputFilename] tuples, where @@ -1822,7 +1849,9 @@ def publishStatesByConfig(Map args) { // instantiate the template def filename = filenameTemplate .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) if (par.multiple) { // if the parameter is multiple: true, the filename // should contain a wildcard '*' that is replaced with @@ -2626,30 +2655,31 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { tuple } - def chModifiedFiltered = workflowArgs.filter ? - chModified | filter{workflowArgs.filter(it)} : - chModified def chRun = null def chPassthrough = null if (workflowArgs.runIf) { - def runIfBranch = chModifiedFiltered.branch{ tup -> + def runIfBranch = chModified.branch{ tup -> run: workflowArgs.runIf(tup[0], tup[1]) passthrough: true } chRun = runIfBranch.run chPassthrough = runIfBranch.passthrough } else { - chRun = chModifiedFiltered + chRun = chModified chPassthrough = Channel.empty() } + def chRunFiltered = workflowArgs.filter ? + chRun | filter{workflowArgs.filter(it)} : + chRun + def chArgs = workflowArgs.fromState ? - chRun | map{ + chRunFiltered | map{ def new_data = workflowArgs.fromState(it.take(2)) [it[0], new_data] } : - chRun | map {tup -> tup.take(2)} + chRunFiltered | map {tup -> tup.take(2)} // fill in defaults def chArgsWithDefaults = chArgs @@ -2720,7 +2750,7 @@ def workflowFactory(Map args, Map defaultWfArgs, Map meta) { // | view{"chInitialOutput: ${it.take(3)}"} // join the output [prev_id, new_id, output] with the previous state [prev_id, state, ...] - def chNewState = safeJoin(chInitialOutput, chModifiedFiltered, key_) + def chNewState = safeJoin(chInitialOutput, chRunFiltered, key_) // input tuple format: [join_id, id, output, prev_state, ...] // output tuple format: [join_id, id, new_state, ...] | map{ tup -> @@ -2780,15 +2810,73 @@ meta = [ "config": processConfig(readJsonBlob('''{ "name" : "star_align_reads", "namespace" : "star", - "version" : "v0.1.0", + "version" : "main", + "authors" : [ + { + "name" : "Angela Oliveira Pisco", + "roles" : [ + "author" + ], + "info" : { + "role" : "Contributor", + "links" : { + "github" : "aopisco", + "orcid" : "0000-0003-0142-2355", + "linkedin" : "aopisco" + }, + "organizations" : [ + { + "name" : "Insitro", + "href" : "https://insitro.com", + "role" : "Director of Computational Biology" + }, + { + "name" : "Open Problems", + "href" : "https://openproblems.bio", + "role" : "Core Member" + } + ] + } + }, + { + "name" : "Robrecht Cannoodt", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "links" : { + "email" : "robrecht@data-intuitive.com", + "github" : "rcannood", + "orcid" : "0000-0003-3641-729X", + "linkedin" : "robrechtcannoodt" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Science Engineer" + }, + { + "name" : "Open Problems", + "href" : "https://openproblems.bio", + "role" : "Core Member" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Run Parameters", "arguments" : [ { "type" : "integer", - "name" : "--runRNGseed", + "name" : "--run_rng_seed", "description" : "random number generator seed.", + "info" : { + "orig_name" : "--runRNGseed" + }, "example" : [ 777 ], @@ -2804,8 +2892,11 @@ meta = [ "arguments" : [ { "type" : "file", - "name" : "--genomeDir", + "name" : "--genome_dir", "description" : "path to the directory where genome files are stored (for --runMode alignReads) or will be generated (for --runMode generateGenome)", + "info" : { + "orig_name" : "--genomeDir" + }, "example" : [ "./GenomeDir" ], @@ -2818,8 +2909,11 @@ meta = [ }, { "type" : "string", - "name" : "--genomeLoad", + "name" : "--genome_load", "description" : "mode of shared memory usage for the genome files. Only used with --runMode alignReads.\n\n- LoadAndKeep ... load genome into shared and keep it in memory after run\n- LoadAndRemove ... load genome into shared but remove it after run\n- LoadAndExit ... load genome into shared memory and exit, keeping the genome in memory for future runs\n- Remove ... do not map anything, just remove loaded genome from memory\n- NoSharedMemory ... do not use shared memory, each job will have its own private copy of the genome", + "info" : { + "orig_name" : "--genomeLoad" + }, "example" : [ "NoSharedMemory" ], @@ -2830,8 +2924,11 @@ meta = [ }, { "type" : "file", - "name" : "--genomeFastaFiles", + "name" : "--genome_fasta_files", "description" : "path(s) to the fasta files with the genome sequences, separated by spaces. These files should be plain text FASTA files, they *cannot* be zipped.\n\nRequired for the genome generation (--runMode genomeGenerate). Can also be used in the mapping (--runMode alignReads) to add extra (new) sequences to the genome (e.g. spike-ins).", + "info" : { + "orig_name" : "--genomeFastaFiles" + }, "must_exist" : true, "create_parent" : true, "required" : false, @@ -2841,8 +2938,11 @@ meta = [ }, { "type" : "integer", - "name" : "--genomeFileSizes", + "name" : "--genome_file_sizes", "description" : "genome files exact sizes in bytes. Typically, this should not be defined by the user.", + "info" : { + "orig_name" : "--genomeFileSizes" + }, "example" : [ 0 ], @@ -2853,8 +2953,11 @@ meta = [ }, { "type" : "string", - "name" : "--genomeTransformOutput", - "description" : "which output to transform back to original genome\n\n- SAM ... SAM/BAM alignments\n- SJ ... splice junctions (SJ.out.tab)\n- Quant ... quantifications (from --quantMode option)\n- None ... no transformation of the output", + "name" : "--genome_transform_output", + "description" : "which output to transform back to original genome\n\n- SAM ... SAM/BAM alignments\n- SJ ... splice junctions (SJ.out.tab)\n- Quant ... quantifications (from --quant_mode option)\n- None ... no transformation of the output", + "info" : { + "orig_name" : "--genomeTransformOutput" + }, "required" : false, "direction" : "input", "multiple" : true, @@ -2862,8 +2965,11 @@ meta = [ }, { "type" : "string", - "name" : "--genomeChrSetMitochondrial", + "name" : "--genome_chr_set_mitochondrial", "description" : "names of the mitochondrial chromosomes. Presently only used for STARsolo statistics output/", + "info" : { + "orig_name" : "--genomeChrSetMitochondrial" + }, "example" : [ "chrM", "M", @@ -2881,8 +2987,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--sjdbFileChrStartEnd", + "name" : "--sjdb_file_chr_start_end", "description" : "path to the files with genomic coordinates (chr start end strand) for the splice junction introns. Multiple files can be supplied and will be concatenated.", + "info" : { + "orig_name" : "--sjdbFileChrStartEnd" + }, "required" : false, "direction" : "input", "multiple" : true, @@ -2890,8 +2999,11 @@ meta = [ }, { "type" : "file", - "name" : "--sjdbGTFfile", + "name" : "--sjdb_gtf_file", "description" : "path to the GTF file with annotations", + "info" : { + "orig_name" : "--sjdbGTFfile" + }, "must_exist" : true, "create_parent" : true, "required" : false, @@ -2901,8 +3013,11 @@ meta = [ }, { "type" : "string", - "name" : "--sjdbGTFchrPrefix", + "name" : "--sjdb_gtf_chr_prefix", "description" : "prefix for chromosome names in a GTF file (e.g. 'chr' for using ENSMEBL annotations with UCSC genomes)", + "info" : { + "orig_name" : "--sjdbGTFchrPrefix" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -2910,8 +3025,11 @@ meta = [ }, { "type" : "string", - "name" : "--sjdbGTFfeatureExon", + "name" : "--sjdb_gtf_feature_exon", "description" : "feature type in GTF file to be used as exons for building transcripts", + "info" : { + "orig_name" : "--sjdbGTFfeatureExon" + }, "example" : [ "exon" ], @@ -2922,8 +3040,11 @@ meta = [ }, { "type" : "string", - "name" : "--sjdbGTFtagExonParentTranscript", + "name" : "--sjdb_gtf_tag_exon_parent_transcript", "description" : "GTF attribute name for parent transcript ID (default \\"transcript_id\\" works for GTF files)", + "info" : { + "orig_name" : "--sjdbGTFtagExonParentTranscript" + }, "example" : [ "transcript_id" ], @@ -2934,8 +3055,11 @@ meta = [ }, { "type" : "string", - "name" : "--sjdbGTFtagExonParentGene", + "name" : "--sjdb_gtf_tag_exon_parent_gene", "description" : "GTF attribute name for parent gene ID (default \\"gene_id\\" works for GTF files)", + "info" : { + "orig_name" : "--sjdbGTFtagExonParentGene" + }, "example" : [ "gene_id" ], @@ -2946,8 +3070,11 @@ meta = [ }, { "type" : "string", - "name" : "--sjdbGTFtagExonParentGeneName", + "name" : "--sjdb_gtf_tag_exon_parent_gene_name", "description" : "GTF attribute name for parent gene name", + "info" : { + "orig_name" : "--sjdbGTFtagExonParentGeneName" + }, "example" : [ "gene_name" ], @@ -2958,8 +3085,11 @@ meta = [ }, { "type" : "string", - "name" : "--sjdbGTFtagExonParentGeneType", + "name" : "--sjdb_gtf_tag_exon_parent_gene_type", "description" : "GTF attribute name for parent gene type", + "info" : { + "orig_name" : "--sjdbGTFtagExonParentGeneType" + }, "example" : [ "gene_type", "gene_biotype" @@ -2971,8 +3101,11 @@ meta = [ }, { "type" : "integer", - "name" : "--sjdbOverhang", + "name" : "--sjdb_overhang", "description" : "length of the donor/acceptor sequence on each side of the junctions, ideally = (mate_length - 1)", + "info" : { + "orig_name" : "--sjdbOverhang" + }, "example" : [ 100 ], @@ -2983,8 +3116,11 @@ meta = [ }, { "type" : "integer", - "name" : "--sjdbScore", + "name" : "--sjdb_score", "description" : "extra alignment score for alignments that cross database junctions", + "info" : { + "orig_name" : "--sjdbScore" + }, "example" : [ 2 ], @@ -2995,8 +3131,11 @@ meta = [ }, { "type" : "string", - "name" : "--sjdbInsertSave", + "name" : "--sjdb_insert_save", "description" : "which files to save when sjdb junctions are inserted on the fly at the mapping step\n\n- Basic ... only small junction / transcript files\n- All ... all files including big Genome, SA and SAindex - this will create a complete genome directory", + "info" : { + "orig_name" : "--sjdbInsertSave" + }, "example" : [ "Basic" ], @@ -3012,8 +3151,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--varVCFfile", + "name" : "--var_vcf_file", "description" : "path to the VCF file that contains variation data. The 10th column should contain the genotype information, e.g. 0/1", + "info" : { + "orig_name" : "--varVCFfile" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -3026,8 +3168,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--readFilesType", - "description" : "format of input read files\n\n- Fastx ... FASTA or FASTQ\n- SAM SE ... SAM or BAM single-end reads; for BAM use --readFilesCommand samtools view\n- SAM PE ... SAM or BAM paired-end reads; for BAM use --readFilesCommand samtools view", + "name" : "--read_files_type", + "description" : "format of input read files\n\n- Fastx ... FASTA or FASTQ\n- SAM SE ... SAM or BAM single-end reads; for BAM use --read_files_command samtools view\n- SAM PE ... SAM or BAM paired-end reads; for BAM use --read_files_command samtools view", + "info" : { + "orig_name" : "--readFilesType" + }, "example" : [ "Fastx" ], @@ -3038,8 +3183,11 @@ meta = [ }, { "type" : "string", - "name" : "--readFilesSAMattrKeep", - "description" : "for --readFilesType SAM SE/PE, which SAM tags to keep in the output BAM, e.g.: --readFilesSAMtagsKeep RG PL\n\n- All ... keep all tags\n- None ... do not keep any tags", + "name" : "--read_files_sam_attr_keep", + "description" : "for --read_files_type SAM SE/PE, which SAM tags to keep in the output BAM, e.g.: --readFilesSAMtagsKeep RG PL\n\n- All ... keep all tags\n- None ... do not keep any tags", + "info" : { + "orig_name" : "--readFilesSAMattrKeep" + }, "example" : [ "All" ], @@ -3050,8 +3198,11 @@ meta = [ }, { "type" : "file", - "name" : "--readFilesManifest", + "name" : "--read_files_manifest", "description" : "path to the \\"manifest\\" file with the names of read files. The manifest file should contain 3 tab-separated columns:\n\npaired-end reads: read1_file_name $tab$ read2_file_name $tab$ read_group_line.\nsingle-end reads: read1_file_name $tab$ - $tab$ read_group_line.\nSpaces, but not tabs are allowed in file names.\nIf read_group_line does not start with ID:, it can only contain one ID field, and ID: will be added to it.\nIf read_group_line starts with ID:, it can contain several fields separated by $tab$, and all fields will be be copied verbatim into SAM @RG header line.", + "info" : { + "orig_name" : "--readFilesManifest" + }, "must_exist" : true, "create_parent" : true, "required" : false, @@ -3061,8 +3212,11 @@ meta = [ }, { "type" : "string", - "name" : "--readFilesPrefix", + "name" : "--read_files_prefix", "description" : "prefix for the read files names, i.e. it will be added in front of the strings in --readFilesIn", + "info" : { + "orig_name" : "--readFilesPrefix" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -3070,8 +3224,11 @@ meta = [ }, { "type" : "string", - "name" : "--readFilesCommand", + "name" : "--read_files_command", "description" : "command line to execute for each of the input file. This command should generate FASTA or FASTQ text and send it to stdout\n\nFor example: zcat - to uncompress .gz files, bzcat - to uncompress .bz2 files, etc.", + "info" : { + "orig_name" : "--readFilesCommand" + }, "required" : false, "direction" : "input", "multiple" : true, @@ -3079,8 +3236,11 @@ meta = [ }, { "type" : "integer", - "name" : "--readMapNumber", + "name" : "--read_map_number", "description" : "number of reads to map from the beginning of the file\n\n-1: map all reads", + "info" : { + "orig_name" : "--readMapNumber" + }, "example" : [ -1 ], @@ -3091,8 +3251,11 @@ meta = [ }, { "type" : "string", - "name" : "--readMatesLengthsIn", + "name" : "--read_mates_lengths_in", "description" : "Equal/NotEqual - lengths of names,sequences,qualities for both mates are the same / not the same. NotEqual is safe in all situations.", + "info" : { + "orig_name" : "--readMatesLengthsIn" + }, "example" : [ "NotEqual" ], @@ -3103,8 +3266,11 @@ meta = [ }, { "type" : "string", - "name" : "--readNameSeparator", + "name" : "--read_name_separator", "description" : "character(s) separating the part of the read names that will be trimmed in output (read name after space is always trimmed)", + "info" : { + "orig_name" : "--readNameSeparator" + }, "example" : [ "/" ], @@ -3115,8 +3281,11 @@ meta = [ }, { "type" : "integer", - "name" : "--readQualityScoreBase", + "name" : "--read_quality_score_base", "description" : "number to be subtracted from the ASCII code to get Phred quality score", + "info" : { + "orig_name" : "--readQualityScoreBase" + }, "example" : [ 33 ], @@ -3132,8 +3301,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--clipAdapterType", + "name" : "--clip_adapter_type", "description" : "adapter clipping type\n\n- Hamming ... adapter clipping based on Hamming distance, with the number of mismatches controlled by --clip5pAdapterMMp\n- CellRanger4 ... 5p and 3p adapter clipping similar to CellRanger4. Utilizes Opal package by Martin Sosic: https://github.com/Martinsos/opal\n- None ... no adapter clipping, all other clip* parameters are disregarded", + "info" : { + "orig_name" : "--clipAdapterType" + }, "example" : [ "Hamming" ], @@ -3144,8 +3316,11 @@ meta = [ }, { "type" : "integer", - "name" : "--clip3pNbases", + "name" : "--clip3p_nbases", "description" : "number(s) of bases to clip from 3p of each mate. If one value is given, it will be assumed the same for both mates.", + "info" : { + "orig_name" : "--clip3pNbases" + }, "example" : [ 0 ], @@ -3156,8 +3331,11 @@ meta = [ }, { "type" : "string", - "name" : "--clip3pAdapterSeq", + "name" : "--clip3p_adapter_seq", "description" : "adapter sequences to clip from 3p of each mate. If one value is given, it will be assumed the same for both mates.\n\n- polyA ... polyA sequence with the length equal to read length", + "info" : { + "orig_name" : "--clip3pAdapterSeq" + }, "required" : false, "direction" : "input", "multiple" : true, @@ -3165,8 +3343,11 @@ meta = [ }, { "type" : "double", - "name" : "--clip3pAdapterMMp", + "name" : "--clip3p_adapter_mm_p", "description" : "max proportion of mismatches for 3p adapter clipping for each mate. If one value is given, it will be assumed the same for both mates.", + "info" : { + "orig_name" : "--clip3pAdapterMMp" + }, "example" : [ 0.1 ], @@ -3177,8 +3358,11 @@ meta = [ }, { "type" : "integer", - "name" : "--clip3pAfterAdapterNbases", + "name" : "--clip3p_after_adapter_nbases", "description" : "number of bases to clip from 3p of each mate after the adapter clipping. If one value is given, it will be assumed the same for both mates.", + "info" : { + "orig_name" : "--clip3pAfterAdapterNbases" + }, "example" : [ 0 ], @@ -3189,8 +3373,11 @@ meta = [ }, { "type" : "integer", - "name" : "--clip5pNbases", + "name" : "--clip5p_nbases", "description" : "number(s) of bases to clip from 5p of each mate. If one value is given, it will be assumed the same for both mates.", + "info" : { + "orig_name" : "--clip5pNbases" + }, "example" : [ 0 ], @@ -3206,8 +3393,11 @@ meta = [ "arguments" : [ { "type" : "long", - "name" : "--limitGenomeGenerateRAM", + "name" : "--limit_genome_generate_ram", "description" : "maximum available RAM (bytes) for genome generation", + "info" : { + "orig_name" : "--limitGenomeGenerateRAM" + }, "example" : [ 31000000000 ], @@ -3218,8 +3408,11 @@ meta = [ }, { "type" : "long", - "name" : "--limitIObufferSize", + "name" : "--limit_io_buffer_size", "description" : "max available buffers size (bytes) for input/output, per thread", + "info" : { + "orig_name" : "--limitIObufferSize" + }, "example" : [ 30000000, 50000000 @@ -3231,8 +3424,11 @@ meta = [ }, { "type" : "long", - "name" : "--limitOutSAMoneReadBytes", + "name" : "--limit_out_sam_one_read_bytes", "description" : "max size of the SAM record (bytes) for one read. Recommended value: >(2*(LengthMate1+LengthMate2+100)*outFilterMultimapNmax", + "info" : { + "orig_name" : "--limitOutSAMoneReadBytes" + }, "example" : [ 100000 ], @@ -3243,8 +3439,11 @@ meta = [ }, { "type" : "integer", - "name" : "--limitOutSJoneRead", + "name" : "--limit_out_sj_one_read", "description" : "max number of junctions for one read (including all multi-mappers)", + "info" : { + "orig_name" : "--limitOutSJoneRead" + }, "example" : [ 1000 ], @@ -3255,8 +3454,11 @@ meta = [ }, { "type" : "integer", - "name" : "--limitOutSJcollapsed", + "name" : "--limit_out_sj_collapsed", "description" : "max number of collapsed junctions", + "info" : { + "orig_name" : "--limitOutSJcollapsed" + }, "example" : [ 1000000 ], @@ -3267,8 +3469,11 @@ meta = [ }, { "type" : "long", - "name" : "--limitBAMsortRAM", - "description" : "maximum available RAM (bytes) for sorting BAM. If =0, it will be set to the genome index size. 0 value can only be used with --genomeLoad NoSharedMemory option.", + "name" : "--limit_bam_sort_ram", + "description" : "maximum available RAM (bytes) for sorting BAM. If =0, it will be set to the genome index size. 0 value can only be used with --genome_load NoSharedMemory option.", + "info" : { + "orig_name" : "--limitBAMsortRAM" + }, "example" : [ 0 ], @@ -3279,8 +3484,11 @@ meta = [ }, { "type" : "integer", - "name" : "--limitSjdbInsertNsj", + "name" : "--limit_sjdb_insert_nsj", "description" : "maximum number of junctions to be inserted to the genome on the fly at the mapping stage, including those from annotations and those detected in the 1st step of the 2-pass run", + "info" : { + "orig_name" : "--limitSjdbInsertNsj" + }, "example" : [ 1000000 ], @@ -3291,8 +3499,11 @@ meta = [ }, { "type" : "integer", - "name" : "--limitNreadsSoft", + "name" : "--limit_nreads_soft", "description" : "soft limit on the number of reads", + "info" : { + "orig_name" : "--limitNreadsSoft" + }, "example" : [ -1 ], @@ -3308,8 +3519,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--outTmpKeep", + "name" : "--out_tmp_keep", "description" : "whether to keep the temporary files after STAR runs is finished\n\n- None ... remove all temporary files\n- All ... keep all files", + "info" : { + "orig_name" : "--outTmpKeep" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -3317,8 +3531,11 @@ meta = [ }, { "type" : "string", - "name" : "--outStd", - "description" : "which output will be directed to stdout (standard out)\n\n- Log ... log messages\n- SAM ... alignments in SAM format (which normally are output to Aligned.out.sam file), normal standard output will go into Log.std.out\n- BAM_Unsorted ... alignments in BAM format, unsorted. Requires --outSAMtype BAM Unsorted\n- BAM_SortedByCoordinate ... alignments in BAM format, sorted by coordinate. Requires --outSAMtype BAM SortedByCoordinate\n- BAM_Quant ... alignments to transcriptome in BAM format, unsorted. Requires --quantMode TranscriptomeSAM", + "name" : "--out_std", + "description" : "which output will be directed to stdout (standard out)\n\n- Log ... log messages\n- SAM ... alignments in SAM format (which normally are output to Aligned.out.sam file), normal standard output will go into Log.std.out\n- BAM_Unsorted ... alignments in BAM format, unsorted. Requires --out_sam_type BAM Unsorted\n- BAM_SortedByCoordinate ... alignments in BAM format, sorted by coordinate. Requires --out_sam_type BAM SortedByCoordinate\n- BAM_Quant ... alignments to transcriptome in BAM format, unsorted. Requires --quant_mode TranscriptomeSAM", + "info" : { + "orig_name" : "--outStd" + }, "example" : [ "Log" ], @@ -3329,8 +3546,11 @@ meta = [ }, { "type" : "string", - "name" : "--outReadsUnmapped", + "name" : "--out_reads_unmapped", "description" : "output of unmapped and partially mapped (i.e. mapped only one mate of a paired end read) reads in separate file(s).\n\n- None ... no output\n- Fastx ... output in separate fasta/fastq files, Unmapped.out.mate1/2", + "info" : { + "orig_name" : "--outReadsUnmapped" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -3338,8 +3558,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outQSconversionAdd", + "name" : "--out_qs_conversion_add", "description" : "add this number to the quality score (e.g. to convert from Illumina to Sanger, use -31)", + "info" : { + "orig_name" : "--outQSconversionAdd" + }, "example" : [ 0 ], @@ -3350,8 +3573,11 @@ meta = [ }, { "type" : "string", - "name" : "--outMultimapperOrder", + "name" : "--out_multimapper_order", "description" : "order of multimapping alignments in the output files\n\n- Old_2.4 ... quasi-random order used before 2.5.0\n- Random ... random order of alignments for each multi-mapper. Read mates (pairs) are always adjacent, all alignment for each read stay together. This option will become default in the future releases.", + "info" : { + "orig_name" : "--outMultimapperOrder" + }, "example" : [ "Old_2.4" ], @@ -3367,8 +3593,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--outSAMtype", - "description" : "type of SAM/BAM output\n\n1st word:\n- BAM ... output BAM without sorting\n- SAM ... output SAM without sorting\n- None ... no SAM/BAM output\n2nd, 3rd:\n- Unsorted ... standard unsorted\n- SortedByCoordinate ... sorted by coordinate. This option will allocate extra memory for sorting which can be specified by --limitBAMsortRAM.", + "name" : "--out_sam_type", + "description" : "type of SAM/BAM output\n\n1st word:\n- BAM ... output BAM without sorting\n- SAM ... output SAM without sorting\n- None ... no SAM/BAM output\n2nd, 3rd:\n- Unsorted ... standard unsorted\n- SortedByCoordinate ... sorted by coordinate. This option will allocate extra memory for sorting which can be specified by --limit_bam_sort_ram.", + "info" : { + "orig_name" : "--outSAMtype" + }, "example" : [ "SAM" ], @@ -3379,8 +3608,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMmode", + "name" : "--out_sam_mode", "description" : "mode of SAM output\n\n- None ... no SAM output\n- Full ... full SAM output\n- NoQS ... full SAM but without quality scores", + "info" : { + "orig_name" : "--outSAMmode" + }, "example" : [ "Full" ], @@ -3391,8 +3623,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMstrandField", + "name" : "--out_sam_strand_field", "description" : "Cufflinks-like strand field flag\n\n- None ... not used\n- intronMotif ... strand derived from the intron motif. This option changes the output alignments: reads with inconsistent and/or non-canonical introns are filtered out.", + "info" : { + "orig_name" : "--outSAMstrandField" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -3400,8 +3635,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMattributes", - "description" : "a string of desired SAM attributes, in the order desired for the output SAM. Tags can be listed in any combination/order.\n\n***Presets:\n- None ... no attributes\n- Standard ... NH HI AS nM\n- All ... NH HI AS nM NM MD jM jI MC ch\n***Alignment:\n- NH ... number of loci the reads maps to: =1 for unique mappers, >1 for multimappers. Standard SAM tag.\n- HI ... multiple alignment index, starts with --outSAMattrIHstart (=1 by default). Standard SAM tag.\n- AS ... local alignment score, +1/-1 for matches/mismateches, score* penalties for indels and gaps. For PE reads, total score for two mates. Stadnard SAM tag.\n- nM ... number of mismatches. For PE reads, sum over two mates.\n- NM ... edit distance to the reference (number of mismatched + inserted + deleted bases) for each mate. Standard SAM tag.\n- MD ... string encoding mismatched and deleted reference bases (see standard SAM specifications). Standard SAM tag.\n- jM ... intron motifs for all junctions (i.e. N in CIGAR): 0: non-canonical; 1: GT/AG, 2: CT/AC, 3: GC/AG, 4: CT/GC, 5: AT/AC, 6: GT/AT. If splice junctions database is used, and a junction is annotated, 20 is added to its motif value.\n- jI ... start and end of introns for all junctions (1-based).\n- XS ... alignment strand according to --outSAMstrandField.\n- MC ... mate's CIGAR string. Standard SAM tag.\n- ch ... marks all segment of all chimeric alingments for --chimOutType WithinBAM output.\n- cN ... number of bases clipped from the read ends: 5' and 3'\n***Variation:\n- vA ... variant allele\n- vG ... genomic coordinate of the variant overlapped by the read.\n- vW ... 1 - alignment passes WASP filtering; 2,3,4,5,6,7 - alignment does not pass WASP filtering. Requires --waspOutputMode SAMtag.\n- ha ... haplotype (1/2) when mapping to the diploid genome. Requires genome generated with --genomeTransformType Diploid .\n***STARsolo:\n- CR CY UR UY ... sequences and quality scores of cell barcodes and UMIs for the solo* demultiplexing.\n- GX GN ... gene ID and gene name for unique-gene reads.\n- gx gn ... gene IDs and gene names for unique- and multi-gene reads.\n- CB UB ... error-corrected cell barcodes and UMIs for solo* demultiplexing. Requires --outSAMtype BAM SortedByCoordinate.\n- sM ... assessment of CB and UMI.\n- sS ... sequence of the entire barcode (CB,UMI,adapter).\n- sQ ... quality of the entire barcode.\n- sF ... type of feature overlap and number of features for each alignment\n***Unsupported/undocumented:\n- rB ... alignment block read/genomic coordinates.\n- vR ... read coordinate of the variant.", + "name" : "--out_sam_attributes", + "description" : "a string of desired SAM attributes, in the order desired for the output SAM. Tags can be listed in any combination/order.\n\n***Presets:\n- None ... no attributes\n- Standard ... NH HI AS nM\n- All ... NH HI AS nM NM MD jM jI MC ch\n***Alignment:\n- NH ... number of loci the reads maps to: =1 for unique mappers, >1 for multimappers. Standard SAM tag.\n- HI ... multiple alignment index, starts with --out_sam_attr_ih_start (=1 by default). Standard SAM tag.\n- AS ... local alignment score, +1/-1 for matches/mismateches, score* penalties for indels and gaps. For PE reads, total score for two mates. Stadnard SAM tag.\n- nM ... number of mismatches. For PE reads, sum over two mates.\n- NM ... edit distance to the reference (number of mismatched + inserted + deleted bases) for each mate. Standard SAM tag.\n- MD ... string encoding mismatched and deleted reference bases (see standard SAM specifications). Standard SAM tag.\n- jM ... intron motifs for all junctions (i.e. N in CIGAR): 0: non-canonical; 1: GT/AG, 2: CT/AC, 3: GC/AG, 4: CT/GC, 5: AT/AC, 6: GT/AT. If splice junctions database is used, and a junction is annotated, 20 is added to its motif value.\n- jI ... start and end of introns for all junctions (1-based).\n- XS ... alignment strand according to --out_sam_strand_field.\n- MC ... mate's CIGAR string. Standard SAM tag.\n- ch ... marks all segment of all chimeric alingments for --chim_out_type WithinBAM output.\n- cN ... number of bases clipped from the read ends: 5' and 3'\n***Variation:\n- vA ... variant allele\n- vG ... genomic coordinate of the variant overlapped by the read.\n- vW ... 1 - alignment passes WASP filtering; 2,3,4,5,6,7 - alignment does not pass WASP filtering. Requires --wasp_output_mode SAMtag.\n- ha ... haplotype (1/2) when mapping to the diploid genome. Requires genome generated with --genomeTransformType Diploid .\n***STARsolo:\n- CR CY UR UY ... sequences and quality scores of cell barcodes and UMIs for the solo* demultiplexing.\n- GX GN ... gene ID and gene name for unique-gene reads.\n- gx gn ... gene IDs and gene names for unique- and multi-gene reads.\n- CB UB ... error-corrected cell barcodes and UMIs for solo* demultiplexing. Requires --out_sam_type BAM SortedByCoordinate.\n- sM ... assessment of CB and UMI.\n- sS ... sequence of the entire barcode (CB,UMI,adapter).\n- sQ ... quality of the entire barcode.\n- sF ... type of feature overlap and number of features for each alignment\n***Unsupported/undocumented:\n- rB ... alignment block read/genomic coordinates.\n- vR ... read coordinate of the variant.", + "info" : { + "orig_name" : "--outSAMattributes" + }, "example" : [ "Standard" ], @@ -3412,8 +3650,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outSAMattrIHstart", + "name" : "--out_sam_attr_ih_start", "description" : "start value for the IH attribute. 0 may be required by some downstream software, such as Cufflinks or StringTie.", + "info" : { + "orig_name" : "--outSAMattrIHstart" + }, "example" : [ 1 ], @@ -3424,8 +3665,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMunmapped", + "name" : "--out_sam_unmapped", "description" : "output of unmapped reads in the SAM format\n\n1st word:\n- None ... no output\n- Within ... output unmapped reads within the main SAM file (i.e. Aligned.out.sam)\n2nd word:\n- KeepPairs ... record unmapped mate for each alignment, and, in case of unsorted output, keep it adjacent to its mapped mate. Only affects multi-mapping reads.", + "info" : { + "orig_name" : "--outSAMunmapped" + }, "required" : false, "direction" : "input", "multiple" : true, @@ -3433,8 +3677,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMorder", + "name" : "--out_sam_order", "description" : "type of sorting for the SAM output\n\nPaired: one mate after the other for all paired alignments\nPairedKeepInputOrder: one mate after the other for all paired alignments, the order is kept the same as in the input FASTQ files", + "info" : { + "orig_name" : "--outSAMorder" + }, "example" : [ "Paired" ], @@ -3445,8 +3692,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMprimaryFlag", + "name" : "--out_sam_primary_flag", "description" : "which alignments are considered primary - all others will be marked with 0x100 bit in the FLAG\n\n- OneBestScore ... only one alignment with the best score is primary\n- AllBestScore ... all alignments with the best score are primary", + "info" : { + "orig_name" : "--outSAMprimaryFlag" + }, "example" : [ "OneBestScore" ], @@ -3457,8 +3707,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMreadID", + "name" : "--out_sam_read_id", "description" : "read ID record type\n\n- Standard ... first word (until space) from the FASTx read ID line, removing /1,/2 from the end\n- Number ... read number (index) in the FASTx file", + "info" : { + "orig_name" : "--outSAMreadID" + }, "example" : [ "Standard" ], @@ -3469,8 +3722,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outSAMmapqUnique", + "name" : "--out_sam_mapq_unique", "description" : "0 to 255: the MAPQ value for unique mappers", + "info" : { + "orig_name" : "--outSAMmapqUnique" + }, "example" : [ 255 ], @@ -3481,8 +3737,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outSAMflagOR", + "name" : "--out_sam_flag_or", "description" : "0 to 65535: sam FLAG will be bitwise OR'd with this value, i.e. FLAG=FLAG | outSAMflagOR. This is applied after all flags have been set by STAR, and after outSAMflagAND. Can be used to set specific bits that are not set otherwise.", + "info" : { + "orig_name" : "--outSAMflagOR" + }, "example" : [ 0 ], @@ -3493,8 +3752,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outSAMflagAND", + "name" : "--out_sam_flag_and", "description" : "0 to 65535: sam FLAG will be bitwise AND'd with this value, i.e. FLAG=FLAG & outSAMflagOR. This is applied after all flags have been set by STAR, but before outSAMflagOR. Can be used to unset specific bits that are not set otherwise.", + "info" : { + "orig_name" : "--outSAMflagAND" + }, "example" : [ 65535 ], @@ -3505,8 +3767,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMattrRGline", - "description" : "SAM/BAM read group line. The first word contains the read group identifier and must start with \\"ID:\\", e.g. --outSAMattrRGline ID:xxx CN:yy \\"DS:z z z\\".\n\nxxx will be added as RG tag to each output alignment. Any spaces in the tag values have to be double quoted.\nComma separated RG lines correspons to different (comma separated) input files in --readFilesIn. Commas have to be surrounded by spaces, e.g.\n--outSAMattrRGline ID:xxx , ID:zzz \\"DS:z z\\" , ID:yyy DS:yyyy", + "name" : "--out_sam_attr_rg_line", + "description" : "SAM/BAM read group line. The first word contains the read group identifier and must start with \\"ID:\\", e.g. --out_sam_attr_rg_line ID:xxx CN:yy \\"DS:z z z\\".\n\nxxx will be added as RG tag to each output alignment. Any spaces in the tag values have to be double quoted.\nComma separated RG lines correspons to different (comma separated) input files in --readFilesIn. Commas have to be surrounded by spaces, e.g.\n--out_sam_attr_rg_line ID:xxx , ID:zzz \\"DS:z z\\" , ID:yyy DS:yyyy", + "info" : { + "orig_name" : "--outSAMattrRGline" + }, "required" : false, "direction" : "input", "multiple" : true, @@ -3514,8 +3779,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMheaderHD", + "name" : "--out_sam_header_hd", "description" : "@HD (header) line of the SAM header", + "info" : { + "orig_name" : "--outSAMheaderHD" + }, "required" : false, "direction" : "input", "multiple" : true, @@ -3523,8 +3791,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMheaderPG", + "name" : "--out_sam_header_pg", "description" : "extra @PG (software) line of the SAM header (in addition to STAR)", + "info" : { + "orig_name" : "--outSAMheaderPG" + }, "required" : false, "direction" : "input", "multiple" : true, @@ -3532,8 +3803,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMheaderCommentFile", + "name" : "--out_sam_header_comment_file", "description" : "path to the file with @CO (comment) lines of the SAM header", + "info" : { + "orig_name" : "--outSAMheaderCommentFile" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -3541,8 +3815,11 @@ meta = [ }, { "type" : "string", - "name" : "--outSAMfilter", - "description" : "filter the output into main SAM/BAM files\n\n- KeepOnlyAddedReferences ... only keep the reads for which all alignments are to the extra reference sequences added with --genomeFastaFiles at the mapping stage.\n- KeepAllAddedReferences ... keep all alignments to the extra reference sequences added with --genomeFastaFiles at the mapping stage.", + "name" : "--out_sam_filter", + "description" : "filter the output into main SAM/BAM files\n\n- KeepOnlyAddedReferences ... only keep the reads for which all alignments are to the extra reference sequences added with --genome_fasta_files at the mapping stage.\n- KeepAllAddedReferences ... keep all alignments to the extra reference sequences added with --genome_fasta_files at the mapping stage.", + "info" : { + "orig_name" : "--outSAMfilter" + }, "required" : false, "direction" : "input", "multiple" : true, @@ -3550,8 +3827,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outSAMmultNmax", - "description" : "max number of multiple alignments for a read that will be output to the SAM/BAM files. Note that if this value is not equal to -1, the top scoring alignment will be output first\n\n- -1 ... all alignments (up to --outFilterMultimapNmax) will be output", + "name" : "--out_sam_mult_nmax", + "description" : "max number of multiple alignments for a read that will be output to the SAM/BAM files. Note that if this value is not equal to -1, the top scoring alignment will be output first\n\n- -1 ... all alignments (up to --out_filter_multimap_nmax) will be output", + "info" : { + "orig_name" : "--outSAMmultNmax" + }, "example" : [ -1 ], @@ -3562,8 +3842,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outSAMtlen", + "name" : "--out_sam_tlen", "description" : "calculation method for the TLEN field in the SAM/BAM files\n\n- 1 ... leftmost base of the (+)strand mate to rightmost base of the (-)mate. (+)sign for the (+)strand mate\n- 2 ... leftmost base of any mate to rightmost base of any mate. (+)sign for the mate with the leftmost base. This is different from 1 for overlapping mates with protruding ends", + "info" : { + "orig_name" : "--outSAMtlen" + }, "example" : [ 1 ], @@ -3574,8 +3857,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outBAMcompression", + "name" : "--out_bam_compression", "description" : "-1 to 10 BAM compression level, -1=default compression (6?), 0=no compression, 10=maximum compression", + "info" : { + "orig_name" : "--outBAMcompression" + }, "example" : [ 1 ], @@ -3586,8 +3872,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outBAMsortingThreadN", + "name" : "--out_bam_sorting_thread_n", "description" : ">=0: number of threads for BAM sorting. 0 will default to min(6,--runThreadN).", + "info" : { + "orig_name" : "--outBAMsortingThreadN" + }, "example" : [ 0 ], @@ -3598,8 +3887,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outBAMsortingBinsN", + "name" : "--out_bam_sorting_bins_n", "description" : ">0: number of genome bins for coordinate-sorting", + "info" : { + "orig_name" : "--outBAMsortingBinsN" + }, "example" : [ 50 ], @@ -3615,8 +3907,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--bamRemoveDuplicatesType", + "name" : "--bam_remove_duplicates_type", "description" : "mark duplicates in the BAM file, for now only works with (i) sorted BAM fed with inputBAMfile, and (ii) for paired-end alignments only\n\n- - ... no duplicate removal/marking\n- UniqueIdentical ... mark all multimappers, and duplicate unique mappers. The coordinates, FLAG, CIGAR must be identical\n- UniqueIdenticalNotMulti ... mark duplicate unique mappers but not multimappers.", + "info" : { + "orig_name" : "--bamRemoveDuplicatesType" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -3624,8 +3919,11 @@ meta = [ }, { "type" : "integer", - "name" : "--bamRemoveDuplicatesMate2basesN", + "name" : "--bam_remove_duplicates_mate2bases_n", "description" : "number of bases from the 5' of mate 2 to use in collapsing (e.g. for RAMPAGE)", + "info" : { + "orig_name" : "--bamRemoveDuplicatesMate2basesN" + }, "example" : [ 0 ], @@ -3641,8 +3939,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--outWigType", - "description" : "type of signal output, e.g. \\"bedGraph\\" OR \\"bedGraph read1_5p\\". Requires sorted BAM: --outSAMtype BAM SortedByCoordinate .\n\n1st word:\n- None ... no signal output\n- bedGraph ... bedGraph format\n- wiggle ... wiggle format\n2nd word:\n- read1_5p ... signal from only 5' of the 1st read, useful for CAGE/RAMPAGE etc\n- read2 ... signal from only 2nd read", + "name" : "--out_wig_type", + "description" : "type of signal output, e.g. \\"bedGraph\\" OR \\"bedGraph read1_5p\\". Requires sorted BAM: --out_sam_type BAM SortedByCoordinate .\n\n1st word:\n- None ... no signal output\n- bedGraph ... bedGraph format\n- wiggle ... wiggle format\n2nd word:\n- read1_5p ... signal from only 5' of the 1st read, useful for CAGE/RAMPAGE etc\n- read2 ... signal from only 2nd read", + "info" : { + "orig_name" : "--outWigType" + }, "required" : false, "direction" : "input", "multiple" : true, @@ -3650,8 +3951,11 @@ meta = [ }, { "type" : "string", - "name" : "--outWigStrand", + "name" : "--out_wig_strand", "description" : "strandedness of wiggle/bedGraph output\n\n- Stranded ... separate strands, str1 and str2\n- Unstranded ... collapsed strands", + "info" : { + "orig_name" : "--outWigStrand" + }, "example" : [ "Stranded" ], @@ -3662,8 +3966,11 @@ meta = [ }, { "type" : "string", - "name" : "--outWigReferencesPrefix", + "name" : "--out_wig_references_prefix", "description" : "prefix matching reference names to include in the output wiggle file, e.g. \\"chr\\", default \\"-\\" - include all references", + "info" : { + "orig_name" : "--outWigReferencesPrefix" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -3671,8 +3978,11 @@ meta = [ }, { "type" : "string", - "name" : "--outWigNorm", + "name" : "--out_wig_norm", "description" : "type of normalization for the signal\n\n- RPM ... reads per million of mapped reads\n- None ... no normalization, \\"raw\\" counts", + "info" : { + "orig_name" : "--outWigNorm" + }, "example" : [ "RPM" ], @@ -3688,8 +3998,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--outFilterType", + "name" : "--out_filter_type", "description" : "type of filtering\n\n- Normal ... standard filtering using only current alignment\n- BySJout ... keep only those reads that contain junctions that passed filtering into SJ.out.tab", + "info" : { + "orig_name" : "--outFilterType" + }, "example" : [ "Normal" ], @@ -3700,8 +4013,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outFilterMultimapScoreRange", + "name" : "--out_filter_multimap_score_range", "description" : "the score range below the maximum score for multimapping alignments", + "info" : { + "orig_name" : "--outFilterMultimapScoreRange" + }, "example" : [ 1 ], @@ -3712,8 +4028,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outFilterMultimapNmax", + "name" : "--out_filter_multimap_nmax", "description" : "maximum number of loci the read is allowed to map to. Alignments (all of them) will be output only if the read maps to no more loci than this value.\n\nOtherwise no alignments will be output, and the read will be counted as \\"mapped to too many loci\\" in the Log.final.out .", + "info" : { + "orig_name" : "--outFilterMultimapNmax" + }, "example" : [ 10 ], @@ -3724,8 +4043,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outFilterMismatchNmax", + "name" : "--out_filter_mismatch_nmax", "description" : "alignment will be output only if it has no more mismatches than this value.", + "info" : { + "orig_name" : "--outFilterMismatchNmax" + }, "example" : [ 10 ], @@ -3736,8 +4058,11 @@ meta = [ }, { "type" : "double", - "name" : "--outFilterMismatchNoverLmax", + "name" : "--out_filter_mismatch_nover_lmax", "description" : "alignment will be output only if its ratio of mismatches to *mapped* length is less than or equal to this value.", + "info" : { + "orig_name" : "--outFilterMismatchNoverLmax" + }, "example" : [ 0.3 ], @@ -3748,8 +4073,11 @@ meta = [ }, { "type" : "double", - "name" : "--outFilterMismatchNoverReadLmax", + "name" : "--out_filter_mismatch_nover_read_lmax", "description" : "alignment will be output only if its ratio of mismatches to *read* length is less than or equal to this value.", + "info" : { + "orig_name" : "--outFilterMismatchNoverReadLmax" + }, "example" : [ 1.0 ], @@ -3760,8 +4088,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outFilterScoreMin", + "name" : "--out_filter_score_min", "description" : "alignment will be output only if its score is higher than or equal to this value.", + "info" : { + "orig_name" : "--outFilterScoreMin" + }, "example" : [ 0 ], @@ -3772,8 +4103,11 @@ meta = [ }, { "type" : "double", - "name" : "--outFilterScoreMinOverLread", + "name" : "--out_filter_score_min_over_lread", "description" : "same as outFilterScoreMin, but normalized to read length (sum of mates' lengths for paired-end reads)", + "info" : { + "orig_name" : "--outFilterScoreMinOverLread" + }, "example" : [ 0.66 ], @@ -3784,8 +4118,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outFilterMatchNmin", + "name" : "--out_filter_match_nmin", "description" : "alignment will be output only if the number of matched bases is higher than or equal to this value.", + "info" : { + "orig_name" : "--outFilterMatchNmin" + }, "example" : [ 0 ], @@ -3796,8 +4133,11 @@ meta = [ }, { "type" : "double", - "name" : "--outFilterMatchNminOverLread", + "name" : "--out_filter_match_nmin_over_lread", "description" : "sam as outFilterMatchNmin, but normalized to the read length (sum of mates' lengths for paired-end reads).", + "info" : { + "orig_name" : "--outFilterMatchNminOverLread" + }, "example" : [ 0.66 ], @@ -3808,8 +4148,11 @@ meta = [ }, { "type" : "string", - "name" : "--outFilterIntronMotifs", + "name" : "--out_filter_intron_motifs", "description" : "filter alignment using their motifs\n\n- None ... no filtering\n- RemoveNoncanonical ... filter out alignments that contain non-canonical junctions\n- RemoveNoncanonicalUnannotated ... filter out alignments that contain non-canonical unannotated junctions when using annotated splice junctions database. The annotated non-canonical junctions will be kept.", + "info" : { + "orig_name" : "--outFilterIntronMotifs" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -3817,8 +4160,11 @@ meta = [ }, { "type" : "string", - "name" : "--outFilterIntronStrands", + "name" : "--out_filter_intron_strands", "description" : "filter alignments\n\n- RemoveInconsistentStrands ... remove alignments that have junctions with inconsistent strands\n- None ... no filtering", + "info" : { + "orig_name" : "--outFilterIntronStrands" + }, "example" : [ "RemoveInconsistentStrands" ], @@ -3834,8 +4180,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--outSJtype", + "name" : "--out_sj_type", "description" : "type of splice junction output\n\n- Standard ... standard SJ.out.tab output\n- None ... no splice junction output", + "info" : { + "orig_name" : "--outSJtype" + }, "example" : [ "Standard" ], @@ -3851,8 +4200,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--outSJfilterReads", + "name" : "--out_sj_filter_reads", "description" : "which reads to consider for collapsed splice junctions output\n\n- All ... all reads, unique- and multi-mappers\n- Unique ... uniquely mapping reads only", + "info" : { + "orig_name" : "--outSJfilterReads" + }, "example" : [ "All" ], @@ -3863,8 +4215,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outSJfilterOverhangMin", + "name" : "--out_sj_filter_overhang_min", "description" : "minimum overhang length for splice junctions on both sides for: (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif. -1 means no output for that motif\n\ndoes not apply to annotated junctions", + "info" : { + "orig_name" : "--outSJfilterOverhangMin" + }, "example" : [ 30, 12, @@ -3878,8 +4233,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outSJfilterCountUniqueMin", + "name" : "--out_sj_filter_count_unique_min", "description" : "minimum uniquely mapping read count per junction for: (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif. -1 means no output for that motif\n\nJunctions are output if one of outSJfilterCountUniqueMin OR outSJfilterCountTotalMin conditions are satisfied\ndoes not apply to annotated junctions", + "info" : { + "orig_name" : "--outSJfilterCountUniqueMin" + }, "example" : [ 3, 1, @@ -3893,8 +4251,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outSJfilterCountTotalMin", + "name" : "--out_sj_filter_count_total_min", "description" : "minimum total (multi-mapping+unique) read count per junction for: (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif. -1 means no output for that motif\n\nJunctions are output if one of outSJfilterCountUniqueMin OR outSJfilterCountTotalMin conditions are satisfied\ndoes not apply to annotated junctions", + "info" : { + "orig_name" : "--outSJfilterCountTotalMin" + }, "example" : [ 3, 1, @@ -3908,8 +4269,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outSJfilterDistToOtherSJmin", + "name" : "--out_sj_filter_dist_to_other_sj_min", "description" : "minimum allowed distance to other junctions' donor/acceptor\n\ndoes not apply to annotated junctions", + "info" : { + "orig_name" : "--outSJfilterDistToOtherSJmin" + }, "example" : [ 10, 0, @@ -3923,8 +4287,11 @@ meta = [ }, { "type" : "integer", - "name" : "--outSJfilterIntronMaxVsReadN", + "name" : "--out_sj_filter_intron_max_vs_read_n", "description" : "maximum gap allowed for junctions supported by 1,2,3,,,N reads\n\ni.e. by default junctions supported by 1 read can have gaps <=50000b, by 2 reads: <=100000b, by 3 reads: <=200000. by >=4 reads any gap <=alignIntronMax\ndoes not apply to annotated junctions", + "info" : { + "orig_name" : "--outSJfilterIntronMaxVsReadN" + }, "example" : [ 50000, 100000, @@ -3942,8 +4309,11 @@ meta = [ "arguments" : [ { "type" : "integer", - "name" : "--scoreGap", + "name" : "--score_gap", "description" : "splice junction penalty (independent on intron motif)", + "info" : { + "orig_name" : "--scoreGap" + }, "example" : [ 0 ], @@ -3954,8 +4324,11 @@ meta = [ }, { "type" : "integer", - "name" : "--scoreGapNoncan", + "name" : "--score_gap_noncan", "description" : "non-canonical junction penalty (in addition to scoreGap)", + "info" : { + "orig_name" : "--scoreGapNoncan" + }, "example" : [ -8 ], @@ -3966,8 +4339,11 @@ meta = [ }, { "type" : "integer", - "name" : "--scoreGapGCAG", + "name" : "--score_gap_gcag", "description" : "GC/AG and CT/GC junction penalty (in addition to scoreGap)", + "info" : { + "orig_name" : "--scoreGapGCAG" + }, "example" : [ -4 ], @@ -3978,8 +4354,11 @@ meta = [ }, { "type" : "integer", - "name" : "--scoreGapATAC", + "name" : "--score_gap_atac", "description" : "AT/AC and GT/AT junction penalty (in addition to scoreGap)", + "info" : { + "orig_name" : "--scoreGapATAC" + }, "example" : [ -8 ], @@ -3990,8 +4369,11 @@ meta = [ }, { "type" : "integer", - "name" : "--scoreGenomicLengthLog2scale", + "name" : "--score_genomic_length_log2scale", "description" : "extra score logarithmically scaled with genomic length of the alignment: scoreGenomicLengthLog2scale*log2(genomicLength)", + "info" : { + "orig_name" : "--scoreGenomicLengthLog2scale" + }, "example" : [ 0 ], @@ -4002,8 +4384,11 @@ meta = [ }, { "type" : "integer", - "name" : "--scoreDelOpen", + "name" : "--score_del_open", "description" : "deletion open penalty", + "info" : { + "orig_name" : "--scoreDelOpen" + }, "example" : [ -2 ], @@ -4014,8 +4399,11 @@ meta = [ }, { "type" : "integer", - "name" : "--scoreDelBase", + "name" : "--score_del_base", "description" : "deletion extension penalty per base (in addition to scoreDelOpen)", + "info" : { + "orig_name" : "--scoreDelBase" + }, "example" : [ -2 ], @@ -4026,8 +4414,11 @@ meta = [ }, { "type" : "integer", - "name" : "--scoreInsOpen", + "name" : "--score_ins_open", "description" : "insertion open penalty", + "info" : { + "orig_name" : "--scoreInsOpen" + }, "example" : [ -2 ], @@ -4038,8 +4429,11 @@ meta = [ }, { "type" : "integer", - "name" : "--scoreInsBase", + "name" : "--score_ins_base", "description" : "insertion extension penalty per base (in addition to scoreInsOpen)", + "info" : { + "orig_name" : "--scoreInsBase" + }, "example" : [ -2 ], @@ -4050,8 +4444,11 @@ meta = [ }, { "type" : "integer", - "name" : "--scoreStitchSJshift", + "name" : "--score_stitch_sj_shift", "description" : "maximum score reduction while searching for SJ boundaries in the stitching step", + "info" : { + "orig_name" : "--scoreStitchSJshift" + }, "example" : [ 1 ], @@ -4067,8 +4464,11 @@ meta = [ "arguments" : [ { "type" : "integer", - "name" : "--seedSearchStartLmax", + "name" : "--seed_search_start_lmax", "description" : "defines the search start point through the read - the read is split into pieces no longer than this value", + "info" : { + "orig_name" : "--seedSearchStartLmax" + }, "example" : [ 50 ], @@ -4079,8 +4479,11 @@ meta = [ }, { "type" : "double", - "name" : "--seedSearchStartLmaxOverLread", + "name" : "--seed_search_start_lmax_over_lread", "description" : "seedSearchStartLmax normalized to read length (sum of mates' lengths for paired-end reads)", + "info" : { + "orig_name" : "--seedSearchStartLmaxOverLread" + }, "example" : [ 1.0 ], @@ -4091,8 +4494,11 @@ meta = [ }, { "type" : "integer", - "name" : "--seedSearchLmax", + "name" : "--seed_search_lmax", "description" : "defines the maximum length of the seeds, if =0 seed length is not limited", + "info" : { + "orig_name" : "--seedSearchLmax" + }, "example" : [ 0 ], @@ -4103,8 +4509,11 @@ meta = [ }, { "type" : "integer", - "name" : "--seedMultimapNmax", + "name" : "--seed_multimap_nmax", "description" : "only pieces that map fewer than this value are utilized in the stitching procedure", + "info" : { + "orig_name" : "--seedMultimapNmax" + }, "example" : [ 10000 ], @@ -4115,8 +4524,11 @@ meta = [ }, { "type" : "integer", - "name" : "--seedPerReadNmax", + "name" : "--seed_per_read_nmax", "description" : "max number of seeds per read", + "info" : { + "orig_name" : "--seedPerReadNmax" + }, "example" : [ 1000 ], @@ -4127,8 +4539,11 @@ meta = [ }, { "type" : "integer", - "name" : "--seedPerWindowNmax", + "name" : "--seed_per_window_nmax", "description" : "max number of seeds per window", + "info" : { + "orig_name" : "--seedPerWindowNmax" + }, "example" : [ 50 ], @@ -4139,8 +4554,11 @@ meta = [ }, { "type" : "integer", - "name" : "--seedNoneLociPerWindow", + "name" : "--seed_none_loci_per_window", "description" : "max number of one seed loci per window", + "info" : { + "orig_name" : "--seedNoneLociPerWindow" + }, "example" : [ 10 ], @@ -4151,8 +4569,11 @@ meta = [ }, { "type" : "integer", - "name" : "--seedSplitMin", - "description" : "min length of the seed sequences split by Ns or mate gap", + "name" : "--seed_split_min", + "description" : "min length of the seed sequen''' + '''ces split by Ns or mate gap", + "info" : { + "orig_name" : "--seedSplitMin" + }, "example" : [ 12 ], @@ -4163,8 +4584,11 @@ meta = [ }, { "type" : "integer", - "name" : "--seedMapMin", + "name" : "--seed_map_min", "description" : "min length of seeds to be mapped", + "info" : { + "orig_name" : "--seedMapMin" + }, "example" : [ 5 ], @@ -4175,8 +4599,11 @@ meta = [ }, { "type" : "integer", - "name" : "--alignIntronMin", + "name" : "--align_intron_min", "description" : "minimum intron size, genomic gap is considered intron if its length>=alignIntronMin, otherwise it is considered Deletion", + "info" : { + "orig_name" : "--alignIntronMin" + }, "example" : [ 21 ], @@ -4187,8 +4614,11 @@ meta = [ }, { "type" : "integer", - "name" : "--alignIntronMax", + "name" : "--align_intron_max", "description" : "maximum intron size, if 0, max intron size will be determined by (2^winBinNbits)*winAnchorDistNbins", + "info" : { + "orig_name" : "--alignIntronMax" + }, "example" : [ 0 ], @@ -4199,8 +4629,11 @@ meta = [ }, { "type" : "integer", - "name" : "--alignMatesGapMax", + "name" : "--align_mates_gap_max", "description" : "maximum gap between two mates, if 0, max intron gap will be determined by (2^winBinNbits)*winAnchorDistNbins", + "info" : { + "orig_name" : "--alignMatesGapMax" + }, "example" : [ 0 ], @@ -4211,8 +4644,11 @@ meta = [ }, { "type" : "integer", - "name" : "--alignSJoverhangMin", + "name" : "--align_sj_overhang_min", "description" : "minimum overhang (i.e. block size) for spliced alignments", + "info" : { + "orig_name" : "--alignSJoverhangMin" + }, "example" : [ 5 ], @@ -4223,8 +4659,11 @@ meta = [ }, { "type" : "integer", - "name" : "--alignSJstitchMismatchNmax", + "name" : "--align_sj_stitch_mismatch_nmax", "description" : "maximum number of mismatches for stitching of the splice junctions (-1: no limit).\n\n(1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif.", + "info" : { + "orig_name" : "--alignSJstitchMismatchNmax" + }, "example" : [ 0, -1, @@ -4238,8 +4677,11 @@ meta = [ }, { "type" : "integer", - "name" : "--alignSJDBoverhangMin", + "name" : "--align_sjdb_overhang_min", "description" : "minimum overhang (i.e. block size) for annotated (sjdb) spliced alignments", + "info" : { + "orig_name" : "--alignSJDBoverhangMin" + }, "example" : [ 3 ], @@ -4250,8 +4692,11 @@ meta = [ }, { "type" : "integer", - "name" : "--alignSplicedMateMapLmin", + "name" : "--align_spliced_mate_map_lmin", "description" : "minimum mapped length for a read mate that is spliced", + "info" : { + "orig_name" : "--alignSplicedMateMapLmin" + }, "example" : [ 0 ], @@ -4262,8 +4707,11 @@ meta = [ }, { "type" : "double", - "name" : "--alignSplicedMateMapLminOverLmate", + "name" : "--align_spliced_mate_map_lmin_over_lmate", "description" : "alignSplicedMateMapLmin normalized to mate length", + "info" : { + "orig_name" : "--alignSplicedMateMapLminOverLmate" + }, "example" : [ 0.66 ], @@ -4274,8 +4722,11 @@ meta = [ }, { "type" : "integer", - "name" : "--alignWindowsPerReadNmax", + "name" : "--align_windows_per_read_nmax", "description" : "max number of windows per read", + "info" : { + "orig_name" : "--alignWindowsPerReadNmax" + }, "example" : [ 10000 ], @@ -4286,8 +4737,11 @@ meta = [ }, { "type" : "integer", - "name" : "--alignTranscriptsPerWindowNmax", + "name" : "--align_transcripts_per_window_nmax", "description" : "max number of transcripts per window", + "info" : { + "orig_name" : "--alignTranscriptsPerWindowNmax" + }, "example" : [ 100 ], @@ -4298,8 +4752,11 @@ meta = [ }, { "type" : "integer", - "name" : "--alignTranscriptsPerReadNmax", + "name" : "--align_transcripts_per_read_nmax", "description" : "max number of different alignments per read to consider", + "info" : { + "orig_name" : "--alignTranscriptsPerReadNmax" + }, "example" : [ 10000 ], @@ -4310,8 +4767,11 @@ meta = [ }, { "type" : "string", - "name" : "--alignEndsType", + "name" : "--align_ends_type", "description" : "type of read ends alignment\n\n- Local ... standard local alignment with soft-clipping allowed\n- EndToEnd ... force end-to-end read alignment, do not soft-clip\n- Extend5pOfRead1 ... fully extend only the 5p of the read1, all other ends: local alignment\n- Extend5pOfReads12 ... fully extend only the 5p of the both read1 and read2, all other ends: local alignment", + "info" : { + "orig_name" : "--alignEndsType" + }, "example" : [ "Local" ], @@ -4322,8 +4782,11 @@ meta = [ }, { "type" : "string", - "name" : "--alignEndsProtrude", + "name" : "--align_ends_protrude", "description" : "allow protrusion of alignment ends, i.e. start (end) of the +strand mate downstream of the start (end) of the -strand mate\n\n1st word: int: maximum number of protrusion bases allowed\n2nd word: string:\n- ConcordantPair ... report alignments with non-zero protrusion as concordant pairs\n- DiscordantPair ... report alignments with non-zero protrusion as discordant pairs", + "info" : { + "orig_name" : "--alignEndsProtrude" + }, "example" : [ "0 ConcordantPair" ], @@ -4334,8 +4797,11 @@ meta = [ }, { "type" : "string", - "name" : "--alignSoftClipAtReferenceEnds", + "name" : "--align_soft_clip_at_reference_ends", "description" : "allow the soft-clipping of the alignments past the end of the chromosomes\n\n- Yes ... allow\n- No ... prohibit, useful for compatibility with Cufflinks", + "info" : { + "orig_name" : "--alignSoftClipAtReferenceEnds" + }, "example" : [ "Yes" ], @@ -4346,8 +4812,11 @@ meta = [ }, { "type" : "string", - "name" : "--alignInsertionFlush", + "name" : "--align_insertion_flush", "description" : "how to flush ambiguous insertion positions\n\n- None ... insertions are not flushed\n- Right ... insertions are flushed to the right", + "info" : { + "orig_name" : "--alignInsertionFlush" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -4360,8 +4829,11 @@ meta = [ "arguments" : [ { "type" : "integer", - "name" : "--peOverlapNbasesMin", + "name" : "--pe_overlap_nbases_min", "description" : "minimum number of overlapping bases to trigger mates merging and realignment. Specify >0 value to switch on the \\"merginf of overlapping mates\\" algorithm.", + "info" : { + "orig_name" : "--peOverlapNbasesMin" + }, "example" : [ 0 ], @@ -4372,8 +4844,11 @@ meta = [ }, { "type" : "double", - "name" : "--peOverlapMMp", + "name" : "--pe_overlap_mm_p", "description" : "maximum proportion of mismatched bases in the overlap area", + "info" : { + "orig_name" : "--peOverlapMMp" + }, "example" : [ 0.01 ], @@ -4389,8 +4864,11 @@ meta = [ "arguments" : [ { "type" : "integer", - "name" : "--winAnchorMultimapNmax", + "name" : "--win_anchor_multimap_nmax", "description" : "max number of loci anchors are allowed to map to", + "info" : { + "orig_name" : "--winAnchorMultimapNmax" + }, "example" : [ 50 ], @@ -4401,8 +4879,11 @@ meta = [ }, { "type" : "integer", - "name" : "--winBinNbits", + "name" : "--win_bin_nbits", "description" : "=log2(winBin), where winBin is the size of the bin for the windows/clustering, each window will occupy an integer number of bins.", + "info" : { + "orig_name" : "--winBinNbits" + }, "example" : [ 16 ], @@ -4413,8 +4894,11 @@ meta = [ }, { "type" : "integer", - "name" : "--winAnchorDistNbins", + "name" : "--win_anchor_dist_nbins", "description" : "max number of bins between two anchors that allows aggregation of anchors into one window", + "info" : { + "orig_name" : "--winAnchorDistNbins" + }, "example" : [ 9 ], @@ -4425,8 +4909,11 @@ meta = [ }, { "type" : "integer", - "name" : "--winFlankNbins", + "name" : "--win_flank_nbins", "description" : "log2(winFlank), where win Flank is the size of the left and right flanking regions for each window", + "info" : { + "orig_name" : "--winFlankNbins" + }, "example" : [ 4 ], @@ -4437,8 +4924,11 @@ meta = [ }, { "type" : "double", - "name" : "--winReadCoverageRelativeMin", + "name" : "--win_read_coverage_relative_min", "description" : "minimum relative coverage of the read sequence by the seeds in a window, for STARlong algorithm only.", + "info" : { + "orig_name" : "--winReadCoverageRelativeMin" + }, "example" : [ 0.5 ], @@ -4449,8 +4939,11 @@ meta = [ }, { "type" : "integer", - "name" : "--winReadCoverageBasesMin", + "name" : "--win_read_coverage_bases_min", "description" : "minimum number of bases covered by the seeds in a window , for STARlong algorithm only.", + "info" : { + "orig_name" : "--winReadCoverageBasesMin" + }, "example" : [ 0 ], @@ -4466,8 +4959,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--chimOutType", - "description" : "type of chimeric output\n\n- Junctions ... Chimeric.out.junction\n- SeparateSAMold ... output old SAM into separate Chimeric.out.sam file\n- WithinBAM ... output into main aligned BAM files (Aligned.*.bam)\n- WithinBAM HardClip ... (defa''' + '''ult) hard-clipping in the CIGAR for supplemental chimeric alignments (default if no 2nd word is present)\n- WithinBAM SoftClip ... soft-clipping in the CIGAR for supplemental chimeric alignments", + "name" : "--chim_out_type", + "description" : "type of chimeric output\n\n- Junctions ... Chimeric.out.junction\n- SeparateSAMold ... output old SAM into separate Chimeric.out.sam file\n- WithinBAM ... output into main aligned BAM files (Aligned.*.bam)\n- WithinBAM HardClip ... (default) hard-clipping in the CIGAR for supplemental chimeric alignments (default if no 2nd word is present)\n- WithinBAM SoftClip ... soft-clipping in the CIGAR for supplemental chimeric alignments", + "info" : { + "orig_name" : "--chimOutType" + }, "example" : [ "Junctions" ], @@ -4478,8 +4974,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimSegmentMin", + "name" : "--chim_segment_min", "description" : "minimum length of chimeric segment length, if ==0, no chimeric output", + "info" : { + "orig_name" : "--chimSegmentMin" + }, "example" : [ 0 ], @@ -4490,8 +4989,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimScoreMin", + "name" : "--chim_score_min", "description" : "minimum total (summed) score of the chimeric segments", + "info" : { + "orig_name" : "--chimScoreMin" + }, "example" : [ 0 ], @@ -4502,8 +5004,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimScoreDropMax", + "name" : "--chim_score_drop_max", "description" : "max drop (difference) of chimeric score (the sum of scores of all chimeric segments) from the read length", + "info" : { + "orig_name" : "--chimScoreDropMax" + }, "example" : [ 20 ], @@ -4514,8 +5019,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimScoreSeparation", + "name" : "--chim_score_separation", "description" : "minimum difference (separation) between the best chimeric score and the next one", + "info" : { + "orig_name" : "--chimScoreSeparation" + }, "example" : [ 10 ], @@ -4526,8 +5034,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimScoreJunctionNonGTAG", + "name" : "--chim_score_junction_non_gtag", "description" : "penalty for a non-GT/AG chimeric junction", + "info" : { + "orig_name" : "--chimScoreJunctionNonGTAG" + }, "example" : [ -1 ], @@ -4538,8 +5049,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimJunctionOverhangMin", + "name" : "--chim_junction_overhang_min", "description" : "minimum overhang for a chimeric junction", + "info" : { + "orig_name" : "--chimJunctionOverhangMin" + }, "example" : [ 20 ], @@ -4550,8 +5064,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimSegmentReadGapMax", + "name" : "--chim_segment_read_gap_max", "description" : "maximum gap in the read sequence between chimeric segments", + "info" : { + "orig_name" : "--chimSegmentReadGapMax" + }, "example" : [ 0 ], @@ -4562,8 +5079,11 @@ meta = [ }, { "type" : "string", - "name" : "--chimFilter", + "name" : "--chim_filter", "description" : "different filters for chimeric alignments\n\n- None ... no filtering\n- banGenomicN ... Ns are not allowed in the genome sequence around the chimeric junction", + "info" : { + "orig_name" : "--chimFilter" + }, "example" : [ "banGenomicN" ], @@ -4574,8 +5094,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimMainSegmentMultNmax", + "name" : "--chim_main_segment_mult_nmax", "description" : "maximum number of multi-alignments for the main chimeric segment. =1 will prohibit multimapping main segments.", + "info" : { + "orig_name" : "--chimMainSegmentMultNmax" + }, "example" : [ 10 ], @@ -4586,8 +5109,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimMultimapNmax", + "name" : "--chim_multimap_nmax", "description" : "maximum number of chimeric multi-alignments\n\n- 0 ... use the old scheme for chimeric detection which only considered unique alignments", + "info" : { + "orig_name" : "--chimMultimapNmax" + }, "example" : [ 0 ], @@ -4598,8 +5124,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimMultimapScoreRange", - "description" : "the score range for multi-mapping chimeras below the best chimeric score. Only works with --chimMultimapNmax > 1", + "name" : "--chim_multimap_score_range", + "description" : "the score range for multi-mapping chimeras below the best chimeric score. Only works with --chim_multimap_nmax > 1", + "info" : { + "orig_name" : "--chimMultimapScoreRange" + }, "example" : [ 1 ], @@ -4610,8 +5139,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimNonchimScoreDropMin", + "name" : "--chim_nonchim_score_drop_min", "description" : "to trigger chimeric detection, the drop in the best non-chimeric alignment score with respect to the read length has to be greater than this value", + "info" : { + "orig_name" : "--chimNonchimScoreDropMin" + }, "example" : [ 20 ], @@ -4622,8 +5154,11 @@ meta = [ }, { "type" : "integer", - "name" : "--chimOutJunctionFormat", + "name" : "--chim_out_junction_format", "description" : "formatting type for the Chimeric.out.junction file\n\n- 0 ... no comment lines/headers\n- 1 ... comment lines at the end of the file: command line and Nreads: total, unique/multi-mapping", + "info" : { + "orig_name" : "--chimOutJunctionFormat" + }, "example" : [ 0 ], @@ -4639,8 +5174,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--quantMode", + "name" : "--quant_mode", "description" : "types of quantification requested\n\n- - ... none\n- TranscriptomeSAM ... output SAM/BAM alignments to transcriptome into a separate file\n- GeneCounts ... count reads per gene", + "info" : { + "orig_name" : "--quantMode" + }, "required" : false, "direction" : "input", "multiple" : true, @@ -4648,8 +5186,11 @@ meta = [ }, { "type" : "integer", - "name" : "--quantTranscriptomeBAMcompression", + "name" : "--quant_transcriptome_bam_compression", "description" : "-2 to 10 transcriptome BAM compression level\n\n- -2 ... no BAM output\n- -1 ... default compression (6?)\n- 0 ... no compression\n- 10 ... maximum compression", + "info" : { + "orig_name" : "--quantTranscriptomeBAMcompression" + }, "example" : [ 1 ], @@ -4660,8 +5201,11 @@ meta = [ }, { "type" : "string", - "name" : "--quantTranscriptomeSAMoutput", + "name" : "--quant_transcriptome_sam_output", "description" : "alignment filtering for TranscriptomeSAM output\n\n- BanSingleEnd_BanIndels_ExtendSoftclip ... prohibit indels and single-end alignments, extend softclips - compatible with RSEM\n- BanSingleEnd ... prohibit single-end alignments, allow indels and softclips\n- BanSingleEnd_ExtendSoftclip ... prohibit single-end alignments, extend softclips, allow indels", + "info" : { + "orig_name" : "--quantTranscriptomeSAMoutput" + }, "example" : [ "BanSingleEnd_BanIndels_ExtendSoftclip" ], @@ -4677,8 +5221,11 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--twopassMode", + "name" : "--twopass_mode", "description" : "2-pass mapping mode.\n\n- None ... 1-pass mapping\n- Basic ... basic 2-pass mapping, with all 1st pass junctions inserted into the genome indices on the fly", + "info" : { + "orig_name" : "--twopassMode" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -4686,8 +5233,11 @@ meta = [ }, { "type" : "integer", - "name" : "--twopass1readsN", + "name" : "--twopass1reads_n", "description" : "number of reads to process for the 1st step. Use very large number (or default -1) to map all reads in the first step.", + "info" : { + "orig_name" : "--twopass1readsN" + }, "example" : [ -1 ], @@ -4703,8 +5253,370 @@ meta = [ "arguments" : [ { "type" : "string", - "name" : "--waspOutputMode", + "name" : "--wasp_output_mode", "description" : "WASP allele-specific output type. This is re-implementation of the original WASP mappability filtering by Bryce van de Geijn, Graham McVicker, Yoav Gilad & Jonathan K Pritchard. Please cite the original WASP paper: Nature Methods 12, 1061-1063 (2015), https://www.nature.com/articles/nmeth.3582 .\n\n- SAMtag ... add WASP tags to the alignments that pass WASP filtering", + "info" : { + "orig_name" : "--waspOutputMode" + }, + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + } + ] + }, + { + "name" : "STARsolo (single cell RNA-seq) parameters", + "arguments" : [ + { + "type" : "string", + "name" : "--solo_type", + "description" : "type of single-cell RNA-seq\n\n- CB_UMI_Simple ... (a.k.a. Droplet) one UMI and one Cell Barcode of fixed length in read2, e.g. Drop-seq and 10X Chromium.\n- CB_UMI_Complex ... multiple Cell Barcodes of varying length, one UMI of fixed length and one adapter sequence of fixed length are allowed in read2 only (e.g. inDrop, ddSeq).\n- CB_samTagOut ... output Cell Barcode as CR and/or CB SAm tag. No UMI counting. --readFilesIn cDNA_read1 [cDNA_read2 if paired-end] CellBarcode_read . Requires --out_sam_type BAM Unsorted [and/or SortedByCoordinate]\n- SmartSeq ... Smart-seq: each cell in a separate FASTQ (paired- or single-end), barcodes are corresponding read-groups, no UMI sequences, alignments deduplicated according to alignment start and end (after extending soft-clipped bases)", + "info" : { + "orig_name" : "--soloType" + }, + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_cb_type", + "description" : "cell barcode type\n\nSequence: cell barcode is a sequence (standard option)\nString: cell barcode is an arbitrary string", + "info" : { + "orig_name" : "--soloCBtype" + }, + "example" : [ + "Sequence" + ], + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_cb_whitelist", + "description" : "file(s) with whitelist(s) of cell barcodes. Only --solo_type CB_UMI_Complex allows more than one whitelist file.\n\n- None ... no whitelist: all cell barcodes are allowed", + "info" : { + "orig_name" : "--soloCBwhitelist" + }, + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "integer", + "name" : "--solo_cb_start", + "description" : "cell barcode start base", + "info" : { + "orig_name" : "--soloCBstart" + }, + "example" : [ + 1 + ], + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "integer", + "name" : "--solo_cb_len", + "description" : "cell barcode length", + "info" : { + "orig_name" : "--soloCBlen" + }, + "example" : [ + 16 + ], + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "integer", + "name" : "--solo_umi_start", + "description" : "UMI start base", + "info" : { + "orig_name" : "--soloUMIstart" + }, + "example" : [ + 17 + ], + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "integer", + "name" : "--solo_umi_len", + "description" : "UMI length", + "info" : { + "orig_name" : "--soloUMIlen" + }, + "example" : [ + 10 + ], + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "integer", + "name" : "--solo_barcode_read_length", + "description" : "length of the barcode read\n\n- 1 ... equal to sum of soloCBlen+soloUMIlen\n- 0 ... not defined, do not check", + "info" : { + "orig_name" : "--soloBarcodeReadLength" + }, + "example" : [ + 1 + ], + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "integer", + "name" : "--solo_barcode_mate", + "description" : "identifies which read mate contains the barcode (CB+UMI) sequence\n\n- 0 ... barcode sequence is on separate read, which should always be the last file in the --readFilesIn listed\n- 1 ... barcode sequence is a part of mate 1\n- 2 ... barcode sequence is a part of mate 2", + "info" : { + "orig_name" : "--soloBarcodeMate" + }, + "example" : [ + 0 + ], + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_cb_position", + "description" : "position of Cell Barcode(s) on the barcode read.\n\nPresently only works with --solo_type CB_UMI_Complex, and barcodes are assumed to be on Read2.\nFormat for each barcode: startAnchor_startPosition_endAnchor_endPosition\nstart(end)Anchor defines the Anchor Base for the CB: 0: read start; 1: read end; 2: adapter start; 3: adapter end\nstart(end)Position is the 0-based position with of the CB start(end) with respect to the Anchor Base\nString for different barcodes are separated by space.\nExample: inDrop (Zilionis et al, Nat. Protocols, 2017):\n--solo_cb_position 0_0_2_-1 3_1_3_8", + "info" : { + "orig_name" : "--soloCBposition" + }, + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_umi_position", + "description" : "position of the UMI on the barcode read, same as soloCBposition\n\nExample: inDrop (Zilionis et al, Nat. Protocols, 2017):\n--solo_cb_position 3_9_3_14", + "info" : { + "orig_name" : "--soloUMIposition" + }, + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_adapter_sequence", + "description" : "adapter sequence to anchor barcodes. Only one adapter sequence is allowed.", + "info" : { + "orig_name" : "--soloAdapterSequence" + }, + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "integer", + "name" : "--solo_adapter_mismatches_nmax", + "description" : "maximum number of mismatches allowed in adapter sequence.", + "info" : { + "orig_name" : "--soloAdapterMismatchesNmax" + }, + "example" : [ + 1 + ], + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_cb_match_wl_type", + "description" : "matching the Cell Barcodes to the WhiteList\n\n- Exact ... only exact matches allowed\n- 1MM ... only one match in whitelist with 1 mismatched base allowed. Allowed CBs have to have at least one read with exact match.\n- 1MM_multi ... multiple matches in whitelist with 1 mismatched base allowed, posterior probability calculation is used choose one of the matches.\nAllowed CBs have to have at least one read with exact match. This option matches best with CellRanger 2.2.0\n- 1MM_multi_pseudocounts ... same as 1MM_Multi, but pseudocounts of 1 are added to all whitelist barcodes.\n- 1MM_multi_Nbase_pseudocounts ... same as 1MM_multi_pseudocounts, multimatching to WL is allowed for CBs with N-bases. This option matches best with CellRanger >= 3.0.0\n- EditDist_2 ... allow up to edit distance of 3 fpr each of the barcodes. May include one deletion + one insertion. Only works with --solo_type CB_UMI_Complex. Matches to multiple passlist barcdoes are not allowed. Similar to ParseBio Split-seq pipeline.", + "info" : { + "orig_name" : "--soloCBmatchWLtype" + }, + "example" : [ + "1MM_multi" + ], + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_input_sam_attr_barcode_seq", + "description" : "when inputting reads from a SAM file (--readsFileType SAM SE/PE), these SAM attributes mark the barcode sequence (in proper order).\n\nFor instance, for 10X CellRanger or STARsolo BAMs, use --solo_input_sam_attr_barcode_seq CR UR .\nThis parameter is required when running STARsolo with input from SAM.", + "info" : { + "orig_name" : "--soloInputSAMattrBarcodeSeq" + }, + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_input_sam_attr_barcode_qual", + "description" : "when inputting reads from a SAM file (--readsFileType SAM SE/PE), these SAM attributes mark the barcode qualities (in proper order).\n\nFor instance, for 10X CellRanger or STARsolo BAMs, use --solo_input_sam_attr_barcode_qual CY UY .\nIf this parameter is '-' (default), the quality 'H' will be assigned to all bases.", + "info" : { + "orig_name" : "--soloInputSAMattrBarcodeQual" + }, + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_strand", + "description" : "strandedness of the solo libraries:\n\n- Unstranded ... no strand information\n- Forward ... read strand same as the original RNA molecule\n- Reverse ... read strand opposite to the original RNA molecule", + "info" : { + "orig_name" : "--soloStrand" + }, + "example" : [ + "Forward" + ], + "required" : false, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_features", + "description" : "genomic features for which the UMI counts per Cell Barcode are collected\n\n- Gene ... genes: reads match the gene transcript\n- SJ ... splice junctions: reported in SJ.out.tab\n- GeneFull ... full gene (pre-mRNA): count all reads overlapping genes' exons and introns\n- GeneFull_ExonOverIntron ... full gene (pre-mRNA): count all reads overlapping genes' exons and introns: prioritize 100% overlap with exons\n- GeneFull_Ex50pAS ... full gene (pre-RNA): count all reads overlapping genes' exons and introns: prioritize >50% overlap with exons. Do not count reads with 100% exonic overlap in the antisense direction.", + "info" : { + "orig_name" : "--soloFeatures" + }, + "example" : [ + "Gene" + ], + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_multi_mappers", + "description" : "counting method for reads mapping to multiple genes\n\n- Unique ... count only reads that map to unique genes\n- Uniform ... uniformly distribute multi-genic UMIs to all genes\n- Rescue ... distribute UMIs proportionally to unique+uniform counts (~ first iteration of EM)\n- PropUnique ... distribute UMIs proportionally to unique mappers, if present, and uniformly if not.\n- EM ... multi-gene UMIs are distributed using Expectation Maximization algorithm", + "info" : { + "orig_name" : "--soloMultiMappers" + }, + "example" : [ + "Unique" + ], + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_umi_dedup", + "description" : "type of UMI deduplication (collapsing) algorithm\n\n- 1MM_All ... all UMIs with 1 mismatch distance to each other are collapsed (i.e. counted once).\n- 1MM_Directional_UMItools ... follows the \\"directional\\" method from the UMI-tools by Smith, Heger and Sudbery (Genome Research 2017).\n- 1MM_Directional ... same as 1MM_Directional_UMItools, but with more stringent criteria for duplicate UMIs\n- Exact ... only exactly matching UMIs are collapsed.\n- NoDedup ... no deduplication of UMIs, count all reads.\n- 1MM_CR ... CellRanger2-4 algorithm for 1MM UMI collapsing.", + "info" : { + "orig_name" : "--soloUMIdedup" + }, + "example" : [ + "1MM_All" + ], + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_umi_filtering", + "description" : "type of UMI filtering (for reads uniquely mapping to genes)\n\n- - ... basic filtering: remove UMIs with N and homopolymers (similar to CellRanger 2.2.0).\n- MultiGeneUMI ... basic + remove lower-count UMIs that map to more than one gene.\n- MultiGeneUMI_All ... basic + remove all UMIs that map to more than one gene.\n- MultiGeneUMI_CR ... basic + remove lower-count UMIs that map to more than one gene, matching CellRanger > 3.0.0 .\nOnly works with --solo_umi_dedup 1MM_CR", + "info" : { + "orig_name" : "--soloUMIfiltering" + }, + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_out_file_names", + "description" : "file names for STARsolo output:\n\nfile_name_prefix gene_names barcode_sequences cell_feature_count_matrix", + "info" : { + "orig_name" : "--soloOutFileNames" + }, + "example" : [ + "Solo.out/", + "features.tsv", + "barcodes.tsv", + "matrix.mtx" + ], + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_cell_filter", + "description" : "cell filtering type and parameters\n\n- None ... do not output filtered cells\n- TopCells ... only report top cells by UMI count, followed by the exact number of cells\n- CellRanger2.2 ... simple filtering of CellRanger 2.2.\nCan be followed by numbers: number of expected cells, robust maximum percentile for UMI count, maximum to minimum ratio for UMI count\nThe harcoded values are from CellRanger: nExpectedCells=3000; maxPercentile=0.99; maxMinRatio=10\n- EmptyDrops_CR ... EmptyDrops filtering in CellRanger flavor. Please cite the original EmptyDrops paper: A.T.L Lun et al, Genome Biology, 20, 63 (2019): https://genomebiology.biomedcentral.com/articles/10.1186/s13059-019-1662-y\nCan be followed by 10 numeric parameters: nExpectedCells maxPercentile maxMinRatio indMin indMax umiMin umiMinFracMedian candMaxN FDR simN\nThe harcoded values are from CellRanger: 3000 0.99 10 45000 90000 500 0.01 20000 0.01 10000", + "info" : { + "orig_name" : "--soloCellFilter" + }, + "example" : [ + "CellRanger2.2", + "3000", + "0.99", + "10" + ], + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_out_format_features_gene_field3", + "description" : "field 3 in the Gene features.tsv file. If \\"-\\", then no 3rd field is output.", + "info" : { + "orig_name" : "--soloOutFormatFeaturesGeneField3" + }, + "example" : [ + "Gene Expression" + ], + "required" : false, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "string", + "name" : "--solo_cell_read_stats", + "description" : "Output reads statistics for each CB\n\n- Standard ... standard output", + "info" : { + "orig_name" : "--soloCellReadStats" + }, "required" : false, "direction" : "input", "multiple" : false, @@ -4848,6 +5760,20 @@ meta = [ "direction" : "output", "multiple" : false, "multiple_sep" : ";" + }, + { + "type" : "file", + "name" : "--reads_aligned_to_transcriptome", + "description" : "The output file containing the alignments to transcriptome in BAM formats. This file is generated when --quantMode is set to TranscriptomeSAM.", + "example" : [ + "transcriptome_aligned.bam" + ], + "must_exist" : true, + "create_parent" : true, + "required" : false, + "direction" : "output", + "multiple" : false, + "multiple_sep" : ";" } ] } @@ -4968,7 +5894,7 @@ meta = [ "id" : "docker", "image" : "python:3.12-slim", "target_registry" : "images.viash-hub.com", - "target_tag" : "v0.1.0", + "target_tag" : "main", "namespace_separator" : "/", "setup" : [ { @@ -4990,6 +5916,14 @@ meta = [ "PACKAGES gcc g++ make wget zlib1g-dev unzip xxd" ] }, + { + "type" : "python", + "user" : false, + "packages" : [ + "pyyaml" + ], + "upgrade" : true + }, { "type" : "docker", "run" : [ @@ -5008,22 +5942,23 @@ meta = [ "runner" : "nextflow", "engine" : "docker|native", "output" : "target/nextflow/star/star_align_reads", - "viash_version" : "0.9.0-RC6", - "git_commit" : "b84b29747d0635f2ac83ea63b496be9a9edb6724", - "git_remote" : "https://github.com/viash-hub/biobox" + "viash_version" : "0.9.0", + "git_commit" : "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b", + "git_remote" : "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox", + "git_tag" : "v0.2.0-27-g952ff08" }, "package_config" : { "name" : "biobox", - "version" : "v0.1.0", + "version" : "main", "description" : "A collection of bioinformatics tools for working with sequence data.\n", - "viash_version" : "0.9.0-RC6", + "viash_version" : "0.9.0", "source" : "src", "target" : "target", "config_mods" : [ ".requirements.commands := ['ps']\n", ".engines += { type: \\"native\\" }", ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'", - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" + ".engines[.type == 'docker'].target_tag := 'main'" ], "keywords" : [ "bioinformatics", @@ -5053,166 +5988,192 @@ import tempfile import subprocess import shutil from pathlib import Path +import yaml ## VIASH START # The following code has been auto-generated by Viash. par = { - 'runRNGseed': $( if [ ! -z ${VIASH_PAR_RUNRNGSEED+x} ]; then echo "int(r'${VIASH_PAR_RUNRNGSEED//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'genomeDir': $( if [ ! -z ${VIASH_PAR_GENOMEDIR+x} ]; then echo "r'${VIASH_PAR_GENOMEDIR//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'genomeLoad': $( if [ ! -z ${VIASH_PAR_GENOMELOAD+x} ]; then echo "r'${VIASH_PAR_GENOMELOAD//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'genomeFastaFiles': $( if [ ! -z ${VIASH_PAR_GENOMEFASTAFILES+x} ]; then echo "r'${VIASH_PAR_GENOMEFASTAFILES//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'genomeFileSizes': $( if [ ! -z ${VIASH_PAR_GENOMEFILESIZES+x} ]; then echo "list(map(int, r'${VIASH_PAR_GENOMEFILESIZES//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'genomeTransformOutput': $( if [ ! -z ${VIASH_PAR_GENOMETRANSFORMOUTPUT+x} ]; then echo "r'${VIASH_PAR_GENOMETRANSFORMOUTPUT//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'genomeChrSetMitochondrial': $( if [ ! -z ${VIASH_PAR_GENOMECHRSETMITOCHONDRIAL+x} ]; then echo "r'${VIASH_PAR_GENOMECHRSETMITOCHONDRIAL//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'sjdbFileChrStartEnd': $( if [ ! -z ${VIASH_PAR_SJDBFILECHRSTARTEND+x} ]; then echo "r'${VIASH_PAR_SJDBFILECHRSTARTEND//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'sjdbGTFfile': $( if [ ! -z ${VIASH_PAR_SJDBGTFFILE+x} ]; then echo "r'${VIASH_PAR_SJDBGTFFILE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'sjdbGTFchrPrefix': $( if [ ! -z ${VIASH_PAR_SJDBGTFCHRPREFIX+x} ]; then echo "r'${VIASH_PAR_SJDBGTFCHRPREFIX//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'sjdbGTFfeatureExon': $( if [ ! -z ${VIASH_PAR_SJDBGTFFEATUREEXON+x} ]; then echo "r'${VIASH_PAR_SJDBGTFFEATUREEXON//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'sjdbGTFtagExonParentTranscript': $( if [ ! -z ${VIASH_PAR_SJDBGTFTAGEXONPARENTTRANSCRIPT+x} ]; then echo "r'${VIASH_PAR_SJDBGTFTAGEXONPARENTTRANSCRIPT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'sjdbGTFtagExonParentGene': $( if [ ! -z ${VIASH_PAR_SJDBGTFTAGEXONPARENTGENE+x} ]; then echo "r'${VIASH_PAR_SJDBGTFTAGEXONPARENTGENE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'sjdbGTFtagExonParentGeneName': $( if [ ! -z ${VIASH_PAR_SJDBGTFTAGEXONPARENTGENENAME+x} ]; then echo "r'${VIASH_PAR_SJDBGTFTAGEXONPARENTGENENAME//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'sjdbGTFtagExonParentGeneType': $( if [ ! -z ${VIASH_PAR_SJDBGTFTAGEXONPARENTGENETYPE+x} ]; then echo "r'${VIASH_PAR_SJDBGTFTAGEXONPARENTGENETYPE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'sjdbOverhang': $( if [ ! -z ${VIASH_PAR_SJDBOVERHANG+x} ]; then echo "int(r'${VIASH_PAR_SJDBOVERHANG//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'sjdbScore': $( if [ ! -z ${VIASH_PAR_SJDBSCORE+x} ]; then echo "int(r'${VIASH_PAR_SJDBSCORE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'sjdbInsertSave': $( if [ ! -z ${VIASH_PAR_SJDBINSERTSAVE+x} ]; then echo "r'${VIASH_PAR_SJDBINSERTSAVE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'varVCFfile': $( if [ ! -z ${VIASH_PAR_VARVCFFILE+x} ]; then echo "r'${VIASH_PAR_VARVCFFILE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'readFilesType': $( if [ ! -z ${VIASH_PAR_READFILESTYPE+x} ]; then echo "r'${VIASH_PAR_READFILESTYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'readFilesSAMattrKeep': $( if [ ! -z ${VIASH_PAR_READFILESSAMATTRKEEP+x} ]; then echo "r'${VIASH_PAR_READFILESSAMATTRKEEP//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'readFilesManifest': $( if [ ! -z ${VIASH_PAR_READFILESMANIFEST+x} ]; then echo "r'${VIASH_PAR_READFILESMANIFEST//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'readFilesPrefix': $( if [ ! -z ${VIASH_PAR_READFILESPREFIX+x} ]; then echo "r'${VIASH_PAR_READFILESPREFIX//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'readFilesCommand': $( if [ ! -z ${VIASH_PAR_READFILESCOMMAND+x} ]; then echo "r'${VIASH_PAR_READFILESCOMMAND//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'readMapNumber': $( if [ ! -z ${VIASH_PAR_READMAPNUMBER+x} ]; then echo "int(r'${VIASH_PAR_READMAPNUMBER//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'readMatesLengthsIn': $( if [ ! -z ${VIASH_PAR_READMATESLENGTHSIN+x} ]; then echo "r'${VIASH_PAR_READMATESLENGTHSIN//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'readNameSeparator': $( if [ ! -z ${VIASH_PAR_READNAMESEPARATOR+x} ]; then echo "r'${VIASH_PAR_READNAMESEPARATOR//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'readQualityScoreBase': $( if [ ! -z ${VIASH_PAR_READQUALITYSCOREBASE+x} ]; then echo "int(r'${VIASH_PAR_READQUALITYSCOREBASE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'clipAdapterType': $( if [ ! -z ${VIASH_PAR_CLIPADAPTERTYPE+x} ]; then echo "r'${VIASH_PAR_CLIPADAPTERTYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'clip3pNbases': $( if [ ! -z ${VIASH_PAR_CLIP3PNBASES+x} ]; then echo "list(map(int, r'${VIASH_PAR_CLIP3PNBASES//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'clip3pAdapterSeq': $( if [ ! -z ${VIASH_PAR_CLIP3PADAPTERSEQ+x} ]; then echo "r'${VIASH_PAR_CLIP3PADAPTERSEQ//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'clip3pAdapterMMp': $( if [ ! -z ${VIASH_PAR_CLIP3PADAPTERMMP+x} ]; then echo "list(map(float, r'${VIASH_PAR_CLIP3PADAPTERMMP//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'clip3pAfterAdapterNbases': $( if [ ! -z ${VIASH_PAR_CLIP3PAFTERADAPTERNBASES+x} ]; then echo "list(map(int, r'${VIASH_PAR_CLIP3PAFTERADAPTERNBASES//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'clip5pNbases': $( if [ ! -z ${VIASH_PAR_CLIP5PNBASES+x} ]; then echo "list(map(int, r'${VIASH_PAR_CLIP5PNBASES//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'limitGenomeGenerateRAM': $( if [ ! -z ${VIASH_PAR_LIMITGENOMEGENERATERAM+x} ]; then echo "int(r'${VIASH_PAR_LIMITGENOMEGENERATERAM//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'limitIObufferSize': $( if [ ! -z ${VIASH_PAR_LIMITIOBUFFERSIZE+x} ]; then echo "list(map(int, r'${VIASH_PAR_LIMITIOBUFFERSIZE//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'limitOutSAMoneReadBytes': $( if [ ! -z ${VIASH_PAR_LIMITOUTSAMONEREADBYTES+x} ]; then echo "int(r'${VIASH_PAR_LIMITOUTSAMONEREADBYTES//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'limitOutSJoneRead': $( if [ ! -z ${VIASH_PAR_LIMITOUTSJONEREAD+x} ]; then echo "int(r'${VIASH_PAR_LIMITOUTSJONEREAD//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'limitOutSJcollapsed': $( if [ ! -z ${VIASH_PAR_LIMITOUTSJCOLLAPSED+x} ]; then echo "int(r'${VIASH_PAR_LIMITOUTSJCOLLAPSED//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'limitBAMsortRAM': $( if [ ! -z ${VIASH_PAR_LIMITBAMSORTRAM+x} ]; then echo "int(r'${VIASH_PAR_LIMITBAMSORTRAM//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'limitSjdbInsertNsj': $( if [ ! -z ${VIASH_PAR_LIMITSJDBINSERTNSJ+x} ]; then echo "int(r'${VIASH_PAR_LIMITSJDBINSERTNSJ//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'limitNreadsSoft': $( if [ ! -z ${VIASH_PAR_LIMITNREADSSOFT+x} ]; then echo "int(r'${VIASH_PAR_LIMITNREADSSOFT//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outTmpKeep': $( if [ ! -z ${VIASH_PAR_OUTTMPKEEP+x} ]; then echo "r'${VIASH_PAR_OUTTMPKEEP//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outStd': $( if [ ! -z ${VIASH_PAR_OUTSTD+x} ]; then echo "r'${VIASH_PAR_OUTSTD//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outReadsUnmapped': $( if [ ! -z ${VIASH_PAR_OUTREADSUNMAPPED+x} ]; then echo "r'${VIASH_PAR_OUTREADSUNMAPPED//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outQSconversionAdd': $( if [ ! -z ${VIASH_PAR_OUTQSCONVERSIONADD+x} ]; then echo "int(r'${VIASH_PAR_OUTQSCONVERSIONADD//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outMultimapperOrder': $( if [ ! -z ${VIASH_PAR_OUTMULTIMAPPERORDER+x} ]; then echo "r'${VIASH_PAR_OUTMULTIMAPPERORDER//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outSAMtype': $( if [ ! -z ${VIASH_PAR_OUTSAMTYPE+x} ]; then echo "r'${VIASH_PAR_OUTSAMTYPE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'outSAMmode': $( if [ ! -z ${VIASH_PAR_OUTSAMMODE+x} ]; then echo "r'${VIASH_PAR_OUTSAMMODE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outSAMstrandField': $( if [ ! -z ${VIASH_PAR_OUTSAMSTRANDFIELD+x} ]; then echo "r'${VIASH_PAR_OUTSAMSTRANDFIELD//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outSAMattributes': $( if [ ! -z ${VIASH_PAR_OUTSAMATTRIBUTES+x} ]; then echo "r'${VIASH_PAR_OUTSAMATTRIBUTES//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'outSAMattrIHstart': $( if [ ! -z ${VIASH_PAR_OUTSAMATTRIHSTART+x} ]; then echo "int(r'${VIASH_PAR_OUTSAMATTRIHSTART//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outSAMunmapped': $( if [ ! -z ${VIASH_PAR_OUTSAMUNMAPPED+x} ]; then echo "r'${VIASH_PAR_OUTSAMUNMAPPED//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'outSAMorder': $( if [ ! -z ${VIASH_PAR_OUTSAMORDER+x} ]; then echo "r'${VIASH_PAR_OUTSAMORDER//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outSAMprimaryFlag': $( if [ ! -z ${VIASH_PAR_OUTSAMPRIMARYFLAG+x} ]; then echo "r'${VIASH_PAR_OUTSAMPRIMARYFLAG//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outSAMreadID': $( if [ ! -z ${VIASH_PAR_OUTSAMREADID+x} ]; then echo "r'${VIASH_PAR_OUTSAMREADID//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outSAMmapqUnique': $( if [ ! -z ${VIASH_PAR_OUTSAMMAPQUNIQUE+x} ]; then echo "int(r'${VIASH_PAR_OUTSAMMAPQUNIQUE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outSAMflagOR': $( if [ ! -z ${VIASH_PAR_OUTSAMFLAGOR+x} ]; then echo "int(r'${VIASH_PAR_OUTSAMFLAGOR//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outSAMflagAND': $( if [ ! -z ${VIASH_PAR_OUTSAMFLAGAND+x} ]; then echo "int(r'${VIASH_PAR_OUTSAMFLAGAND//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outSAMattrRGline': $( if [ ! -z ${VIASH_PAR_OUTSAMATTRRGLINE+x} ]; then echo "r'${VIASH_PAR_OUTSAMATTRRGLINE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'outSAMheaderHD': $( if [ ! -z ${VIASH_PAR_OUTSAMHEADERHD+x} ]; then echo "r'${VIASH_PAR_OUTSAMHEADERHD//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'outSAMheaderPG': $( if [ ! -z ${VIASH_PAR_OUTSAMHEADERPG+x} ]; then echo "r'${VIASH_PAR_OUTSAMHEADERPG//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'outSAMheaderCommentFile': $( if [ ! -z ${VIASH_PAR_OUTSAMHEADERCOMMENTFILE+x} ]; then echo "r'${VIASH_PAR_OUTSAMHEADERCOMMENTFILE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outSAMfilter': $( if [ ! -z ${VIASH_PAR_OUTSAMFILTER+x} ]; then echo "r'${VIASH_PAR_OUTSAMFILTER//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'outSAMmultNmax': $( if [ ! -z ${VIASH_PAR_OUTSAMMULTNMAX+x} ]; then echo "int(r'${VIASH_PAR_OUTSAMMULTNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outSAMtlen': $( if [ ! -z ${VIASH_PAR_OUTSAMTLEN+x} ]; then echo "int(r'${VIASH_PAR_OUTSAMTLEN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outBAMcompression': $( if [ ! -z ${VIASH_PAR_OUTBAMCOMPRESSION+x} ]; then echo "int(r'${VIASH_PAR_OUTBAMCOMPRESSION//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outBAMsortingThreadN': $( if [ ! -z ${VIASH_PAR_OUTBAMSORTINGTHREADN+x} ]; then echo "int(r'${VIASH_PAR_OUTBAMSORTINGTHREADN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outBAMsortingBinsN': $( if [ ! -z ${VIASH_PAR_OUTBAMSORTINGBINSN+x} ]; then echo "int(r'${VIASH_PAR_OUTBAMSORTINGBINSN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'bamRemoveDuplicatesType': $( if [ ! -z ${VIASH_PAR_BAMREMOVEDUPLICATESTYPE+x} ]; then echo "r'${VIASH_PAR_BAMREMOVEDUPLICATESTYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'bamRemoveDuplicatesMate2basesN': $( if [ ! -z ${VIASH_PAR_BAMREMOVEDUPLICATESMATE2BASESN+x} ]; then echo "int(r'${VIASH_PAR_BAMREMOVEDUPLICATESMATE2BASESN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outWigType': $( if [ ! -z ${VIASH_PAR_OUTWIGTYPE+x} ]; then echo "r'${VIASH_PAR_OUTWIGTYPE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'outWigStrand': $( if [ ! -z ${VIASH_PAR_OUTWIGSTRAND+x} ]; then echo "r'${VIASH_PAR_OUTWIGSTRAND//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outWigReferencesPrefix': $( if [ ! -z ${VIASH_PAR_OUTWIGREFERENCESPREFIX+x} ]; then echo "r'${VIASH_PAR_OUTWIGREFERENCESPREFIX//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outWigNorm': $( if [ ! -z ${VIASH_PAR_OUTWIGNORM+x} ]; then echo "r'${VIASH_PAR_OUTWIGNORM//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outFilterType': $( if [ ! -z ${VIASH_PAR_OUTFILTERTYPE+x} ]; then echo "r'${VIASH_PAR_OUTFILTERTYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outFilterMultimapScoreRange': $( if [ ! -z ${VIASH_PAR_OUTFILTERMULTIMAPSCORERANGE+x} ]; then echo "int(r'${VIASH_PAR_OUTFILTERMULTIMAPSCORERANGE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outFilterMultimapNmax': $( if [ ! -z ${VIASH_PAR_OUTFILTERMULTIMAPNMAX+x} ]; then echo "int(r'${VIASH_PAR_OUTFILTERMULTIMAPNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outFilterMismatchNmax': $( if [ ! -z ${VIASH_PAR_OUTFILTERMISMATCHNMAX+x} ]; then echo "int(r'${VIASH_PAR_OUTFILTERMISMATCHNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outFilterMismatchNoverLmax': $( if [ ! -z ${VIASH_PAR_OUTFILTERMISMATCHNOVERLMAX+x} ]; then echo "float(r'${VIASH_PAR_OUTFILTERMISMATCHNOVERLMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outFilterMismatchNoverReadLmax': $( if [ ! -z ${VIASH_PAR_OUTFILTERMISMATCHNOVERREADLMAX+x} ]; then echo "float(r'${VIASH_PAR_OUTFILTERMISMATCHNOVERREADLMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outFilterScoreMin': $( if [ ! -z ${VIASH_PAR_OUTFILTERSCOREMIN+x} ]; then echo "int(r'${VIASH_PAR_OUTFILTERSCOREMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outFilterScoreMinOverLread': $( if [ ! -z ${VIASH_PAR_OUTFILTERSCOREMINOVERLREAD+x} ]; then echo "float(r'${VIASH_PAR_OUTFILTERSCOREMINOVERLREAD//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outFilterMatchNmin': $( if [ ! -z ${VIASH_PAR_OUTFILTERMATCHNMIN+x} ]; then echo "int(r'${VIASH_PAR_OUTFILTERMATCHNMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outFilterMatchNminOverLread': $( if [ ! -z ${VIASH_PAR_OUTFILTERMATCHNMINOVERLREAD+x} ]; then echo "float(r'${VIASH_PAR_OUTFILTERMATCHNMINOVERLREAD//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'outFilterIntronMotifs': $( if [ ! -z ${VIASH_PAR_OUTFILTERINTRONMOTIFS+x} ]; then echo "r'${VIASH_PAR_OUTFILTERINTRONMOTIFS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outFilterIntronStrands': $( if [ ! -z ${VIASH_PAR_OUTFILTERINTRONSTRANDS+x} ]; then echo "r'${VIASH_PAR_OUTFILTERINTRONSTRANDS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outSJtype': $( if [ ! -z ${VIASH_PAR_OUTSJTYPE+x} ]; then echo "r'${VIASH_PAR_OUTSJTYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outSJfilterReads': $( if [ ! -z ${VIASH_PAR_OUTSJFILTERREADS+x} ]; then echo "r'${VIASH_PAR_OUTSJFILTERREADS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'outSJfilterOverhangMin': $( if [ ! -z ${VIASH_PAR_OUTSJFILTEROVERHANGMIN+x} ]; then echo "list(map(int, r'${VIASH_PAR_OUTSJFILTEROVERHANGMIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'outSJfilterCountUniqueMin': $( if [ ! -z ${VIASH_PAR_OUTSJFILTERCOUNTUNIQUEMIN+x} ]; then echo "list(map(int, r'${VIASH_PAR_OUTSJFILTERCOUNTUNIQUEMIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'outSJfilterCountTotalMin': $( if [ ! -z ${VIASH_PAR_OUTSJFILTERCOUNTTOTALMIN+x} ]; then echo "list(map(int, r'${VIASH_PAR_OUTSJFILTERCOUNTTOTALMIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'outSJfilterDistToOtherSJmin': $( if [ ! -z ${VIASH_PAR_OUTSJFILTERDISTTOOTHERSJMIN+x} ]; then echo "list(map(int, r'${VIASH_PAR_OUTSJFILTERDISTTOOTHERSJMIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'outSJfilterIntronMaxVsReadN': $( if [ ! -z ${VIASH_PAR_OUTSJFILTERINTRONMAXVSREADN+x} ]; then echo "list(map(int, r'${VIASH_PAR_OUTSJFILTERINTRONMAXVSREADN//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'scoreGap': $( if [ ! -z ${VIASH_PAR_SCOREGAP+x} ]; then echo "int(r'${VIASH_PAR_SCOREGAP//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'scoreGapNoncan': $( if [ ! -z ${VIASH_PAR_SCOREGAPNONCAN+x} ]; then echo "int(r'${VIASH_PAR_SCOREGAPNONCAN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'scoreGapGCAG': $( if [ ! -z ${VIASH_PAR_SCOREGAPGCAG+x} ]; then echo "int(r'${VIASH_PAR_SCOREGAPGCAG//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'scoreGapATAC': $( if [ ! -z ${VIASH_PAR_SCOREGAPATAC+x} ]; then echo "int(r'${VIASH_PAR_SCOREGAPATAC//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'scoreGenomicLengthLog2scale': $( if [ ! -z ${VIASH_PAR_SCOREGENOMICLENGTHLOG2SCALE+x} ]; then echo "int(r'${VIASH_PAR_SCOREGENOMICLENGTHLOG2SCALE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'scoreDelOpen': $( if [ ! -z ${VIASH_PAR_SCOREDELOPEN+x} ]; then echo "int(r'${VIASH_PAR_SCOREDELOPEN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'scoreDelBase': $( if [ ! -z ${VIASH_PAR_SCOREDELBASE+x} ]; then echo "int(r'${VIASH_PAR_SCOREDELBASE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'scoreInsOpen': $( if [ ! -z ${VIASH_PAR_SCOREINSOPEN+x} ]; then echo "int(r'${VIASH_PAR_SCOREINSOPEN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'scoreInsBase': $( if [ ! -z ${VIASH_PAR_SCOREINSBASE+x} ]; then echo "int(r'${VIASH_PAR_SCOREINSBASE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'scoreStitchSJshift': $( if [ ! -z ${VIASH_PAR_SCORESTITCHSJSHIFT+x} ]; then echo "int(r'${VIASH_PAR_SCORESTITCHSJSHIFT//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'seedSearchStartLmax': $( if [ ! -z ${VIASH_PAR_SEEDSEARCHSTARTLMAX+x} ]; then echo "int(r'${VIASH_PAR_SEEDSEARCHSTARTLMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'seedSearchStartLmaxOverLread': $( if [ ! -z ${VIASH_PAR_SEEDSEARCHSTARTLMAXOVERLREAD+x} ]; then echo "float(r'${VIASH_PAR_SEEDSEARCHSTARTLMAXOVERLREAD//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'seedSearchLmax': $( if [ ! -z ${VIASH_PAR_SEEDSEARCHLMAX+x} ]; then echo "int(r'${VIASH_PAR_SEEDSEARCHLMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'seedMultimapNmax': $( if [ ! -z ${VIASH_PAR_SEEDMULTIMAPNMAX+x} ]; then echo "int(r'${VIASH_PAR_SEEDMULTIMAPNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'seedPerReadNmax': $( if [ ! -z ${VIASH_PAR_SEEDPERREADNMAX+x} ]; then echo "int(r'${VIASH_PAR_SEEDPERREADNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'seedPerWindowNmax': $( if [ ! -z ${VIASH_PAR_SEEDPERWINDOWNMAX+x} ]; then echo "int(r'${VIASH_PAR_SEEDPERWINDOWNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'seedNoneLociPerWindow': $( if [ ! -z ${VIASH_PAR_SEEDNONELOCIPERWINDOW+x} ]; then echo "int(r'${VIASH_PAR_SEEDNONELOCIPERWINDOW//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'seedSplitMin': $( if [ ! -z ${VIASH_PAR_SEEDSPLITMIN+x} ]; then echo "int(r'${VIASH_PAR_SEEDSPLITMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'seedMapMin': $( if [ ! -z ${VIASH_PAR_SEEDMAPMIN+x} ]; then echo "int(r'${VIASH_PAR_SEEDMAPMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'alignIntronMin': $( if [ ! -z ${VIASH_PAR_ALIGNINTRONMIN+x} ]; then echo "int(r'${VIASH_PAR_ALIGNINTRONMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'alignIntronMax': $( if [ ! -z ${VIASH_PAR_ALIGNINTRONMAX+x} ]; then echo "int(r'${VIASH_PAR_ALIGNINTRONMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'alignMatesGapMax': $( if [ ! -z ${VIASH_PAR_ALIGNMATESGAPMAX+x} ]; then echo "int(r'${VIASH_PAR_ALIGNMATESGAPMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'alignSJoverhangMin': $( if [ ! -z ${VIASH_PAR_ALIGNSJOVERHANGMIN+x} ]; then echo "int(r'${VIASH_PAR_ALIGNSJOVERHANGMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'alignSJstitchMismatchNmax': $( if [ ! -z ${VIASH_PAR_ALIGNSJSTITCHMISMATCHNMAX+x} ]; then echo "list(map(int, r'${VIASH_PAR_ALIGNSJSTITCHMISMATCHNMAX//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), - 'alignSJDBoverhangMin': $( if [ ! -z ${VIASH_PAR_ALIGNSJDBOVERHANGMIN+x} ]; then echo "int(r'${VIASH_PAR_ALIGNSJDBOVERHANGMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'alignSplicedMateMapLmin': $( if [ ! -z ${VIASH_PAR_ALIGNSPLICEDMATEMAPLMIN+x} ]; then echo "int(r'${VIASH_PAR_ALIGNSPLICEDMATEMAPLMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'alignSplicedMateMapLminOverLmate': $( if [ ! -z ${VIASH_PAR_ALIGNSPLICEDMATEMAPLMINOVERLMATE+x} ]; then echo "float(r'${VIASH_PAR_ALIGNSPLICEDMATEMAPLMINOVERLMATE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'alignWindowsPerReadNmax': $( if [ ! -z ${VIASH_PAR_ALIGNWINDOWSPERREADNMAX+x} ]; then echo "int(r'${VIASH_PAR_ALIGNWINDOWSPERREADNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'alignTranscriptsPerWindowNmax': $( if [ ! -z ${VIASH_PAR_ALIGNTRANSCRIPTSPERWINDOWNMAX+x} ]; then echo "int(r'${VIASH_PAR_ALIGNTRANSCRIPTSPERWINDOWNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'alignTranscriptsPerReadNmax': $( if [ ! -z ${VIASH_PAR_ALIGNTRANSCRIPTSPERREADNMAX+x} ]; then echo "int(r'${VIASH_PAR_ALIGNTRANSCRIPTSPERREADNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'alignEndsType': $( if [ ! -z ${VIASH_PAR_ALIGNENDSTYPE+x} ]; then echo "r'${VIASH_PAR_ALIGNENDSTYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'alignEndsProtrude': $( if [ ! -z ${VIASH_PAR_ALIGNENDSPROTRUDE+x} ]; then echo "r'${VIASH_PAR_ALIGNENDSPROTRUDE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'alignSoftClipAtReferenceEnds': $( if [ ! -z ${VIASH_PAR_ALIGNSOFTCLIPATREFERENCEENDS+x} ]; then echo "r'${VIASH_PAR_ALIGNSOFTCLIPATREFERENCEENDS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'alignInsertionFlush': $( if [ ! -z ${VIASH_PAR_ALIGNINSERTIONFLUSH+x} ]; then echo "r'${VIASH_PAR_ALIGNINSERTIONFLUSH//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'peOverlapNbasesMin': $( if [ ! -z ${VIASH_PAR_PEOVERLAPNBASESMIN+x} ]; then echo "int(r'${VIASH_PAR_PEOVERLAPNBASESMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'peOverlapMMp': $( if [ ! -z ${VIASH_PAR_PEOVERLAPMMP+x} ]; then echo "float(r'${VIASH_PAR_PEOVERLAPMMP//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'winAnchorMultimapNmax': $( if [ ! -z ${VIASH_PAR_WINANCHORMULTIMAPNMAX+x} ]; then echo "int(r'${VIASH_PAR_WINANCHORMULTIMAPNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'winBinNbits': $( if [ ! -z ${VIASH_PAR_WINBINNBITS+x} ]; then echo "int(r'${VIASH_PAR_WINBINNBITS//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'winAnchorDistNbins': $( if [ ! -z ${VIASH_PAR_WINANCHORDISTNBINS+x} ]; then echo "int(r'${VIASH_PAR_WINANCHORDISTNBINS//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'winFlankNbins': $( if [ ! -z ${VIASH_PAR_WINFLANKNBINS+x} ]; then echo "int(r'${VIASH_PAR_WINFLANKNBINS//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'winReadCoverageRelativeMin': $( if [ ! -z ${VIASH_PAR_WINREADCOVERAGERELATIVEMIN+x} ]; then echo "float(r'${VIASH_PAR_WINREADCOVERAGERELATIVEMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'winReadCoverageBasesMin': $( if [ ! -z ${VIASH_PAR_WINREADCOVERAGEBASESMIN+x} ]; then echo "int(r'${VIASH_PAR_WINREADCOVERAGEBASESMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimOutType': $( if [ ! -z ${VIASH_PAR_CHIMOUTTYPE+x} ]; then echo "r'${VIASH_PAR_CHIMOUTTYPE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'chimSegmentMin': $( if [ ! -z ${VIASH_PAR_CHIMSEGMENTMIN+x} ]; then echo "int(r'${VIASH_PAR_CHIMSEGMENTMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimScoreMin': $( if [ ! -z ${VIASH_PAR_CHIMSCOREMIN+x} ]; then echo "int(r'${VIASH_PAR_CHIMSCOREMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimScoreDropMax': $( if [ ! -z ${VIASH_PAR_CHIMSCOREDROPMAX+x} ]; then echo "int(r'${VIASH_PAR_CHIMSCOREDROPMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimScoreSeparation': $( if [ ! -z ${VIASH_PAR_CHIMSCORESEPARATION+x} ]; then echo "int(r'${VIASH_PAR_CHIMSCORESEPARATION//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimScoreJunctionNonGTAG': $( if [ ! -z ${VIASH_PAR_CHIMSCOREJUNCTIONNONGTAG+x} ]; then echo "int(r'${VIASH_PAR_CHIMSCOREJUNCTIONNONGTAG//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimJunctionOverhangMin': $( if [ ! -z ${VIASH_PAR_CHIMJUNCTIONOVERHANGMIN+x} ]; then echo "int(r'${VIASH_PAR_CHIMJUNCTIONOVERHANGMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimSegmentReadGapMax': $( if [ ! -z ${VIASH_PAR_CHIMSEGMENTREADGAPMAX+x} ]; then echo "int(r'${VIASH_PAR_CHIMSEGMENTREADGAPMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimFilter': $( if [ ! -z ${VIASH_PAR_CHIMFILTER+x} ]; then echo "r'${VIASH_PAR_CHIMFILTER//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'chimMainSegmentMultNmax': $( if [ ! -z ${VIASH_PAR_CHIMMAINSEGMENTMULTNMAX+x} ]; then echo "int(r'${VIASH_PAR_CHIMMAINSEGMENTMULTNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimMultimapNmax': $( if [ ! -z ${VIASH_PAR_CHIMMULTIMAPNMAX+x} ]; then echo "int(r'${VIASH_PAR_CHIMMULTIMAPNMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimMultimapScoreRange': $( if [ ! -z ${VIASH_PAR_CHIMMULTIMAPSCORERANGE+x} ]; then echo "int(r'${VIASH_PAR_CHIMMULTIMAPSCORERANGE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimNonchimScoreDropMin': $( if [ ! -z ${VIASH_PAR_CHIMNONCHIMSCOREDROPMIN+x} ]; then echo "int(r'${VIASH_PAR_CHIMNONCHIMSCOREDROPMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'chimOutJunctionFormat': $( if [ ! -z ${VIASH_PAR_CHIMOUTJUNCTIONFORMAT+x} ]; then echo "int(r'${VIASH_PAR_CHIMOUTJUNCTIONFORMAT//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'quantMode': $( if [ ! -z ${VIASH_PAR_QUANTMODE+x} ]; then echo "r'${VIASH_PAR_QUANTMODE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), - 'quantTranscriptomeBAMcompression': $( if [ ! -z ${VIASH_PAR_QUANTTRANSCRIPTOMEBAMCOMPRESSION+x} ]; then echo "int(r'${VIASH_PAR_QUANTTRANSCRIPTOMEBAMCOMPRESSION//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'quantTranscriptomeSAMoutput': $( if [ ! -z ${VIASH_PAR_QUANTTRANSCRIPTOMESAMOUTPUT+x} ]; then echo "r'${VIASH_PAR_QUANTTRANSCRIPTOMESAMOUTPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'twopassMode': $( if [ ! -z ${VIASH_PAR_TWOPASSMODE+x} ]; then echo "r'${VIASH_PAR_TWOPASSMODE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'twopass1readsN': $( if [ ! -z ${VIASH_PAR_TWOPASS1READSN+x} ]; then echo "int(r'${VIASH_PAR_TWOPASS1READSN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), - 'waspOutputMode': $( if [ ! -z ${VIASH_PAR_WASPOUTPUTMODE+x} ]; then echo "r'${VIASH_PAR_WASPOUTPUTMODE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'run_rng_seed': $( if [ ! -z ${VIASH_PAR_RUN_RNG_SEED+x} ]; then echo "int(r'${VIASH_PAR_RUN_RNG_SEED//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'genome_dir': $( if [ ! -z ${VIASH_PAR_GENOME_DIR+x} ]; then echo "r'${VIASH_PAR_GENOME_DIR//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'genome_load': $( if [ ! -z ${VIASH_PAR_GENOME_LOAD+x} ]; then echo "r'${VIASH_PAR_GENOME_LOAD//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'genome_fasta_files': $( if [ ! -z ${VIASH_PAR_GENOME_FASTA_FILES+x} ]; then echo "r'${VIASH_PAR_GENOME_FASTA_FILES//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'genome_file_sizes': $( if [ ! -z ${VIASH_PAR_GENOME_FILE_SIZES+x} ]; then echo "list(map(int, r'${VIASH_PAR_GENOME_FILE_SIZES//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'genome_transform_output': $( if [ ! -z ${VIASH_PAR_GENOME_TRANSFORM_OUTPUT+x} ]; then echo "r'${VIASH_PAR_GENOME_TRANSFORM_OUTPUT//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'genome_chr_set_mitochondrial': $( if [ ! -z ${VIASH_PAR_GENOME_CHR_SET_MITOCHONDRIAL+x} ]; then echo "r'${VIASH_PAR_GENOME_CHR_SET_MITOCHONDRIAL//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'sjdb_file_chr_start_end': $( if [ ! -z ${VIASH_PAR_SJDB_FILE_CHR_START_END+x} ]; then echo "r'${VIASH_PAR_SJDB_FILE_CHR_START_END//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'sjdb_gtf_file': $( if [ ! -z ${VIASH_PAR_SJDB_GTF_FILE+x} ]; then echo "r'${VIASH_PAR_SJDB_GTF_FILE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'sjdb_gtf_chr_prefix': $( if [ ! -z ${VIASH_PAR_SJDB_GTF_CHR_PREFIX+x} ]; then echo "r'${VIASH_PAR_SJDB_GTF_CHR_PREFIX//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'sjdb_gtf_feature_exon': $( if [ ! -z ${VIASH_PAR_SJDB_GTF_FEATURE_EXON+x} ]; then echo "r'${VIASH_PAR_SJDB_GTF_FEATURE_EXON//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'sjdb_gtf_tag_exon_parent_transcript': $( if [ ! -z ${VIASH_PAR_SJDB_GTF_TAG_EXON_PARENT_TRANSCRIPT+x} ]; then echo "r'${VIASH_PAR_SJDB_GTF_TAG_EXON_PARENT_TRANSCRIPT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'sjdb_gtf_tag_exon_parent_gene': $( if [ ! -z ${VIASH_PAR_SJDB_GTF_TAG_EXON_PARENT_GENE+x} ]; then echo "r'${VIASH_PAR_SJDB_GTF_TAG_EXON_PARENT_GENE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'sjdb_gtf_tag_exon_parent_gene_name': $( if [ ! -z ${VIASH_PAR_SJDB_GTF_TAG_EXON_PARENT_GENE_NAME+x} ]; then echo "r'${VIASH_PAR_SJDB_GTF_TAG_EXON_PARENT_GENE_NAME//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'sjdb_gtf_tag_exon_parent_gene_type': $( if [ ! -z ${VIASH_PAR_SJDB_GTF_TAG_EXON_PARENT_GENE_TYPE+x} ]; then echo "r'${VIASH_PAR_SJDB_GTF_TAG_EXON_PARENT_GENE_TYPE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'sjdb_overhang': $( if [ ! -z ${VIASH_PAR_SJDB_OVERHANG+x} ]; then echo "int(r'${VIASH_PAR_SJDB_OVERHANG//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'sjdb_score': $( if [ ! -z ${VIASH_PAR_SJDB_SCORE+x} ]; then echo "int(r'${VIASH_PAR_SJDB_SCORE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'sjdb_insert_save': $( if [ ! -z ${VIASH_PAR_SJDB_INSERT_SAVE+x} ]; then echo "r'${VIASH_PAR_SJDB_INSERT_SAVE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'var_vcf_file': $( if [ ! -z ${VIASH_PAR_VAR_VCF_FILE+x} ]; then echo "r'${VIASH_PAR_VAR_VCF_FILE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'read_files_type': $( if [ ! -z ${VIASH_PAR_READ_FILES_TYPE+x} ]; then echo "r'${VIASH_PAR_READ_FILES_TYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'read_files_sam_attr_keep': $( if [ ! -z ${VIASH_PAR_READ_FILES_SAM_ATTR_KEEP+x} ]; then echo "r'${VIASH_PAR_READ_FILES_SAM_ATTR_KEEP//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'read_files_manifest': $( if [ ! -z ${VIASH_PAR_READ_FILES_MANIFEST+x} ]; then echo "r'${VIASH_PAR_READ_FILES_MANIFEST//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'read_files_prefix': $( if [ ! -z ${VIASH_PAR_READ_FILES_PREFIX+x} ]; then echo "r'${VIASH_PAR_READ_FILES_PREFIX//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'read_files_command': $( if [ ! -z ${VIASH_PAR_READ_FILES_COMMAND+x} ]; then echo "r'${VIASH_PAR_READ_FILES_COMMAND//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'read_map_number': $( if [ ! -z ${VIASH_PAR_READ_MAP_NUMBER+x} ]; then echo "int(r'${VIASH_PAR_READ_MAP_NUMBER//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'read_mates_lengths_in': $( if [ ! -z ${VIASH_PAR_READ_MATES_LENGTHS_IN+x} ]; then echo "r'${VIASH_PAR_READ_MATES_LENGTHS_IN//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'read_name_separator': $( if [ ! -z ${VIASH_PAR_READ_NAME_SEPARATOR+x} ]; then echo "r'${VIASH_PAR_READ_NAME_SEPARATOR//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'read_quality_score_base': $( if [ ! -z ${VIASH_PAR_READ_QUALITY_SCORE_BASE+x} ]; then echo "int(r'${VIASH_PAR_READ_QUALITY_SCORE_BASE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'clip_adapter_type': $( if [ ! -z ${VIASH_PAR_CLIP_ADAPTER_TYPE+x} ]; then echo "r'${VIASH_PAR_CLIP_ADAPTER_TYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'clip3p_nbases': $( if [ ! -z ${VIASH_PAR_CLIP3P_NBASES+x} ]; then echo "list(map(int, r'${VIASH_PAR_CLIP3P_NBASES//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'clip3p_adapter_seq': $( if [ ! -z ${VIASH_PAR_CLIP3P_ADAPTER_SEQ+x} ]; then echo "r'${VIASH_PAR_CLIP3P_ADAPTER_SEQ//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'clip3p_adapter_mm_p': $( if [ ! -z ${VIASH_PAR_CLIP3P_ADAPTER_MM_P+x} ]; then echo "list(map(float, r'${VIASH_PAR_CLIP3P_ADAPTER_MM_P//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'clip3p_after_adapter_nbases': $( if [ ! -z ${VIASH_PAR_CLIP3P_AFTER_ADAPTER_NBASES+x} ]; then echo "list(map(int, r'${VIASH_PAR_CLIP3P_AFTER_ADAPTER_NBASES//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'clip5p_nbases': $( if [ ! -z ${VIASH_PAR_CLIP5P_NBASES+x} ]; then echo "list(map(int, r'${VIASH_PAR_CLIP5P_NBASES//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'limit_genome_generate_ram': $( if [ ! -z ${VIASH_PAR_LIMIT_GENOME_GENERATE_RAM+x} ]; then echo "int(r'${VIASH_PAR_LIMIT_GENOME_GENERATE_RAM//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'limit_io_buffer_size': $( if [ ! -z ${VIASH_PAR_LIMIT_IO_BUFFER_SIZE+x} ]; then echo "list(map(int, r'${VIASH_PAR_LIMIT_IO_BUFFER_SIZE//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'limit_out_sam_one_read_bytes': $( if [ ! -z ${VIASH_PAR_LIMIT_OUT_SAM_ONE_READ_BYTES+x} ]; then echo "int(r'${VIASH_PAR_LIMIT_OUT_SAM_ONE_READ_BYTES//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'limit_out_sj_one_read': $( if [ ! -z ${VIASH_PAR_LIMIT_OUT_SJ_ONE_READ+x} ]; then echo "int(r'${VIASH_PAR_LIMIT_OUT_SJ_ONE_READ//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'limit_out_sj_collapsed': $( if [ ! -z ${VIASH_PAR_LIMIT_OUT_SJ_COLLAPSED+x} ]; then echo "int(r'${VIASH_PAR_LIMIT_OUT_SJ_COLLAPSED//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'limit_bam_sort_ram': $( if [ ! -z ${VIASH_PAR_LIMIT_BAM_SORT_RAM+x} ]; then echo "int(r'${VIASH_PAR_LIMIT_BAM_SORT_RAM//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'limit_sjdb_insert_nsj': $( if [ ! -z ${VIASH_PAR_LIMIT_SJDB_INSERT_NSJ+x} ]; then echo "int(r'${VIASH_PAR_LIMIT_SJDB_INSERT_NSJ//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'limit_nreads_soft': $( if [ ! -z ${VIASH_PAR_LIMIT_NREADS_SOFT+x} ]; then echo "int(r'${VIASH_PAR_LIMIT_NREADS_SOFT//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_tmp_keep': $( if [ ! -z ${VIASH_PAR_OUT_TMP_KEEP+x} ]; then echo "r'${VIASH_PAR_OUT_TMP_KEEP//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_std': $( if [ ! -z ${VIASH_PAR_OUT_STD+x} ]; then echo "r'${VIASH_PAR_OUT_STD//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_reads_unmapped': $( if [ ! -z ${VIASH_PAR_OUT_READS_UNMAPPED+x} ]; then echo "r'${VIASH_PAR_OUT_READS_UNMAPPED//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_qs_conversion_add': $( if [ ! -z ${VIASH_PAR_OUT_QS_CONVERSION_ADD+x} ]; then echo "int(r'${VIASH_PAR_OUT_QS_CONVERSION_ADD//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_multimapper_order': $( if [ ! -z ${VIASH_PAR_OUT_MULTIMAPPER_ORDER+x} ]; then echo "r'${VIASH_PAR_OUT_MULTIMAPPER_ORDER//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_sam_type': $( if [ ! -z ${VIASH_PAR_OUT_SAM_TYPE+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_TYPE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'out_sam_mode': $( if [ ! -z ${VIASH_PAR_OUT_SAM_MODE+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_MODE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_sam_strand_field': $( if [ ! -z ${VIASH_PAR_OUT_SAM_STRAND_FIELD+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_STRAND_FIELD//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_sam_attributes': $( if [ ! -z ${VIASH_PAR_OUT_SAM_ATTRIBUTES+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_ATTRIBUTES//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'out_sam_attr_ih_start': $( if [ ! -z ${VIASH_PAR_OUT_SAM_ATTR_IH_START+x} ]; then echo "int(r'${VIASH_PAR_OUT_SAM_ATTR_IH_START//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_sam_unmapped': $( if [ ! -z ${VIASH_PAR_OUT_SAM_UNMAPPED+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_UNMAPPED//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'out_sam_order': $( if [ ! -z ${VIASH_PAR_OUT_SAM_ORDER+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_ORDER//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_sam_primary_flag': $( if [ ! -z ${VIASH_PAR_OUT_SAM_PRIMARY_FLAG+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_PRIMARY_FLAG//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_sam_read_id': $( if [ ! -z ${VIASH_PAR_OUT_SAM_READ_ID+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_READ_ID//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_sam_mapq_unique': $( if [ ! -z ${VIASH_PAR_OUT_SAM_MAPQ_UNIQUE+x} ]; then echo "int(r'${VIASH_PAR_OUT_SAM_MAPQ_UNIQUE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_sam_flag_or': $( if [ ! -z ${VIASH_PAR_OUT_SAM_FLAG_OR+x} ]; then echo "int(r'${VIASH_PAR_OUT_SAM_FLAG_OR//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_sam_flag_and': $( if [ ! -z ${VIASH_PAR_OUT_SAM_FLAG_AND+x} ]; then echo "int(r'${VIASH_PAR_OUT_SAM_FLAG_AND//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_sam_attr_rg_line': $( if [ ! -z ${VIASH_PAR_OUT_SAM_ATTR_RG_LINE+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_ATTR_RG_LINE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'out_sam_header_hd': $( if [ ! -z ${VIASH_PAR_OUT_SAM_HEADER_HD+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_HEADER_HD//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'out_sam_header_pg': $( if [ ! -z ${VIASH_PAR_OUT_SAM_HEADER_PG+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_HEADER_PG//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'out_sam_header_comment_file': $( if [ ! -z ${VIASH_PAR_OUT_SAM_HEADER_COMMENT_FILE+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_HEADER_COMMENT_FILE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_sam_filter': $( if [ ! -z ${VIASH_PAR_OUT_SAM_FILTER+x} ]; then echo "r'${VIASH_PAR_OUT_SAM_FILTER//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'out_sam_mult_nmax': $( if [ ! -z ${VIASH_PAR_OUT_SAM_MULT_NMAX+x} ]; then echo "int(r'${VIASH_PAR_OUT_SAM_MULT_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_sam_tlen': $( if [ ! -z ${VIASH_PAR_OUT_SAM_TLEN+x} ]; then echo "int(r'${VIASH_PAR_OUT_SAM_TLEN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_bam_compression': $( if [ ! -z ${VIASH_PAR_OUT_BAM_COMPRESSION+x} ]; then echo "int(r'${VIASH_PAR_OUT_BAM_COMPRESSION//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_bam_sorting_thread_n': $( if [ ! -z ${VIASH_PAR_OUT_BAM_SORTING_THREAD_N+x} ]; then echo "int(r'${VIASH_PAR_OUT_BAM_SORTING_THREAD_N//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_bam_sorting_bins_n': $( if [ ! -z ${VIASH_PAR_OUT_BAM_SORTING_BINS_N+x} ]; then echo "int(r'${VIASH_PAR_OUT_BAM_SORTING_BINS_N//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'bam_remove_duplicates_type': $( if [ ! -z ${VIASH_PAR_BAM_REMOVE_DUPLICATES_TYPE+x} ]; then echo "r'${VIASH_PAR_BAM_REMOVE_DUPLICATES_TYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'bam_remove_duplicates_mate2bases_n': $( if [ ! -z ${VIASH_PAR_BAM_REMOVE_DUPLICATES_MATE2BASES_N+x} ]; then echo "int(r'${VIASH_PAR_BAM_REMOVE_DUPLICATES_MATE2BASES_N//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_wig_type': $( if [ ! -z ${VIASH_PAR_OUT_WIG_TYPE+x} ]; then echo "r'${VIASH_PAR_OUT_WIG_TYPE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'out_wig_strand': $( if [ ! -z ${VIASH_PAR_OUT_WIG_STRAND+x} ]; then echo "r'${VIASH_PAR_OUT_WIG_STRAND//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_wig_references_prefix': $( if [ ! -z ${VIASH_PAR_OUT_WIG_REFERENCES_PREFIX+x} ]; then echo "r'${VIASH_PAR_OUT_WIG_REFERENCES_PREFIX//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_wig_norm': $( if [ ! -z ${VIASH_PAR_OUT_WIG_NORM+x} ]; then echo "r'${VIASH_PAR_OUT_WIG_NORM//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_filter_type': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_TYPE+x} ]; then echo "r'${VIASH_PAR_OUT_FILTER_TYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_filter_multimap_score_range': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_MULTIMAP_SCORE_RANGE+x} ]; then echo "int(r'${VIASH_PAR_OUT_FILTER_MULTIMAP_SCORE_RANGE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_filter_multimap_nmax': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_MULTIMAP_NMAX+x} ]; then echo "int(r'${VIASH_PAR_OUT_FILTER_MULTIMAP_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_filter_mismatch_nmax': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_MISMATCH_NMAX+x} ]; then echo "int(r'${VIASH_PAR_OUT_FILTER_MISMATCH_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_filter_mismatch_nover_lmax': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_MISMATCH_NOVER_LMAX+x} ]; then echo "float(r'${VIASH_PAR_OUT_FILTER_MISMATCH_NOVER_LMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_filter_mismatch_nover_read_lmax': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_MISMATCH_NOVER_READ_LMAX+x} ]; then echo "float(r'${VIASH_PAR_OUT_FILTER_MISMATCH_NOVER_READ_LMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_filter_score_min': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_SCORE_MIN+x} ]; then echo "int(r'${VIASH_PAR_OUT_FILTER_SCORE_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_filter_score_min_over_lread': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_SCORE_MIN_OVER_LREAD+x} ]; then echo "float(r'${VIASH_PAR_OUT_FILTER_SCORE_MIN_OVER_LREAD//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_filter_match_nmin': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_MATCH_NMIN+x} ]; then echo "int(r'${VIASH_PAR_OUT_FILTER_MATCH_NMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_filter_match_nmin_over_lread': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_MATCH_NMIN_OVER_LREAD+x} ]; then echo "float(r'${VIASH_PAR_OUT_FILTER_MATCH_NMIN_OVER_LREAD//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'out_filter_intron_motifs': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_INTRON_MOTIFS+x} ]; then echo "r'${VIASH_PAR_OUT_FILTER_INTRON_MOTIFS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_filter_intron_strands': $( if [ ! -z ${VIASH_PAR_OUT_FILTER_INTRON_STRANDS+x} ]; then echo "r'${VIASH_PAR_OUT_FILTER_INTRON_STRANDS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_sj_type': $( if [ ! -z ${VIASH_PAR_OUT_SJ_TYPE+x} ]; then echo "r'${VIASH_PAR_OUT_SJ_TYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_sj_filter_reads': $( if [ ! -z ${VIASH_PAR_OUT_SJ_FILTER_READS+x} ]; then echo "r'${VIASH_PAR_OUT_SJ_FILTER_READS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'out_sj_filter_overhang_min': $( if [ ! -z ${VIASH_PAR_OUT_SJ_FILTER_OVERHANG_MIN+x} ]; then echo "list(map(int, r'${VIASH_PAR_OUT_SJ_FILTER_OVERHANG_MIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'out_sj_filter_count_unique_min': $( if [ ! -z ${VIASH_PAR_OUT_SJ_FILTER_COUNT_UNIQUE_MIN+x} ]; then echo "list(map(int, r'${VIASH_PAR_OUT_SJ_FILTER_COUNT_UNIQUE_MIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'out_sj_filter_count_total_min': $( if [ ! -z ${VIASH_PAR_OUT_SJ_FILTER_COUNT_TOTAL_MIN+x} ]; then echo "list(map(int, r'${VIASH_PAR_OUT_SJ_FILTER_COUNT_TOTAL_MIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'out_sj_filter_dist_to_other_sj_min': $( if [ ! -z ${VIASH_PAR_OUT_SJ_FILTER_DIST_TO_OTHER_SJ_MIN+x} ]; then echo "list(map(int, r'${VIASH_PAR_OUT_SJ_FILTER_DIST_TO_OTHER_SJ_MIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'out_sj_filter_intron_max_vs_read_n': $( if [ ! -z ${VIASH_PAR_OUT_SJ_FILTER_INTRON_MAX_VS_READ_N+x} ]; then echo "list(map(int, r'${VIASH_PAR_OUT_SJ_FILTER_INTRON_MAX_VS_READ_N//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'score_gap': $( if [ ! -z ${VIASH_PAR_SCORE_GAP+x} ]; then echo "int(r'${VIASH_PAR_SCORE_GAP//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'score_gap_noncan': $( if [ ! -z ${VIASH_PAR_SCORE_GAP_NONCAN+x} ]; then echo "int(r'${VIASH_PAR_SCORE_GAP_NONCAN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'score_gap_gcag': $( if [ ! -z ${VIASH_PAR_SCORE_GAP_GCAG+x} ]; then echo "int(r'${VIASH_PAR_SCORE_GAP_GCAG//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'score_gap_atac': $( if [ ! -z ${VIASH_PAR_SCORE_GAP_ATAC+x} ]; then echo "int(r'${VIASH_PAR_SCORE_GAP_ATAC//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'score_genomic_length_log2scale': $( if [ ! -z ${VIASH_PAR_SCORE_GENOMIC_LENGTH_LOG2SCALE+x} ]; then echo "int(r'${VIASH_PAR_SCORE_GENOMIC_LENGTH_LOG2SCALE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'score_del_open': $( if [ ! -z ${VIASH_PAR_SCORE_DEL_OPEN+x} ]; then echo "int(r'${VIASH_PAR_SCORE_DEL_OPEN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'score_del_base': $( if [ ! -z ${VIASH_PAR_SCORE_DEL_BASE+x} ]; then echo "int(r'${VIASH_PAR_SCORE_DEL_BASE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'score_ins_open': $( if [ ! -z ${VIASH_PAR_SCORE_INS_OPEN+x} ]; then echo "int(r'${VIASH_PAR_SCORE_INS_OPEN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'score_ins_base': $( if [ ! -z ${VIASH_PAR_SCORE_INS_BASE+x} ]; then echo "int(r'${VIASH_PAR_SCORE_INS_BASE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'score_stitch_sj_shift': $( if [ ! -z ${VIASH_PAR_SCORE_STITCH_SJ_SHIFT+x} ]; then echo "int(r'${VIASH_PAR_SCORE_STITCH_SJ_SHIFT//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'seed_search_start_lmax': $( if [ ! -z ${VIASH_PAR_SEED_SEARCH_START_LMAX+x} ]; then echo "int(r'${VIASH_PAR_SEED_SEARCH_START_LMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'seed_search_start_lmax_over_lread': $( if [ ! -z ${VIASH_PAR_SEED_SEARCH_START_LMAX_OVER_LREAD+x} ]; then echo "float(r'${VIASH_PAR_SEED_SEARCH_START_LMAX_OVER_LREAD//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'seed_search_lmax': $( if [ ! -z ${VIASH_PAR_SEED_SEARCH_LMAX+x} ]; then echo "int(r'${VIASH_PAR_SEED_SEARCH_LMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'seed_multimap_nmax': $( if [ ! -z ${VIASH_PAR_SEED_MULTIMAP_NMAX+x} ]; then echo "int(r'${VIASH_PAR_SEED_MULTIMAP_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'seed_per_read_nmax': $( if [ ! -z ${VIASH_PAR_SEED_PER_READ_NMAX+x} ]; then echo "int(r'${VIASH_PAR_SEED_PER_READ_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'seed_per_window_nmax': $( if [ ! -z ${VIASH_PAR_SEED_PER_WINDOW_NMAX+x} ]; then echo "int(r'${VIASH_PAR_SEED_PER_WINDOW_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'seed_none_loci_per_window': $( if [ ! -z ${VIASH_PAR_SEED_NONE_LOCI_PER_WINDOW+x} ]; then echo "int(r'${VIASH_PAR_SEED_NONE_LOCI_PER_WINDOW//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'seed_split_min': $( if [ ! -z ${VIASH_PAR_SEED_SPLIT_MIN+x} ]; then echo "int(r'${VIASH_PAR_SEED_SPLIT_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'seed_map_min': $( if [ ! -z ${VIASH_PAR_SEED_MAP_MIN+x} ]; then echo "int(r'${VIASH_PAR_SEED_MAP_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'align_intron_min': $( if [ ! -z ${VIASH_PAR_ALIGN_INTRON_MIN+x} ]; then echo "int(r'${VIASH_PAR_ALIGN_INTRON_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'align_intron_max': $( if [ ! -z ${VIASH_PAR_ALIGN_INTRON_MAX+x} ]; then echo "int(r'${VIASH_PAR_ALIGN_INTRON_MAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'align_mates_gap_max': $( if [ ! -z ${VIASH_PAR_ALIGN_MATES_GAP_MAX+x} ]; then echo "int(r'${VIASH_PAR_ALIGN_MATES_GAP_MAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'align_sj_overhang_min': $( if [ ! -z ${VIASH_PAR_ALIGN_SJ_OVERHANG_MIN+x} ]; then echo "int(r'${VIASH_PAR_ALIGN_SJ_OVERHANG_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'align_sj_stitch_mismatch_nmax': $( if [ ! -z ${VIASH_PAR_ALIGN_SJ_STITCH_MISMATCH_NMAX+x} ]; then echo "list(map(int, r'${VIASH_PAR_ALIGN_SJ_STITCH_MISMATCH_NMAX//\\'/\\'\\"\\'\\"r\\'}'.split(';')))"; else echo None; fi ), + 'align_sjdb_overhang_min': $( if [ ! -z ${VIASH_PAR_ALIGN_SJDB_OVERHANG_MIN+x} ]; then echo "int(r'${VIASH_PAR_ALIGN_SJDB_OVERHANG_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'align_spliced_mate_map_lmin': $( if [ ! -z ${VIASH_PAR_ALIGN_SPLICED_MATE_MAP_LMIN+x} ]; then echo "int(r'${VIASH_PAR_ALIGN_SPLICED_MATE_MAP_LMIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'align_spliced_mate_map_lmin_over_lmate': $( if [ ! -z ${VIASH_PAR_ALIGN_SPLICED_MATE_MAP_LMIN_OVER_LMATE+x} ]; then echo "float(r'${VIASH_PAR_ALIGN_SPLICED_MATE_MAP_LMIN_OVER_LMATE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'align_windows_per_read_nmax': $( if [ ! -z ${VIASH_PAR_ALIGN_WINDOWS_PER_READ_NMAX+x} ]; then echo "int(r'${VIASH_PAR_ALIGN_WINDOWS_PER_READ_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'align_transcripts_per_window_nmax': $( if [ ! -z ${VIASH_PAR_ALIGN_TRANSCRIPTS_PER_WINDOW_NMAX+x} ]; then echo "int(r'${VIASH_PAR_ALIGN_TRANSCRIPTS_PER_WINDOW_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'align_transcripts_per_read_nmax': $( if [ ! -z ${VIASH_PAR_ALIGN_TRANSCRIPTS_PER_READ_NMAX+x} ]; then echo "int(r'${VIASH_PAR_ALIGN_TRANSCRIPTS_PER_READ_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'align_ends_type': $( if [ ! -z ${VIASH_PAR_ALIGN_ENDS_TYPE+x} ]; then echo "r'${VIASH_PAR_ALIGN_ENDS_TYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'align_ends_protrude': $( if [ ! -z ${VIASH_PAR_ALIGN_ENDS_PROTRUDE+x} ]; then echo "r'${VIASH_PAR_ALIGN_ENDS_PROTRUDE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'align_soft_clip_at_reference_ends': $( if [ ! -z ${VIASH_PAR_ALIGN_SOFT_CLIP_AT_REFERENCE_ENDS+x} ]; then echo "r'${VIASH_PAR_ALIGN_SOFT_CLIP_AT_REFERENCE_ENDS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'align_insertion_flush': $( if [ ! -z ${VIASH_PAR_ALIGN_INSERTION_FLUSH+x} ]; then echo "r'${VIASH_PAR_ALIGN_INSERTION_FLUSH//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'pe_overlap_nbases_min': $( if [ ! -z ${VIASH_PAR_PE_OVERLAP_NBASES_MIN+x} ]; then echo "int(r'${VIASH_PAR_PE_OVERLAP_NBASES_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'pe_overlap_mm_p': $( if [ ! -z ${VIASH_PAR_PE_OVERLAP_MM_P+x} ]; then echo "float(r'${VIASH_PAR_PE_OVERLAP_MM_P//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'win_anchor_multimap_nmax': $( if [ ! -z ${VIASH_PAR_WIN_ANCHOR_MULTIMAP_NMAX+x} ]; then echo "int(r'${VIASH_PAR_WIN_ANCHOR_MULTIMAP_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'win_bin_nbits': $( if [ ! -z ${VIASH_PAR_WIN_BIN_NBITS+x} ]; then echo "int(r'${VIASH_PAR_WIN_BIN_NBITS//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'win_anchor_dist_nbins': $( if [ ! -z ${VIASH_PAR_WIN_ANCHOR_DIST_NBINS+x} ]; then echo "int(r'${VIASH_PAR_WIN_ANCHOR_DIST_NBINS//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'win_flank_nbins': $( if [ ! -z ${VIASH_PAR_WIN_FLANK_NBINS+x} ]; then echo "int(r'${VIASH_PAR_WIN_FLANK_NBINS//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'win_read_coverage_relative_min': $( if [ ! -z ${VIASH_PAR_WIN_READ_COVERAGE_RELATIVE_MIN+x} ]; then echo "float(r'${VIASH_PAR_WIN_READ_COVERAGE_RELATIVE_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'win_read_coverage_bases_min': $( if [ ! -z ${VIASH_PAR_WIN_READ_COVERAGE_BASES_MIN+x} ]; then echo "int(r'${VIASH_PAR_WIN_READ_COVERAGE_BASES_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_out_type': $( if [ ! -z ${VIASH_PAR_CHIM_OUT_TYPE+x} ]; then echo "r'${VIASH_PAR_CHIM_OUT_TYPE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'chim_segment_min': $( if [ ! -z ${VIASH_PAR_CHIM_SEGMENT_MIN+x} ]; then echo "int(r'${VIASH_PAR_CHIM_SEGMENT_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_score_min': $( if [ ! -z ${VIASH_PAR_CHIM_SCORE_MIN+x} ]; then echo "int(r'${VIASH_PAR_CHIM_SCORE_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_score_drop_max': $( if [ ! -z ${VIASH_PAR_CHIM_SCORE_DROP_MAX+x} ]; then echo "int(r'${VIASH_PAR_CHIM_SCORE_DROP_MAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_score_separation': $( if [ ! -z ${VIASH_PAR_CHIM_SCORE_SEPARATION+x} ]; then echo "int(r'${VIASH_PAR_CHIM_SCORE_SEPARATION//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_score_junction_non_gtag': $( if [ ! -z ${VIASH_PAR_CHIM_SCORE_JUNCTION_NON_GTAG+x} ]; then echo "int(r'${VIASH_PAR_CHIM_SCORE_JUNCTION_NON_GTAG//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_junction_overhang_min': $( if [ ! -z ${VIASH_PAR_CHIM_JUNCTION_OVERHANG_MIN+x} ]; then echo "int(r'${VIASH_PAR_CHIM_JUNCTION_OVERHANG_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_segment_read_gap_max': $( if [ ! -z ${VIASH_PAR_CHIM_SEGMENT_READ_GAP_MAX+x} ]; then echo "int(r'${VIASH_PAR_CHIM_SEGMENT_READ_GAP_MAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_filter': $( if [ ! -z ${VIASH_PAR_CHIM_FILTER+x} ]; then echo "r'${VIASH_PAR_CHIM_FILTER//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'chim_main_segment_mult_nmax': $( if [ ! -z ${VIASH_PAR_CHIM_MAIN_SEGMENT_MULT_NMAX+x} ]; then echo "int(r'${VIASH_PAR_CHIM_MAIN_SEGMENT_MULT_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_multimap_nmax': $( if [ ! -z ${VIASH_PAR_CHIM_MULTIMAP_NMAX+x} ]; then echo "int(r'${VIASH_PAR_CHIM_MULTIMAP_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_multimap_score_range': $( if [ ! -z ${VIASH_PAR_CHIM_MULTIMAP_SCORE_RANGE+x} ]; then echo "int(r'${VIASH_PAR_CHIM_MULTIMAP_SCORE_RANGE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_nonchim_score_drop_min': $( if [ ! -z ${VIASH_PAR_CHIM_NONCHIM_SCORE_DROP_MIN+x} ]; then echo "int(r'${VIASH_PAR_CHIM_NONCHIM_SCORE_DROP_MIN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'chim_out_junction_format': $( if [ ! -z ${VIASH_PAR_CHIM_OUT_JUNCTION_FORMAT+x} ]; then echo "int(r'${VIASH_PAR_CHIM_OUT_JUNCTION_FORMAT//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'quant_mode': $( if [ ! -z ${VIASH_PAR_QUANT_MODE+x} ]; then echo "r'${VIASH_PAR_QUANT_MODE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'quant_transcriptome_bam_compression': $( if [ ! -z ${VIASH_PAR_QUANT_TRANSCRIPTOME_BAM_COMPRESSION+x} ]; then echo "int(r'${VIASH_PAR_QUANT_TRANSCRIPTOME_BAM_COMPRESSION//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'quant_transcriptome_sam_output': $( if [ ! -z ${VIASH_PAR_QUANT_TRANSCRIPTOME_SAM_OUTPUT+x} ]; then echo "r'${VIASH_PAR_QUANT_TRANSCRIPTOME_SAM_OUTPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'twopass_mode': $( if [ ! -z ${VIASH_PAR_TWOPASS_MODE+x} ]; then echo "r'${VIASH_PAR_TWOPASS_MODE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'twopass1reads_n': $( if [ ! -z ${VIASH_PAR_TWOPASS1READS_N+x} ]; then echo "int(r'${VIASH_PAR_TWOPASS1READS_N//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'wasp_output_mode': $( if [ ! -z ${VIASH_PAR_WASP_OUTPUT_MODE+x} ]; then echo "r'${VIASH_PAR_WASP_OUTPUT_MODE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'solo_type': $( if [ ! -z ${VIASH_PAR_SOLO_TYPE+x} ]; then echo "r'${VIASH_PAR_SOLO_TYPE//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_cb_type': $( if [ ! -z ${VIASH_PAR_SOLO_CB_TYPE+x} ]; then echo "r'${VIASH_PAR_SOLO_CB_TYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'solo_cb_whitelist': $( if [ ! -z ${VIASH_PAR_SOLO_CB_WHITELIST+x} ]; then echo "r'${VIASH_PAR_SOLO_CB_WHITELIST//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_cb_start': $( if [ ! -z ${VIASH_PAR_SOLO_CB_START+x} ]; then echo "int(r'${VIASH_PAR_SOLO_CB_START//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'solo_cb_len': $( if [ ! -z ${VIASH_PAR_SOLO_CB_LEN+x} ]; then echo "int(r'${VIASH_PAR_SOLO_CB_LEN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'solo_umi_start': $( if [ ! -z ${VIASH_PAR_SOLO_UMI_START+x} ]; then echo "int(r'${VIASH_PAR_SOLO_UMI_START//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'solo_umi_len': $( if [ ! -z ${VIASH_PAR_SOLO_UMI_LEN+x} ]; then echo "int(r'${VIASH_PAR_SOLO_UMI_LEN//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'solo_barcode_read_length': $( if [ ! -z ${VIASH_PAR_SOLO_BARCODE_READ_LENGTH+x} ]; then echo "int(r'${VIASH_PAR_SOLO_BARCODE_READ_LENGTH//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'solo_barcode_mate': $( if [ ! -z ${VIASH_PAR_SOLO_BARCODE_MATE+x} ]; then echo "int(r'${VIASH_PAR_SOLO_BARCODE_MATE//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'solo_cb_position': $( if [ ! -z ${VIASH_PAR_SOLO_CB_POSITION+x} ]; then echo "r'${VIASH_PAR_SOLO_CB_POSITION//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_umi_position': $( if [ ! -z ${VIASH_PAR_SOLO_UMI_POSITION+x} ]; then echo "r'${VIASH_PAR_SOLO_UMI_POSITION//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'solo_adapter_sequence': $( if [ ! -z ${VIASH_PAR_SOLO_ADAPTER_SEQUENCE+x} ]; then echo "r'${VIASH_PAR_SOLO_ADAPTER_SEQUENCE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'solo_adapter_mismatches_nmax': $( if [ ! -z ${VIASH_PAR_SOLO_ADAPTER_MISMATCHES_NMAX+x} ]; then echo "int(r'${VIASH_PAR_SOLO_ADAPTER_MISMATCHES_NMAX//\\'/\\'\\"\\'\\"r\\'}')"; else echo None; fi ), + 'solo_cb_match_wl_type': $( if [ ! -z ${VIASH_PAR_SOLO_CB_MATCH_WL_TYPE+x} ]; then echo "r'${VIASH_PAR_SOLO_CB_MATCH_WL_TYPE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'solo_input_sam_attr_barcode_seq': $( if [ ! -z ${VIASH_PAR_SOLO_INPUT_SAM_ATTR_BARCODE_SEQ+x} ]; then echo "r'${VIASH_PAR_SOLO_INPUT_SAM_ATTR_BARCODE_SEQ//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_input_sam_attr_barcode_qual': $( if [ ! -z ${VIASH_PAR_SOLO_INPUT_SAM_ATTR_BARCODE_QUAL+x} ]; then echo "r'${VIASH_PAR_SOLO_INPUT_SAM_ATTR_BARCODE_QUAL//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_strand': $( if [ ! -z ${VIASH_PAR_SOLO_STRAND+x} ]; then echo "r'${VIASH_PAR_SOLO_STRAND//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'solo_features': $( if [ ! -z ${VIASH_PAR_SOLO_FEATURES+x} ]; then echo "r'${VIASH_PAR_SOLO_FEATURES//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_multi_mappers': $( if [ ! -z ${VIASH_PAR_SOLO_MULTI_MAPPERS+x} ]; then echo "r'${VIASH_PAR_SOLO_MULTI_MAPPERS//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_umi_dedup': $( if [ ! -z ${VIASH_PAR_SOLO_UMI_DEDUP+x} ]; then echo "r'${VIASH_PAR_SOLO_UMI_DEDUP//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_umi_filtering': $( if [ ! -z ${VIASH_PAR_SOLO_UMI_FILTERING+x} ]; then echo "r'${VIASH_PAR_SOLO_UMI_FILTERING//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_out_file_names': $( if [ ! -z ${VIASH_PAR_SOLO_OUT_FILE_NAMES+x} ]; then echo "r'${VIASH_PAR_SOLO_OUT_FILE_NAMES//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_cell_filter': $( if [ ! -z ${VIASH_PAR_SOLO_CELL_FILTER+x} ]; then echo "r'${VIASH_PAR_SOLO_CELL_FILTER//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_out_format_features_gene_field3': $( if [ ! -z ${VIASH_PAR_SOLO_OUT_FORMAT_FEATURES_GENE_FIELD3+x} ]; then echo "r'${VIASH_PAR_SOLO_OUT_FORMAT_FEATURES_GENE_FIELD3//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), + 'solo_cell_read_stats': $( if [ ! -z ${VIASH_PAR_SOLO_CELL_READ_STATS+x} ]; then echo "r'${VIASH_PAR_SOLO_CELL_READ_STATS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), 'input': $( if [ ! -z ${VIASH_PAR_INPUT+x} ]; then echo "r'${VIASH_PAR_INPUT//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), 'input_r2': $( if [ ! -z ${VIASH_PAR_INPUT_R2+x} ]; then echo "r'${VIASH_PAR_INPUT_R2//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ), 'aligned_reads': $( if [ ! -z ${VIASH_PAR_ALIGNED_READS+x} ]; then echo "r'${VIASH_PAR_ALIGNED_READS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), @@ -5221,7 +6182,8 @@ par = { 'unmapped_r2': $( if [ ! -z ${VIASH_PAR_UNMAPPED_R2+x} ]; then echo "r'${VIASH_PAR_UNMAPPED_R2//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), 'chimeric_junctions': $( if [ ! -z ${VIASH_PAR_CHIMERIC_JUNCTIONS+x} ]; then echo "r'${VIASH_PAR_CHIMERIC_JUNCTIONS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), 'log': $( if [ ! -z ${VIASH_PAR_LOG+x} ]; then echo "r'${VIASH_PAR_LOG//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), - 'splice_junctions': $( if [ ! -z ${VIASH_PAR_SPLICE_JUNCTIONS+x} ]; then echo "r'${VIASH_PAR_SPLICE_JUNCTIONS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ) + 'splice_junctions': $( if [ ! -z ${VIASH_PAR_SPLICE_JUNCTIONS+x} ]; then echo "r'${VIASH_PAR_SPLICE_JUNCTIONS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'reads_aligned_to_transcriptome': $( if [ ! -z ${VIASH_PAR_READS_ALIGNED_TO_TRANSCRIPTOME+x} ]; then echo "r'${VIASH_PAR_READS_ALIGNED_TO_TRANSCRIPTOME//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ) } meta = { 'name': $( if [ ! -z ${VIASH_META_NAME+x} ]; then echo "r'${VIASH_META_NAME//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), @@ -5249,6 +6211,15 @@ dep = { ## VIASH END +# read config +with open(meta["config"], 'r') as stream: + config = yaml.safe_load(stream) +all_arguments = { + arg["name"].lstrip('-'): arg + for argument_group in config["argument_groups"] + for arg in argument_group["arguments"] +} + ################################################## # check and process SE / PE R1 input files input_r1 = par["input"] @@ -5285,7 +6256,8 @@ expected_outputs = { "log": "Log.final.out", "splice_junctions": "SJ.out.tab", "unmapped": "Unmapped.out.mate1", - "unmapped_r2": "Unmapped.out.mate2" + "unmapped_r2": "Unmapped.out.mate2", + "reads_aligned_to_transcriptome": "Aligned.toTranscriptome.out.bam" } output_paths = {name: par[name] for name in expected_outputs.keys()} for name in expected_outputs.keys(): @@ -5313,8 +6285,13 @@ with tempfile.TemporaryDirectory(prefix="star-", dir=meta["temp_dir"], ignore_cl cmd_args = [ "STAR" ] for name, value in par.items(): if value is not None: + if name in all_arguments: + arg_info = all_arguments[name].get("info", {}) + cli_name = arg_info.get("orig_name", f"--{name}") + else: + cli_name = f"--{name}" val_to_add = value if isinstance(value, list) else [value] - cmd_args.extend([f"--{name}"] + [str(x) for x in val_to_add]) + cmd_args.extend([cli_name] + [str(x) for x in val_to_add]) print("", flush=True) # run command @@ -5414,7 +6391,11 @@ def vdsl3WorkflowFactory(Map args, Map meta, String rawScript) { val = val.join(par.multiple_sep) } if (par.direction == "output" && par.type == "file") { - val = val.replaceAll('\\$id', id).replaceAll('\\$key', key) + val = val + .replaceAll('\\$id', id) + .replaceAll('\\$\\{id\\}', id) + .replaceAll('\\$key', key) + .replaceAll('\\$\\{key\\}', key) } [parName, val] } @@ -5545,7 +6526,8 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def createParentStr = meta.config.allArguments .findAll { it.type == "file" && it.direction == "output" && it.create_parent } .collect { par -> - "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent \\\"\" + (args[\"${par.plainName}\"] instanceof String ? args[\"${par.plainName}\"] : args[\"${par.plainName}\"].join('\" \"')) + \"\\\"\" : \"\" }" + def contents = "args[\"${par.plainName}\"] instanceof List ? args[\"${par.plainName}\"].join('\" \"') : args[\"${par.plainName}\"]" + "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent '\" + escapeText(${contents}) + \"'\" : \"\" }" } .join("\n") @@ -5553,8 +6535,8 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def inputFileExports = meta.config.allArguments .findAll { it.type == "file" && it.direction.toLowerCase() == "input" } .collect { par -> - def viash_par_contents = "(viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName})" - "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}=\\\"\" + ${viash_par_contents} + \"\\\"\"}" + def contents = "viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName}" + "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}='\" + escapeText(${contents}) + \"'\"}" } // NOTE: if using docker, use /tmp instead of tmpDir! @@ -5591,6 +6573,7 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { def procStr = """nextflow.enable.dsl=2 | + |def escapeText = { s -> s.toString().replaceAll("'", "'\\\"'\\\"'") } |process $procKey {$drctvStrs |input: | tuple val(id)$inputPaths, val(args), path(resourcesDir, stageAs: ".viash_meta_resources") @@ -5602,10 +6585,9 @@ def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { |$stub |\"\"\" |script:$assertStr - |def escapeText = { s -> s.toString().replaceAll('([`"])', '\\\\\\\\\$1') } |def parInject = args | .findAll{key, value -> value != null} - | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}=\\\"\${escapeText(value)}\\\""} + | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}='\${escapeText(value)}'"} | .join("\\n") |\"\"\" |# meta exports @@ -5690,7 +6672,7 @@ meta["defaults"] = [ "container" : { "registry" : "images.viash-hub.com", "image" : "vsh/biobox/star/star_align_reads", - "tag" : "v0.1.0" + "tag" : "main" }, "tag" : "$id" }'''), diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/nextflow.config b/target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/nextflow.config similarity index 98% rename from target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/nextflow.config rename to target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/nextflow.config index 54b1a38..aaf983d 100644 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/nextflow.config +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/nextflow.config @@ -2,8 +2,9 @@ manifest { name = 'star/star_align_reads' mainScript = 'main.nf' nextflowVersion = '!>=20.12.1-edge' - version = 'v0.1.0' + version = 'main' description = 'Aligns reads to a reference genome using STAR.\n' + author = 'Angela Oliveira Pisco, Robrecht Cannoodt' } process.container = 'nextflow/bash:latest' diff --git a/target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/nextflow_schema.json b/target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/nextflow_schema.json new file mode 100644 index 0000000..b839aa8 --- /dev/null +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/nextflow_schema.json @@ -0,0 +1,2314 @@ +{ +"$schema": "http://json-schema.org/draft-07/schema", +"title": "star_align_reads", +"description": "Aligns reads to a reference genome using STAR.\n", +"type": "object", +"definitions": { + + + + "inputs" : { + "title": "Inputs", + "type": "object", + "description": "No description", + "properties": { + + + "input": { + "type": + "string", + "description": "Type: List of `file`, required, example: `mysample_S1_L001_R1_001.fastq.gz`, multiple_sep: `\";\"`. The single-end or paired-end R1 FastQ files to be processed", + "help_text": "Type: List of `file`, required, example: `mysample_S1_L001_R1_001.fastq.gz`, multiple_sep: `\";\"`. The single-end or paired-end R1 FastQ files to be processed." + + } + + + , + "input_r2": { + "type": + "string", + "description": "Type: List of `file`, example: `mysample_S1_L001_R2_001.fastq.gz`, multiple_sep: `\";\"`. The paired-end R2 FastQ files to be processed", + "help_text": "Type: List of `file`, example: `mysample_S1_L001_R2_001.fastq.gz`, multiple_sep: `\";\"`. The paired-end R2 FastQ files to be processed. Only required if --input is a paired-end R1 file." + + } + + +} +}, + + + "outputs" : { + "title": "Outputs", + "type": "object", + "description": "No description", + "properties": { + + + "aligned_reads": { + "type": + "string", + "description": "Type: `file`, required, default: `$id.$key.aligned_reads.bam`, example: `aligned_reads.bam`. The output file containing the aligned reads", + "help_text": "Type: `file`, required, default: `$id.$key.aligned_reads.bam`, example: `aligned_reads.bam`. The output file containing the aligned reads." + , + "default":"$id.$key.aligned_reads.bam" + } + + + , + "reads_per_gene": { + "type": + "string", + "description": "Type: `file`, default: `$id.$key.reads_per_gene.tsv`, example: `reads_per_gene.tsv`. The output file containing the number of reads per gene", + "help_text": "Type: `file`, default: `$id.$key.reads_per_gene.tsv`, example: `reads_per_gene.tsv`. The output file containing the number of reads per gene." + , + "default":"$id.$key.reads_per_gene.tsv" + } + + + , + "unmapped": { + "type": + "string", + "description": "Type: `file`, default: `$id.$key.unmapped.fastq`, example: `unmapped.fastq`. The output file containing the unmapped reads", + "help_text": "Type: `file`, default: `$id.$key.unmapped.fastq`, example: `unmapped.fastq`. The output file containing the unmapped reads." + , + "default":"$id.$key.unmapped.fastq" + } + + + , + "unmapped_r2": { + "type": + "string", + "description": "Type: `file`, default: `$id.$key.unmapped_r2.fastq`, example: `unmapped_r2.fastq`. The output file containing the unmapped R2 reads", + "help_text": "Type: `file`, default: `$id.$key.unmapped_r2.fastq`, example: `unmapped_r2.fastq`. The output file containing the unmapped R2 reads." + , + "default":"$id.$key.unmapped_r2.fastq" + } + + + , + "chimeric_junctions": { + "type": + "string", + "description": "Type: `file`, default: `$id.$key.chimeric_junctions.tsv`, example: `chimeric_junctions.tsv`. The output file containing the chimeric junctions", + "help_text": "Type: `file`, default: `$id.$key.chimeric_junctions.tsv`, example: `chimeric_junctions.tsv`. The output file containing the chimeric junctions." + , + "default":"$id.$key.chimeric_junctions.tsv" + } + + + , + "log": { + "type": + "string", + "description": "Type: `file`, default: `$id.$key.log.txt`, example: `log.txt`. The output file containing the log of the alignment process", + "help_text": "Type: `file`, default: `$id.$key.log.txt`, example: `log.txt`. The output file containing the log of the alignment process." + , + "default":"$id.$key.log.txt" + } + + + , + "splice_junctions": { + "type": + "string", + "description": "Type: `file`, default: `$id.$key.splice_junctions.tsv`, example: `splice_junctions.tsv`. The output file containing the splice junctions", + "help_text": "Type: `file`, default: `$id.$key.splice_junctions.tsv`, example: `splice_junctions.tsv`. The output file containing the splice junctions." + , + "default":"$id.$key.splice_junctions.tsv" + } + + + , + "reads_aligned_to_transcriptome": { + "type": + "string", + "description": "Type: `file`, default: `$id.$key.reads_aligned_to_transcriptome.bam`, example: `transcriptome_aligned.bam`. The output file containing the alignments to transcriptome in BAM formats", + "help_text": "Type: `file`, default: `$id.$key.reads_aligned_to_transcriptome.bam`, example: `transcriptome_aligned.bam`. The output file containing the alignments to transcriptome in BAM formats. This file is generated when --quantMode is set to TranscriptomeSAM." + , + "default":"$id.$key.reads_aligned_to_transcriptome.bam" + } + + +} +}, + + + "run parameters" : { + "title": "Run Parameters", + "type": "object", + "description": "No description", + "properties": { + + + "run_rng_seed": { + "type": + "integer", + "description": "Type: `integer`, example: `777`. random number generator seed", + "help_text": "Type: `integer`, example: `777`. random number generator seed." + + } + + +} +}, + + + "genome parameters" : { + "title": "Genome Parameters", + "type": "object", + "description": "No description", + "properties": { + + + "genome_dir": { + "type": + "string", + "description": "Type: `file`, required, example: `./GenomeDir`. path to the directory where genome files are stored (for --runMode alignReads) or will be generated (for --runMode generateGenome)", + "help_text": "Type: `file`, required, example: `./GenomeDir`. path to the directory where genome files are stored (for --runMode alignReads) or will be generated (for --runMode generateGenome)" + + } + + + , + "genome_load": { + "type": + "string", + "description": "Type: `string`, example: `NoSharedMemory`. mode of shared memory usage for the genome files", + "help_text": "Type: `string`, example: `NoSharedMemory`. mode of shared memory usage for the genome files. Only used with --runMode alignReads.\n\n- LoadAndKeep ... load genome into shared and keep it in memory after run\n- LoadAndRemove ... load genome into shared but remove it after run\n- LoadAndExit ... load genome into shared memory and exit, keeping the genome in memory for future runs\n- Remove ... do not map anything, just remove loaded genome from memory\n- NoSharedMemory ... do not use shared memory, each job will have its own private copy of the genome" + + } + + + , + "genome_fasta_files": { + "type": + "string", + "description": "Type: List of `file`, multiple_sep: `\";\"`. path(s) to the fasta files with the genome sequences, separated by spaces", + "help_text": "Type: List of `file`, multiple_sep: `\";\"`. path(s) to the fasta files with the genome sequences, separated by spaces. These files should be plain text FASTA files, they *cannot* be zipped.\n\nRequired for the genome generation (--runMode genomeGenerate). Can also be used in the mapping (--runMode alignReads) to add extra (new) sequences to the genome (e.g. spike-ins)." + + } + + + , + "genome_file_sizes": { + "type": + "string", + "description": "Type: List of `integer`, example: `0`, multiple_sep: `\";\"`. genome files exact sizes in bytes", + "help_text": "Type: List of `integer`, example: `0`, multiple_sep: `\";\"`. genome files exact sizes in bytes. Typically, this should not be defined by the user." + + } + + + , + "genome_transform_output": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. which output to transform back to original genome\n\n- SAM ", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. which output to transform back to original genome\n\n- SAM ... SAM/BAM alignments\n- SJ ... splice junctions (SJ.out.tab)\n- Quant ... quantifications (from --quant_mode option)\n- None ... no transformation of the output" + + } + + + , + "genome_chr_set_mitochondrial": { + "type": + "string", + "description": "Type: List of `string`, example: `chrM;M;MT`, multiple_sep: `\";\"`. names of the mitochondrial chromosomes", + "help_text": "Type: List of `string`, example: `chrM;M;MT`, multiple_sep: `\";\"`. names of the mitochondrial chromosomes. Presently only used for STARsolo statistics output/" + + } + + +} +}, + + + "splice junctions database" : { + "title": "Splice Junctions Database", + "type": "object", + "description": "No description", + "properties": { + + + "sjdb_file_chr_start_end": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. path to the files with genomic coordinates (chr \u003ctab\u003e start \u003ctab\u003e end \u003ctab\u003e strand) for the splice junction introns", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. path to the files with genomic coordinates (chr \u003ctab\u003e start \u003ctab\u003e end \u003ctab\u003e strand) for the splice junction introns. Multiple files can be supplied and will be concatenated." + + } + + + , + "sjdb_gtf_file": { + "type": + "string", + "description": "Type: `file`. path to the GTF file with annotations", + "help_text": "Type: `file`. path to the GTF file with annotations" + + } + + + , + "sjdb_gtf_chr_prefix": { + "type": + "string", + "description": "Type: `string`. prefix for chromosome names in a GTF file (e", + "help_text": "Type: `string`. prefix for chromosome names in a GTF file (e.g. \u0027chr\u0027 for using ENSMEBL annotations with UCSC genomes)" + + } + + + , + "sjdb_gtf_feature_exon": { + "type": + "string", + "description": "Type: `string`, example: `exon`. feature type in GTF file to be used as exons for building transcripts", + "help_text": "Type: `string`, example: `exon`. feature type in GTF file to be used as exons for building transcripts" + + } + + + , + "sjdb_gtf_tag_exon_parent_transcript": { + "type": + "string", + "description": "Type: `string`, example: `transcript_id`. GTF attribute name for parent transcript ID (default \"transcript_id\" works for GTF files)", + "help_text": "Type: `string`, example: `transcript_id`. GTF attribute name for parent transcript ID (default \"transcript_id\" works for GTF files)" + + } + + + , + "sjdb_gtf_tag_exon_parent_gene": { + "type": + "string", + "description": "Type: `string`, example: `gene_id`. GTF attribute name for parent gene ID (default \"gene_id\" works for GTF files)", + "help_text": "Type: `string`, example: `gene_id`. GTF attribute name for parent gene ID (default \"gene_id\" works for GTF files)" + + } + + + , + "sjdb_gtf_tag_exon_parent_gene_name": { + "type": + "string", + "description": "Type: List of `string`, example: `gene_name`, multiple_sep: `\";\"`. GTF attribute name for parent gene name", + "help_text": "Type: List of `string`, example: `gene_name`, multiple_sep: `\";\"`. GTF attribute name for parent gene name" + + } + + + , + "sjdb_gtf_tag_exon_parent_gene_type": { + "type": + "string", + "description": "Type: List of `string`, example: `gene_type;gene_biotype`, multiple_sep: `\";\"`. GTF attribute name for parent gene type", + "help_text": "Type: List of `string`, example: `gene_type;gene_biotype`, multiple_sep: `\";\"`. GTF attribute name for parent gene type" + + } + + + , + "sjdb_overhang": { + "type": + "integer", + "description": "Type: `integer`, example: `100`. length of the donor/acceptor sequence on each side of the junctions, ideally = (mate_length - 1)", + "help_text": "Type: `integer`, example: `100`. length of the donor/acceptor sequence on each side of the junctions, ideally = (mate_length - 1)" + + } + + + , + "sjdb_score": { + "type": + "integer", + "description": "Type: `integer`, example: `2`. extra alignment score for alignments that cross database junctions", + "help_text": "Type: `integer`, example: `2`. extra alignment score for alignments that cross database junctions" + + } + + + , + "sjdb_insert_save": { + "type": + "string", + "description": "Type: `string`, example: `Basic`. which files to save when sjdb junctions are inserted on the fly at the mapping step\n\n- Basic ", + "help_text": "Type: `string`, example: `Basic`. which files to save when sjdb junctions are inserted on the fly at the mapping step\n\n- Basic ... only small junction / transcript files\n- All ... all files including big Genome, SA and SAindex - this will create a complete genome directory" + + } + + +} +}, + + + "variation parameters" : { + "title": "Variation parameters", + "type": "object", + "description": "No description", + "properties": { + + + "var_vcf_file": { + "type": + "string", + "description": "Type: `string`. path to the VCF file that contains variation data", + "help_text": "Type: `string`. path to the VCF file that contains variation data. The 10th column should contain the genotype information, e.g. 0/1" + + } + + +} +}, + + + "read parameters" : { + "title": "Read Parameters", + "type": "object", + "description": "No description", + "properties": { + + + "read_files_type": { + "type": + "string", + "description": "Type: `string`, example: `Fastx`. format of input read files\n\n- Fastx ", + "help_text": "Type: `string`, example: `Fastx`. format of input read files\n\n- Fastx ... FASTA or FASTQ\n- SAM SE ... SAM or BAM single-end reads; for BAM use --read_files_command samtools view\n- SAM PE ... SAM or BAM paired-end reads; for BAM use --read_files_command samtools view" + + } + + + , + "read_files_sam_attr_keep": { + "type": + "string", + "description": "Type: List of `string`, example: `All`, multiple_sep: `\";\"`. for --read_files_type SAM SE/PE, which SAM tags to keep in the output BAM, e", + "help_text": "Type: List of `string`, example: `All`, multiple_sep: `\";\"`. for --read_files_type SAM SE/PE, which SAM tags to keep in the output BAM, e.g.: --readFilesSAMtagsKeep RG PL\n\n- All ... keep all tags\n- None ... do not keep any tags" + + } + + + , + "read_files_manifest": { + "type": + "string", + "description": "Type: `file`. path to the \"manifest\" file with the names of read files", + "help_text": "Type: `file`. path to the \"manifest\" file with the names of read files. The manifest file should contain 3 tab-separated columns:\n\npaired-end reads: read1_file_name $tab$ read2_file_name $tab$ read_group_line.\nsingle-end reads: read1_file_name $tab$ - $tab$ read_group_line.\nSpaces, but not tabs are allowed in file names.\nIf read_group_line does not start with ID:, it can only contain one ID field, and ID: will be added to it.\nIf read_group_line starts with ID:, it can contain several fields separated by $tab$, and all fields will be be copied verbatim into SAM @RG header line." + + } + + + , + "read_files_prefix": { + "type": + "string", + "description": "Type: `string`. prefix for the read files names, i", + "help_text": "Type: `string`. prefix for the read files names, i.e. it will be added in front of the strings in --readFilesIn" + + } + + + , + "read_files_command": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. command line to execute for each of the input file", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. command line to execute for each of the input file. This command should generate FASTA or FASTQ text and send it to stdout\n\nFor example: zcat - to uncompress .gz files, bzcat - to uncompress .bz2 files, etc." + + } + + + , + "read_map_number": { + "type": + "integer", + "description": "Type: `integer`, example: `-1`. number of reads to map from the beginning of the file\n\n-1: map all reads", + "help_text": "Type: `integer`, example: `-1`. number of reads to map from the beginning of the file\n\n-1: map all reads" + + } + + + , + "read_mates_lengths_in": { + "type": + "string", + "description": "Type: `string`, example: `NotEqual`. Equal/NotEqual - lengths of names,sequences,qualities for both mates are the same / not the same", + "help_text": "Type: `string`, example: `NotEqual`. Equal/NotEqual - lengths of names,sequences,qualities for both mates are the same / not the same. NotEqual is safe in all situations." + + } + + + , + "read_name_separator": { + "type": + "string", + "description": "Type: List of `string`, example: `/`, multiple_sep: `\";\"`. character(s) separating the part of the read names that will be trimmed in output (read name after space is always trimmed)", + "help_text": "Type: List of `string`, example: `/`, multiple_sep: `\";\"`. character(s) separating the part of the read names that will be trimmed in output (read name after space is always trimmed)" + + } + + + , + "read_quality_score_base": { + "type": + "integer", + "description": "Type: `integer`, example: `33`. number to be subtracted from the ASCII code to get Phred quality score", + "help_text": "Type: `integer`, example: `33`. number to be subtracted from the ASCII code to get Phred quality score" + + } + + +} +}, + + + "read clipping" : { + "title": "Read Clipping", + "type": "object", + "description": "No description", + "properties": { + + + "clip_adapter_type": { + "type": + "string", + "description": "Type: `string`, example: `Hamming`. adapter clipping type\n\n- Hamming ", + "help_text": "Type: `string`, example: `Hamming`. adapter clipping type\n\n- Hamming ... adapter clipping based on Hamming distance, with the number of mismatches controlled by --clip5pAdapterMMp\n- CellRanger4 ... 5p and 3p adapter clipping similar to CellRanger4. Utilizes Opal package by Martin Sosic: https://github.com/Martinsos/opal\n- None ... no adapter clipping, all other clip* parameters are disregarded" + + } + + + , + "clip3p_nbases": { + "type": + "string", + "description": "Type: List of `integer`, example: `0`, multiple_sep: `\";\"`. number(s) of bases to clip from 3p of each mate", + "help_text": "Type: List of `integer`, example: `0`, multiple_sep: `\";\"`. number(s) of bases to clip from 3p of each mate. If one value is given, it will be assumed the same for both mates." + + } + + + , + "clip3p_adapter_seq": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. adapter sequences to clip from 3p of each mate", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. adapter sequences to clip from 3p of each mate. If one value is given, it will be assumed the same for both mates.\n\n- polyA ... polyA sequence with the length equal to read length" + + } + + + , + "clip3p_adapter_mm_p": { + "type": + "string", + "description": "Type: List of `double`, example: `0.1`, multiple_sep: `\";\"`. max proportion of mismatches for 3p adapter clipping for each mate", + "help_text": "Type: List of `double`, example: `0.1`, multiple_sep: `\";\"`. max proportion of mismatches for 3p adapter clipping for each mate. If one value is given, it will be assumed the same for both mates." + + } + + + , + "clip3p_after_adapter_nbases": { + "type": + "string", + "description": "Type: List of `integer`, example: `0`, multiple_sep: `\";\"`. number of bases to clip from 3p of each mate after the adapter clipping", + "help_text": "Type: List of `integer`, example: `0`, multiple_sep: `\";\"`. number of bases to clip from 3p of each mate after the adapter clipping. If one value is given, it will be assumed the same for both mates." + + } + + + , + "clip5p_nbases": { + "type": + "string", + "description": "Type: List of `integer`, example: `0`, multiple_sep: `\";\"`. number(s) of bases to clip from 5p of each mate", + "help_text": "Type: List of `integer`, example: `0`, multiple_sep: `\";\"`. number(s) of bases to clip from 5p of each mate. If one value is given, it will be assumed the same for both mates." + + } + + +} +}, + + + "limits" : { + "title": "Limits", + "type": "object", + "description": "No description", + "properties": { + + + "limit_genome_generate_ram": { + "type": + "string", + "description": "Type: `long`, example: `31000000000`. maximum available RAM (bytes) for genome generation", + "help_text": "Type: `long`, example: `31000000000`. maximum available RAM (bytes) for genome generation" + + } + + + , + "limit_io_buffer_size": { + "type": + "string", + "description": "Type: List of `long`, example: `30000000;50000000`, multiple_sep: `\";\"`. max available buffers size (bytes) for input/output, per thread", + "help_text": "Type: List of `long`, example: `30000000;50000000`, multiple_sep: `\";\"`. max available buffers size (bytes) for input/output, per thread" + + } + + + , + "limit_out_sam_one_read_bytes": { + "type": + "string", + "description": "Type: `long`, example: `100000`. max size of the SAM record (bytes) for one read", + "help_text": "Type: `long`, example: `100000`. max size of the SAM record (bytes) for one read. Recommended value: \u003e(2*(LengthMate1+LengthMate2+100)*outFilterMultimapNmax" + + } + + + , + "limit_out_sj_one_read": { + "type": + "integer", + "description": "Type: `integer`, example: `1000`. max number of junctions for one read (including all multi-mappers)", + "help_text": "Type: `integer`, example: `1000`. max number of junctions for one read (including all multi-mappers)" + + } + + + , + "limit_out_sj_collapsed": { + "type": + "integer", + "description": "Type: `integer`, example: `1000000`. max number of collapsed junctions", + "help_text": "Type: `integer`, example: `1000000`. max number of collapsed junctions" + + } + + + , + "limit_bam_sort_ram": { + "type": + "string", + "description": "Type: `long`, example: `0`. maximum available RAM (bytes) for sorting BAM", + "help_text": "Type: `long`, example: `0`. maximum available RAM (bytes) for sorting BAM. If =0, it will be set to the genome index size. 0 value can only be used with --genome_load NoSharedMemory option." + + } + + + , + "limit_sjdb_insert_nsj": { + "type": + "integer", + "description": "Type: `integer`, example: `1000000`. maximum number of junctions to be inserted to the genome on the fly at the mapping stage, including those from annotations and those detected in the 1st step of the 2-pass run", + "help_text": "Type: `integer`, example: `1000000`. maximum number of junctions to be inserted to the genome on the fly at the mapping stage, including those from annotations and those detected in the 1st step of the 2-pass run" + + } + + + , + "limit_nreads_soft": { + "type": + "integer", + "description": "Type: `integer`, example: `-1`. soft limit on the number of reads", + "help_text": "Type: `integer`, example: `-1`. soft limit on the number of reads" + + } + + +} +}, + + + "output: general" : { + "title": "Output: general", + "type": "object", + "description": "No description", + "properties": { + + + "out_tmp_keep": { + "type": + "string", + "description": "Type: `string`. whether to keep the temporary files after STAR runs is finished\n\n- None ", + "help_text": "Type: `string`. whether to keep the temporary files after STAR runs is finished\n\n- None ... remove all temporary files\n- All ... keep all files" + + } + + + , + "out_std": { + "type": + "string", + "description": "Type: `string`, example: `Log`. which output will be directed to stdout (standard out)\n\n- Log ", + "help_text": "Type: `string`, example: `Log`. which output will be directed to stdout (standard out)\n\n- Log ... log messages\n- SAM ... alignments in SAM format (which normally are output to Aligned.out.sam file), normal standard output will go into Log.std.out\n- BAM_Unsorted ... alignments in BAM format, unsorted. Requires --out_sam_type BAM Unsorted\n- BAM_SortedByCoordinate ... alignments in BAM format, sorted by coordinate. Requires --out_sam_type BAM SortedByCoordinate\n- BAM_Quant ... alignments to transcriptome in BAM format, unsorted. Requires --quant_mode TranscriptomeSAM" + + } + + + , + "out_reads_unmapped": { + "type": + "string", + "description": "Type: `string`. output of unmapped and partially mapped (i", + "help_text": "Type: `string`. output of unmapped and partially mapped (i.e. mapped only one mate of a paired end read) reads in separate file(s).\n\n- None ... no output\n- Fastx ... output in separate fasta/fastq files, Unmapped.out.mate1/2" + + } + + + , + "out_qs_conversion_add": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. add this number to the quality score (e", + "help_text": "Type: `integer`, example: `0`. add this number to the quality score (e.g. to convert from Illumina to Sanger, use -31)" + + } + + + , + "out_multimapper_order": { + "type": + "string", + "description": "Type: `string`, example: `Old_2.4`. order of multimapping alignments in the output files\n\n- Old_2", + "help_text": "Type: `string`, example: `Old_2.4`. order of multimapping alignments in the output files\n\n- Old_2.4 ... quasi-random order used before 2.5.0\n- Random ... random order of alignments for each multi-mapper. Read mates (pairs) are always adjacent, all alignment for each read stay together. This option will become default in the future releases." + + } + + +} +}, + + + "output: sam and bam" : { + "title": "Output: SAM and BAM", + "type": "object", + "description": "No description", + "properties": { + + + "out_sam_type": { + "type": + "string", + "description": "Type: List of `string`, example: `SAM`, multiple_sep: `\";\"`. type of SAM/BAM output\n\n1st word:\n- BAM ", + "help_text": "Type: List of `string`, example: `SAM`, multiple_sep: `\";\"`. type of SAM/BAM output\n\n1st word:\n- BAM ... output BAM without sorting\n- SAM ... output SAM without sorting\n- None ... no SAM/BAM output\n2nd, 3rd:\n- Unsorted ... standard unsorted\n- SortedByCoordinate ... sorted by coordinate. This option will allocate extra memory for sorting which can be specified by --limit_bam_sort_ram." + + } + + + , + "out_sam_mode": { + "type": + "string", + "description": "Type: `string`, example: `Full`. mode of SAM output\n\n- None ", + "help_text": "Type: `string`, example: `Full`. mode of SAM output\n\n- None ... no SAM output\n- Full ... full SAM output\n- NoQS ... full SAM but without quality scores" + + } + + + , + "out_sam_strand_field": { + "type": + "string", + "description": "Type: `string`. Cufflinks-like strand field flag\n\n- None ", + "help_text": "Type: `string`. Cufflinks-like strand field flag\n\n- None ... not used\n- intronMotif ... strand derived from the intron motif. This option changes the output alignments: reads with inconsistent and/or non-canonical introns are filtered out." + + } + + + , + "out_sam_attributes": { + "type": + "string", + "description": "Type: List of `string`, example: `Standard`, multiple_sep: `\";\"`. a string of desired SAM attributes, in the order desired for the output SAM", + "help_text": "Type: List of `string`, example: `Standard`, multiple_sep: `\";\"`. a string of desired SAM attributes, in the order desired for the output SAM. Tags can be listed in any combination/order.\n\n***Presets:\n- None ... no attributes\n- Standard ... NH HI AS nM\n- All ... NH HI AS nM NM MD jM jI MC ch\n***Alignment:\n- NH ... number of loci the reads maps to: =1 for unique mappers, \u003e1 for multimappers. Standard SAM tag.\n- HI ... multiple alignment index, starts with --out_sam_attr_ih_start (=1 by default). Standard SAM tag.\n- AS ... local alignment score, +1/-1 for matches/mismateches, score* penalties for indels and gaps. For PE reads, total score for two mates. Stadnard SAM tag.\n- nM ... number of mismatches. For PE reads, sum over two mates.\n- NM ... edit distance to the reference (number of mismatched + inserted + deleted bases) for each mate. Standard SAM tag.\n- MD ... string encoding mismatched and deleted reference bases (see standard SAM specifications). Standard SAM tag.\n- jM ... intron motifs for all junctions (i.e. N in CIGAR): 0: non-canonical; 1: GT/AG, 2: CT/AC, 3: GC/AG, 4: CT/GC, 5: AT/AC, 6: GT/AT. If splice junctions database is used, and a junction is annotated, 20 is added to its motif value.\n- jI ... start and end of introns for all junctions (1-based).\n- XS ... alignment strand according to --out_sam_strand_field.\n- MC ... mate\u0027s CIGAR string. Standard SAM tag.\n- ch ... marks all segment of all chimeric alingments for --chim_out_type WithinBAM output.\n- cN ... number of bases clipped from the read ends: 5\u0027 and 3\u0027\n***Variation:\n- vA ... variant allele\n- vG ... genomic coordinate of the variant overlapped by the read.\n- vW ... 1 - alignment passes WASP filtering; 2,3,4,5,6,7 - alignment does not pass WASP filtering. Requires --wasp_output_mode SAMtag.\n- ha ... haplotype (1/2) when mapping to the diploid genome. Requires genome generated with --genomeTransformType Diploid .\n***STARsolo:\n- CR CY UR UY ... sequences and quality scores of cell barcodes and UMIs for the solo* demultiplexing.\n- GX GN ... gene ID and gene name for unique-gene reads.\n- gx gn ... gene IDs and gene names for unique- and multi-gene reads.\n- CB UB ... error-corrected cell barcodes and UMIs for solo* demultiplexing. Requires --out_sam_type BAM SortedByCoordinate.\n- sM ... assessment of CB and UMI.\n- sS ... sequence of the entire barcode (CB,UMI,adapter).\n- sQ ... quality of the entire barcode.\n- sF ... type of feature overlap and number of features for each alignment\n***Unsupported/undocumented:\n- rB ... alignment block read/genomic coordinates.\n- vR ... read coordinate of the variant." + + } + + + , + "out_sam_attr_ih_start": { + "type": + "integer", + "description": "Type: `integer`, example: `1`. start value for the IH attribute", + "help_text": "Type: `integer`, example: `1`. start value for the IH attribute. 0 may be required by some downstream software, such as Cufflinks or StringTie." + + } + + + , + "out_sam_unmapped": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. output of unmapped reads in the SAM format\n\n1st word:\n- None ", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. output of unmapped reads in the SAM format\n\n1st word:\n- None ... no output\n- Within ... output unmapped reads within the main SAM file (i.e. Aligned.out.sam)\n2nd word:\n- KeepPairs ... record unmapped mate for each alignment, and, in case of unsorted output, keep it adjacent to its mapped mate. Only affects multi-mapping reads." + + } + + + , + "out_sam_order": { + "type": + "string", + "description": "Type: `string`, example: `Paired`. type of sorting for the SAM output\n\nPaired: one mate after the other for all paired alignments\nPairedKeepInputOrder: one mate after the other for all paired alignments, the order is kept the same as in the input FASTQ files", + "help_text": "Type: `string`, example: `Paired`. type of sorting for the SAM output\n\nPaired: one mate after the other for all paired alignments\nPairedKeepInputOrder: one mate after the other for all paired alignments, the order is kept the same as in the input FASTQ files" + + } + + + , + "out_sam_primary_flag": { + "type": + "string", + "description": "Type: `string`, example: `OneBestScore`. which alignments are considered primary - all others will be marked with 0x100 bit in the FLAG\n\n- OneBestScore ", + "help_text": "Type: `string`, example: `OneBestScore`. which alignments are considered primary - all others will be marked with 0x100 bit in the FLAG\n\n- OneBestScore ... only one alignment with the best score is primary\n- AllBestScore ... all alignments with the best score are primary" + + } + + + , + "out_sam_read_id": { + "type": + "string", + "description": "Type: `string`, example: `Standard`. read ID record type\n\n- Standard ", + "help_text": "Type: `string`, example: `Standard`. read ID record type\n\n- Standard ... first word (until space) from the FASTx read ID line, removing /1,/2 from the end\n- Number ... read number (index) in the FASTx file" + + } + + + , + "out_sam_mapq_unique": { + "type": + "integer", + "description": "Type: `integer`, example: `255`. 0 to 255: the MAPQ value for unique mappers", + "help_text": "Type: `integer`, example: `255`. 0 to 255: the MAPQ value for unique mappers" + + } + + + , + "out_sam_flag_or": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. 0 to 65535: sam FLAG will be bitwise OR\u0027d with this value, i", + "help_text": "Type: `integer`, example: `0`. 0 to 65535: sam FLAG will be bitwise OR\u0027d with this value, i.e. FLAG=FLAG | outSAMflagOR. This is applied after all flags have been set by STAR, and after outSAMflagAND. Can be used to set specific bits that are not set otherwise." + + } + + + , + "out_sam_flag_and": { + "type": + "integer", + "description": "Type: `integer`, example: `65535`. 0 to 65535: sam FLAG will be bitwise AND\u0027d with this value, i", + "help_text": "Type: `integer`, example: `65535`. 0 to 65535: sam FLAG will be bitwise AND\u0027d with this value, i.e. FLAG=FLAG \u0026 outSAMflagOR. This is applied after all flags have been set by STAR, but before outSAMflagOR. Can be used to unset specific bits that are not set otherwise." + + } + + + , + "out_sam_attr_rg_line": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. SAM/BAM read group line", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. SAM/BAM read group line. The first word contains the read group identifier and must start with \"ID:\", e.g. --out_sam_attr_rg_line ID:xxx CN:yy \"DS:z z z\".\n\nxxx will be added as RG tag to each output alignment. Any spaces in the tag values have to be double quoted.\nComma separated RG lines correspons to different (comma separated) input files in --readFilesIn. Commas have to be surrounded by spaces, e.g.\n--out_sam_attr_rg_line ID:xxx , ID:zzz \"DS:z z\" , ID:yyy DS:yyyy" + + } + + + , + "out_sam_header_hd": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. @HD (header) line of the SAM header", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. @HD (header) line of the SAM header" + + } + + + , + "out_sam_header_pg": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. extra @PG (software) line of the SAM header (in addition to STAR)", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. extra @PG (software) line of the SAM header (in addition to STAR)" + + } + + + , + "out_sam_header_comment_file": { + "type": + "string", + "description": "Type: `string`. path to the file with @CO (comment) lines of the SAM header", + "help_text": "Type: `string`. path to the file with @CO (comment) lines of the SAM header" + + } + + + , + "out_sam_filter": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. filter the output into main SAM/BAM files\n\n- KeepOnlyAddedReferences ", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. filter the output into main SAM/BAM files\n\n- KeepOnlyAddedReferences ... only keep the reads for which all alignments are to the extra reference sequences added with --genome_fasta_files at the mapping stage.\n- KeepAllAddedReferences ... keep all alignments to the extra reference sequences added with --genome_fasta_files at the mapping stage." + + } + + + , + "out_sam_mult_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `-1`. max number of multiple alignments for a read that will be output to the SAM/BAM files", + "help_text": "Type: `integer`, example: `-1`. max number of multiple alignments for a read that will be output to the SAM/BAM files. Note that if this value is not equal to -1, the top scoring alignment will be output first\n\n- -1 ... all alignments (up to --out_filter_multimap_nmax) will be output" + + } + + + , + "out_sam_tlen": { + "type": + "integer", + "description": "Type: `integer`, example: `1`. calculation method for the TLEN field in the SAM/BAM files\n\n- 1 ", + "help_text": "Type: `integer`, example: `1`. calculation method for the TLEN field in the SAM/BAM files\n\n- 1 ... leftmost base of the (+)strand mate to rightmost base of the (-)mate. (+)sign for the (+)strand mate\n- 2 ... leftmost base of any mate to rightmost base of any mate. (+)sign for the mate with the leftmost base. This is different from 1 for overlapping mates with protruding ends" + + } + + + , + "out_bam_compression": { + "type": + "integer", + "description": "Type: `integer`, example: `1`. -1 to 10 BAM compression level, -1=default compression (6?), 0=no compression, 10=maximum compression", + "help_text": "Type: `integer`, example: `1`. -1 to 10 BAM compression level, -1=default compression (6?), 0=no compression, 10=maximum compression" + + } + + + , + "out_bam_sorting_thread_n": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. \u003e=0: number of threads for BAM sorting", + "help_text": "Type: `integer`, example: `0`. \u003e=0: number of threads for BAM sorting. 0 will default to min(6,--runThreadN)." + + } + + + , + "out_bam_sorting_bins_n": { + "type": + "integer", + "description": "Type: `integer`, example: `50`. \u003e0: number of genome bins for coordinate-sorting", + "help_text": "Type: `integer`, example: `50`. \u003e0: number of genome bins for coordinate-sorting" + + } + + +} +}, + + + "bam processing" : { + "title": "BAM processing", + "type": "object", + "description": "No description", + "properties": { + + + "bam_remove_duplicates_type": { + "type": + "string", + "description": "Type: `string`. mark duplicates in the BAM file, for now only works with (i) sorted BAM fed with inputBAMfile, and (ii) for paired-end alignments only\n\n- - ", + "help_text": "Type: `string`. mark duplicates in the BAM file, for now only works with (i) sorted BAM fed with inputBAMfile, and (ii) for paired-end alignments only\n\n- - ... no duplicate removal/marking\n- UniqueIdentical ... mark all multimappers, and duplicate unique mappers. The coordinates, FLAG, CIGAR must be identical\n- UniqueIdenticalNotMulti ... mark duplicate unique mappers but not multimappers." + + } + + + , + "bam_remove_duplicates_mate2bases_n": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. number of bases from the 5\u0027 of mate 2 to use in collapsing (e", + "help_text": "Type: `integer`, example: `0`. number of bases from the 5\u0027 of mate 2 to use in collapsing (e.g. for RAMPAGE)" + + } + + +} +}, + + + "output wiggle" : { + "title": "Output Wiggle", + "type": "object", + "description": "No description", + "properties": { + + + "out_wig_type": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. type of signal output, e", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. type of signal output, e.g. \"bedGraph\" OR \"bedGraph read1_5p\". Requires sorted BAM: --out_sam_type BAM SortedByCoordinate .\n\n1st word:\n- None ... no signal output\n- bedGraph ... bedGraph format\n- wiggle ... wiggle format\n2nd word:\n- read1_5p ... signal from only 5\u0027 of the 1st read, useful for CAGE/RAMPAGE etc\n- read2 ... signal from only 2nd read" + + } + + + , + "out_wig_strand": { + "type": + "string", + "description": "Type: `string`, example: `Stranded`. strandedness of wiggle/bedGraph output\n\n- Stranded ", + "help_text": "Type: `string`, example: `Stranded`. strandedness of wiggle/bedGraph output\n\n- Stranded ... separate strands, str1 and str2\n- Unstranded ... collapsed strands" + + } + + + , + "out_wig_references_prefix": { + "type": + "string", + "description": "Type: `string`. prefix matching reference names to include in the output wiggle file, e", + "help_text": "Type: `string`. prefix matching reference names to include in the output wiggle file, e.g. \"chr\", default \"-\" - include all references" + + } + + + , + "out_wig_norm": { + "type": + "string", + "description": "Type: `string`, example: `RPM`. type of normalization for the signal\n\n- RPM ", + "help_text": "Type: `string`, example: `RPM`. type of normalization for the signal\n\n- RPM ... reads per million of mapped reads\n- None ... no normalization, \"raw\" counts" + + } + + +} +}, + + + "output filtering" : { + "title": "Output Filtering", + "type": "object", + "description": "No description", + "properties": { + + + "out_filter_type": { + "type": + "string", + "description": "Type: `string`, example: `Normal`. type of filtering\n\n- Normal ", + "help_text": "Type: `string`, example: `Normal`. type of filtering\n\n- Normal ... standard filtering using only current alignment\n- BySJout ... keep only those reads that contain junctions that passed filtering into SJ.out.tab" + + } + + + , + "out_filter_multimap_score_range": { + "type": + "integer", + "description": "Type: `integer`, example: `1`. the score range below the maximum score for multimapping alignments", + "help_text": "Type: `integer`, example: `1`. the score range below the maximum score for multimapping alignments" + + } + + + , + "out_filter_multimap_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `10`. maximum number of loci the read is allowed to map to", + "help_text": "Type: `integer`, example: `10`. maximum number of loci the read is allowed to map to. Alignments (all of them) will be output only if the read maps to no more loci than this value.\n\nOtherwise no alignments will be output, and the read will be counted as \"mapped to too many loci\" in the Log.final.out ." + + } + + + , + "out_filter_mismatch_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `10`. alignment will be output only if it has no more mismatches than this value", + "help_text": "Type: `integer`, example: `10`. alignment will be output only if it has no more mismatches than this value." + + } + + + , + "out_filter_mismatch_nover_lmax": { + "type": + "number", + "description": "Type: `double`, example: `0.3`. alignment will be output only if its ratio of mismatches to *mapped* length is less than or equal to this value", + "help_text": "Type: `double`, example: `0.3`. alignment will be output only if its ratio of mismatches to *mapped* length is less than or equal to this value." + + } + + + , + "out_filter_mismatch_nover_read_lmax": { + "type": + "number", + "description": "Type: `double`, example: `1.0`. alignment will be output only if its ratio of mismatches to *read* length is less than or equal to this value", + "help_text": "Type: `double`, example: `1.0`. alignment will be output only if its ratio of mismatches to *read* length is less than or equal to this value." + + } + + + , + "out_filter_score_min": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. alignment will be output only if its score is higher than or equal to this value", + "help_text": "Type: `integer`, example: `0`. alignment will be output only if its score is higher than or equal to this value." + + } + + + , + "out_filter_score_min_over_lread": { + "type": + "number", + "description": "Type: `double`, example: `0.66`. same as outFilterScoreMin, but normalized to read length (sum of mates\u0027 lengths for paired-end reads)", + "help_text": "Type: `double`, example: `0.66`. same as outFilterScoreMin, but normalized to read length (sum of mates\u0027 lengths for paired-end reads)" + + } + + + , + "out_filter_match_nmin": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. alignment will be output only if the number of matched bases is higher than or equal to this value", + "help_text": "Type: `integer`, example: `0`. alignment will be output only if the number of matched bases is higher than or equal to this value." + + } + + + , + "out_filter_match_nmin_over_lread": { + "type": + "number", + "description": "Type: `double`, example: `0.66`. sam as outFilterMatchNmin, but normalized to the read length (sum of mates\u0027 lengths for paired-end reads)", + "help_text": "Type: `double`, example: `0.66`. sam as outFilterMatchNmin, but normalized to the read length (sum of mates\u0027 lengths for paired-end reads)." + + } + + + , + "out_filter_intron_motifs": { + "type": + "string", + "description": "Type: `string`. filter alignment using their motifs\n\n- None ", + "help_text": "Type: `string`. filter alignment using their motifs\n\n- None ... no filtering\n- RemoveNoncanonical ... filter out alignments that contain non-canonical junctions\n- RemoveNoncanonicalUnannotated ... filter out alignments that contain non-canonical unannotated junctions when using annotated splice junctions database. The annotated non-canonical junctions will be kept." + + } + + + , + "out_filter_intron_strands": { + "type": + "string", + "description": "Type: `string`, example: `RemoveInconsistentStrands`. filter alignments\n\n- RemoveInconsistentStrands ", + "help_text": "Type: `string`, example: `RemoveInconsistentStrands`. filter alignments\n\n- RemoveInconsistentStrands ... remove alignments that have junctions with inconsistent strands\n- None ... no filtering" + + } + + +} +}, + + + "output splice junctions (sj.out.tab)" : { + "title": "Output splice junctions (SJ.out.tab)", + "type": "object", + "description": "No description", + "properties": { + + + "out_sj_type": { + "type": + "string", + "description": "Type: `string`, example: `Standard`. type of splice junction output\n\n- Standard ", + "help_text": "Type: `string`, example: `Standard`. type of splice junction output\n\n- Standard ... standard SJ.out.tab output\n- None ... no splice junction output" + + } + + +} +}, + + + "output filtering: splice junctions" : { + "title": "Output Filtering: Splice Junctions", + "type": "object", + "description": "No description", + "properties": { + + + "out_sj_filter_reads": { + "type": + "string", + "description": "Type: `string`, example: `All`. which reads to consider for collapsed splice junctions output\n\n- All ", + "help_text": "Type: `string`, example: `All`. which reads to consider for collapsed splice junctions output\n\n- All ... all reads, unique- and multi-mappers\n- Unique ... uniquely mapping reads only" + + } + + + , + "out_sj_filter_overhang_min": { + "type": + "string", + "description": "Type: List of `integer`, example: `30;12;12;12`, multiple_sep: `\";\"`. minimum overhang length for splice junctions on both sides for: (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif", + "help_text": "Type: List of `integer`, example: `30;12;12;12`, multiple_sep: `\";\"`. minimum overhang length for splice junctions on both sides for: (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif. -1 means no output for that motif\n\ndoes not apply to annotated junctions" + + } + + + , + "out_sj_filter_count_unique_min": { + "type": + "string", + "description": "Type: List of `integer`, example: `3;1;1;1`, multiple_sep: `\";\"`. minimum uniquely mapping read count per junction for: (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif", + "help_text": "Type: List of `integer`, example: `3;1;1;1`, multiple_sep: `\";\"`. minimum uniquely mapping read count per junction for: (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif. -1 means no output for that motif\n\nJunctions are output if one of outSJfilterCountUniqueMin OR outSJfilterCountTotalMin conditions are satisfied\ndoes not apply to annotated junctions" + + } + + + , + "out_sj_filter_count_total_min": { + "type": + "string", + "description": "Type: List of `integer`, example: `3;1;1;1`, multiple_sep: `\";\"`. minimum total (multi-mapping+unique) read count per junction for: (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif", + "help_text": "Type: List of `integer`, example: `3;1;1;1`, multiple_sep: `\";\"`. minimum total (multi-mapping+unique) read count per junction for: (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif. -1 means no output for that motif\n\nJunctions are output if one of outSJfilterCountUniqueMin OR outSJfilterCountTotalMin conditions are satisfied\ndoes not apply to annotated junctions" + + } + + + , + "out_sj_filter_dist_to_other_sj_min": { + "type": + "string", + "description": "Type: List of `integer`, example: `10;0;5;10`, multiple_sep: `\";\"`. minimum allowed distance to other junctions\u0027 donor/acceptor\n\ndoes not apply to annotated junctions", + "help_text": "Type: List of `integer`, example: `10;0;5;10`, multiple_sep: `\";\"`. minimum allowed distance to other junctions\u0027 donor/acceptor\n\ndoes not apply to annotated junctions" + + } + + + , + "out_sj_filter_intron_max_vs_read_n": { + "type": + "string", + "description": "Type: List of `integer`, example: `50000;100000;200000`, multiple_sep: `\";\"`. maximum gap allowed for junctions supported by 1,2,3,,,N reads\n\ni", + "help_text": "Type: List of `integer`, example: `50000;100000;200000`, multiple_sep: `\";\"`. maximum gap allowed for junctions supported by 1,2,3,,,N reads\n\ni.e. by default junctions supported by 1 read can have gaps \u003c=50000b, by 2 reads: \u003c=100000b, by 3 reads: \u003c=200000. by \u003e=4 reads any gap \u003c=alignIntronMax\ndoes not apply to annotated junctions" + + } + + +} +}, + + + "scoring" : { + "title": "Scoring", + "type": "object", + "description": "No description", + "properties": { + + + "score_gap": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. splice junction penalty (independent on intron motif)", + "help_text": "Type: `integer`, example: `0`. splice junction penalty (independent on intron motif)" + + } + + + , + "score_gap_noncan": { + "type": + "integer", + "description": "Type: `integer`, example: `-8`. non-canonical junction penalty (in addition to scoreGap)", + "help_text": "Type: `integer`, example: `-8`. non-canonical junction penalty (in addition to scoreGap)" + + } + + + , + "score_gap_gcag": { + "type": + "integer", + "description": "Type: `integer`, example: `-4`. GC/AG and CT/GC junction penalty (in addition to scoreGap)", + "help_text": "Type: `integer`, example: `-4`. GC/AG and CT/GC junction penalty (in addition to scoreGap)" + + } + + + , + "score_gap_atac": { + "type": + "integer", + "description": "Type: `integer`, example: `-8`. AT/AC and GT/AT junction penalty (in addition to scoreGap)", + "help_text": "Type: `integer`, example: `-8`. AT/AC and GT/AT junction penalty (in addition to scoreGap)" + + } + + + , + "score_genomic_length_log2scale": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. extra score logarithmically scaled with genomic length of the alignment: scoreGenomicLengthLog2scale*log2(genomicLength)", + "help_text": "Type: `integer`, example: `0`. extra score logarithmically scaled with genomic length of the alignment: scoreGenomicLengthLog2scale*log2(genomicLength)" + + } + + + , + "score_del_open": { + "type": + "integer", + "description": "Type: `integer`, example: `-2`. deletion open penalty", + "help_text": "Type: `integer`, example: `-2`. deletion open penalty" + + } + + + , + "score_del_base": { + "type": + "integer", + "description": "Type: `integer`, example: `-2`. deletion extension penalty per base (in addition to scoreDelOpen)", + "help_text": "Type: `integer`, example: `-2`. deletion extension penalty per base (in addition to scoreDelOpen)" + + } + + + , + "score_ins_open": { + "type": + "integer", + "description": "Type: `integer`, example: `-2`. insertion open penalty", + "help_text": "Type: `integer`, example: `-2`. insertion open penalty" + + } + + + , + "score_ins_base": { + "type": + "integer", + "description": "Type: `integer`, example: `-2`. insertion extension penalty per base (in addition to scoreInsOpen)", + "help_text": "Type: `integer`, example: `-2`. insertion extension penalty per base (in addition to scoreInsOpen)" + + } + + + , + "score_stitch_sj_shift": { + "type": + "integer", + "description": "Type: `integer`, example: `1`. maximum score reduction while searching for SJ boundaries in the stitching step", + "help_text": "Type: `integer`, example: `1`. maximum score reduction while searching for SJ boundaries in the stitching step" + + } + + +} +}, + + + "alignments and seeding" : { + "title": "Alignments and Seeding", + "type": "object", + "description": "No description", + "properties": { + + + "seed_search_start_lmax": { + "type": + "integer", + "description": "Type: `integer`, example: `50`. defines the search start point through the read - the read is split into pieces no longer than this value", + "help_text": "Type: `integer`, example: `50`. defines the search start point through the read - the read is split into pieces no longer than this value" + + } + + + , + "seed_search_start_lmax_over_lread": { + "type": + "number", + "description": "Type: `double`, example: `1.0`. seedSearchStartLmax normalized to read length (sum of mates\u0027 lengths for paired-end reads)", + "help_text": "Type: `double`, example: `1.0`. seedSearchStartLmax normalized to read length (sum of mates\u0027 lengths for paired-end reads)" + + } + + + , + "seed_search_lmax": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. defines the maximum length of the seeds, if =0 seed length is not limited", + "help_text": "Type: `integer`, example: `0`. defines the maximum length of the seeds, if =0 seed length is not limited" + + } + + + , + "seed_multimap_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `10000`. only pieces that map fewer than this value are utilized in the stitching procedure", + "help_text": "Type: `integer`, example: `10000`. only pieces that map fewer than this value are utilized in the stitching procedure" + + } + + + , + "seed_per_read_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `1000`. max number of seeds per read", + "help_text": "Type: `integer`, example: `1000`. max number of seeds per read" + + } + + + , + "seed_per_window_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `50`. max number of seeds per window", + "help_text": "Type: `integer`, example: `50`. max number of seeds per window" + + } + + + , + "seed_none_loci_per_window": { + "type": + "integer", + "description": "Type: `integer`, example: `10`. max number of one seed loci per window", + "help_text": "Type: `integer`, example: `10`. max number of one seed loci per window" + + } + + + , + "seed_split_min": { + "type": + "integer", + "description": "Type: `integer`, example: `12`. min length of the seed sequences split by Ns or mate gap", + "help_text": "Type: `integer`, example: `12`. min length of the seed sequences split by Ns or mate gap" + + } + + + , + "seed_map_min": { + "type": + "integer", + "description": "Type: `integer`, example: `5`. min length of seeds to be mapped", + "help_text": "Type: `integer`, example: `5`. min length of seeds to be mapped" + + } + + + , + "align_intron_min": { + "type": + "integer", + "description": "Type: `integer`, example: `21`. minimum intron size, genomic gap is considered intron if its length\u003e=alignIntronMin, otherwise it is considered Deletion", + "help_text": "Type: `integer`, example: `21`. minimum intron size, genomic gap is considered intron if its length\u003e=alignIntronMin, otherwise it is considered Deletion" + + } + + + , + "align_intron_max": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. maximum intron size, if 0, max intron size will be determined by (2^winBinNbits)*winAnchorDistNbins", + "help_text": "Type: `integer`, example: `0`. maximum intron size, if 0, max intron size will be determined by (2^winBinNbits)*winAnchorDistNbins" + + } + + + , + "align_mates_gap_max": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. maximum gap between two mates, if 0, max intron gap will be determined by (2^winBinNbits)*winAnchorDistNbins", + "help_text": "Type: `integer`, example: `0`. maximum gap between two mates, if 0, max intron gap will be determined by (2^winBinNbits)*winAnchorDistNbins" + + } + + + , + "align_sj_overhang_min": { + "type": + "integer", + "description": "Type: `integer`, example: `5`. minimum overhang (i", + "help_text": "Type: `integer`, example: `5`. minimum overhang (i.e. block size) for spliced alignments" + + } + + + , + "align_sj_stitch_mismatch_nmax": { + "type": + "string", + "description": "Type: List of `integer`, example: `0;-1;0;0`, multiple_sep: `\";\"`. maximum number of mismatches for stitching of the splice junctions (-1: no limit)", + "help_text": "Type: List of `integer`, example: `0;-1;0;0`, multiple_sep: `\";\"`. maximum number of mismatches for stitching of the splice junctions (-1: no limit).\n\n(1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif." + + } + + + , + "align_sjdb_overhang_min": { + "type": + "integer", + "description": "Type: `integer`, example: `3`. minimum overhang (i", + "help_text": "Type: `integer`, example: `3`. minimum overhang (i.e. block size) for annotated (sjdb) spliced alignments" + + } + + + , + "align_spliced_mate_map_lmin": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. minimum mapped length for a read mate that is spliced", + "help_text": "Type: `integer`, example: `0`. minimum mapped length for a read mate that is spliced" + + } + + + , + "align_spliced_mate_map_lmin_over_lmate": { + "type": + "number", + "description": "Type: `double`, example: `0.66`. alignSplicedMateMapLmin normalized to mate length", + "help_text": "Type: `double`, example: `0.66`. alignSplicedMateMapLmin normalized to mate length" + + } + + + , + "align_windows_per_read_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `10000`. max number of windows per read", + "help_text": "Type: `integer`, example: `10000`. max number of windows per read" + + } + + + , + "align_transcripts_per_window_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `100`. max number of transcripts per window", + "help_text": "Type: `integer`, example: `100`. max number of transcripts per window" + + } + + + , + "align_transcripts_per_read_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `10000`. max number of different alignments per read to consider", + "help_text": "Type: `integer`, example: `10000`. max number of different alignments per read to consider" + + } + + + , + "align_ends_type": { + "type": + "string", + "description": "Type: `string`, example: `Local`. type of read ends alignment\n\n- Local ", + "help_text": "Type: `string`, example: `Local`. type of read ends alignment\n\n- Local ... standard local alignment with soft-clipping allowed\n- EndToEnd ... force end-to-end read alignment, do not soft-clip\n- Extend5pOfRead1 ... fully extend only the 5p of the read1, all other ends: local alignment\n- Extend5pOfReads12 ... fully extend only the 5p of the both read1 and read2, all other ends: local alignment" + + } + + + , + "align_ends_protrude": { + "type": + "string", + "description": "Type: `string`, example: `0 ConcordantPair`. allow protrusion of alignment ends, i", + "help_text": "Type: `string`, example: `0 ConcordantPair`. allow protrusion of alignment ends, i.e. start (end) of the +strand mate downstream of the start (end) of the -strand mate\n\n1st word: int: maximum number of protrusion bases allowed\n2nd word: string:\n- ConcordantPair ... report alignments with non-zero protrusion as concordant pairs\n- DiscordantPair ... report alignments with non-zero protrusion as discordant pairs" + + } + + + , + "align_soft_clip_at_reference_ends": { + "type": + "string", + "description": "Type: `string`, example: `Yes`. allow the soft-clipping of the alignments past the end of the chromosomes\n\n- Yes ", + "help_text": "Type: `string`, example: `Yes`. allow the soft-clipping of the alignments past the end of the chromosomes\n\n- Yes ... allow\n- No ... prohibit, useful for compatibility with Cufflinks" + + } + + + , + "align_insertion_flush": { + "type": + "string", + "description": "Type: `string`. how to flush ambiguous insertion positions\n\n- None ", + "help_text": "Type: `string`. how to flush ambiguous insertion positions\n\n- None ... insertions are not flushed\n- Right ... insertions are flushed to the right" + + } + + +} +}, + + + "paired-end reads" : { + "title": "Paired-End reads", + "type": "object", + "description": "No description", + "properties": { + + + "pe_overlap_nbases_min": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. minimum number of overlapping bases to trigger mates merging and realignment", + "help_text": "Type: `integer`, example: `0`. minimum number of overlapping bases to trigger mates merging and realignment. Specify \u003e0 value to switch on the \"merginf of overlapping mates\" algorithm." + + } + + + , + "pe_overlap_mm_p": { + "type": + "number", + "description": "Type: `double`, example: `0.01`. maximum proportion of mismatched bases in the overlap area", + "help_text": "Type: `double`, example: `0.01`. maximum proportion of mismatched bases in the overlap area" + + } + + +} +}, + + + "windows, anchors, binning" : { + "title": "Windows, Anchors, Binning", + "type": "object", + "description": "No description", + "properties": { + + + "win_anchor_multimap_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `50`. max number of loci anchors are allowed to map to", + "help_text": "Type: `integer`, example: `50`. max number of loci anchors are allowed to map to" + + } + + + , + "win_bin_nbits": { + "type": + "integer", + "description": "Type: `integer`, example: `16`. =log2(winBin), where winBin is the size of the bin for the windows/clustering, each window will occupy an integer number of bins", + "help_text": "Type: `integer`, example: `16`. =log2(winBin), where winBin is the size of the bin for the windows/clustering, each window will occupy an integer number of bins." + + } + + + , + "win_anchor_dist_nbins": { + "type": + "integer", + "description": "Type: `integer`, example: `9`. max number of bins between two anchors that allows aggregation of anchors into one window", + "help_text": "Type: `integer`, example: `9`. max number of bins between two anchors that allows aggregation of anchors into one window" + + } + + + , + "win_flank_nbins": { + "type": + "integer", + "description": "Type: `integer`, example: `4`. log2(winFlank), where win Flank is the size of the left and right flanking regions for each window", + "help_text": "Type: `integer`, example: `4`. log2(winFlank), where win Flank is the size of the left and right flanking regions for each window" + + } + + + , + "win_read_coverage_relative_min": { + "type": + "number", + "description": "Type: `double`, example: `0.5`. minimum relative coverage of the read sequence by the seeds in a window, for STARlong algorithm only", + "help_text": "Type: `double`, example: `0.5`. minimum relative coverage of the read sequence by the seeds in a window, for STARlong algorithm only." + + } + + + , + "win_read_coverage_bases_min": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. minimum number of bases covered by the seeds in a window , for STARlong algorithm only", + "help_text": "Type: `integer`, example: `0`. minimum number of bases covered by the seeds in a window , for STARlong algorithm only." + + } + + +} +}, + + + "chimeric alignments" : { + "title": "Chimeric Alignments", + "type": "object", + "description": "No description", + "properties": { + + + "chim_out_type": { + "type": + "string", + "description": "Type: List of `string`, example: `Junctions`, multiple_sep: `\";\"`. type of chimeric output\n\n- Junctions ", + "help_text": "Type: List of `string`, example: `Junctions`, multiple_sep: `\";\"`. type of chimeric output\n\n- Junctions ... Chimeric.out.junction\n- SeparateSAMold ... output old SAM into separate Chimeric.out.sam file\n- WithinBAM ... output into main aligned BAM files (Aligned.*.bam)\n- WithinBAM HardClip ... (default) hard-clipping in the CIGAR for supplemental chimeric alignments (default if no 2nd word is present)\n- WithinBAM SoftClip ... soft-clipping in the CIGAR for supplemental chimeric alignments" + + } + + + , + "chim_segment_min": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. minimum length of chimeric segment length, if ==0, no chimeric output", + "help_text": "Type: `integer`, example: `0`. minimum length of chimeric segment length, if ==0, no chimeric output" + + } + + + , + "chim_score_min": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. minimum total (summed) score of the chimeric segments", + "help_text": "Type: `integer`, example: `0`. minimum total (summed) score of the chimeric segments" + + } + + + , + "chim_score_drop_max": { + "type": + "integer", + "description": "Type: `integer`, example: `20`. max drop (difference) of chimeric score (the sum of scores of all chimeric segments) from the read length", + "help_text": "Type: `integer`, example: `20`. max drop (difference) of chimeric score (the sum of scores of all chimeric segments) from the read length" + + } + + + , + "chim_score_separation": { + "type": + "integer", + "description": "Type: `integer`, example: `10`. minimum difference (separation) between the best chimeric score and the next one", + "help_text": "Type: `integer`, example: `10`. minimum difference (separation) between the best chimeric score and the next one" + + } + + + , + "chim_score_junction_non_gtag": { + "type": + "integer", + "description": "Type: `integer`, example: `-1`. penalty for a non-GT/AG chimeric junction", + "help_text": "Type: `integer`, example: `-1`. penalty for a non-GT/AG chimeric junction" + + } + + + , + "chim_junction_overhang_min": { + "type": + "integer", + "description": "Type: `integer`, example: `20`. minimum overhang for a chimeric junction", + "help_text": "Type: `integer`, example: `20`. minimum overhang for a chimeric junction" + + } + + + , + "chim_segment_read_gap_max": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. maximum gap in the read sequence between chimeric segments", + "help_text": "Type: `integer`, example: `0`. maximum gap in the read sequence between chimeric segments" + + } + + + , + "chim_filter": { + "type": + "string", + "description": "Type: List of `string`, example: `banGenomicN`, multiple_sep: `\";\"`. different filters for chimeric alignments\n\n- None ", + "help_text": "Type: List of `string`, example: `banGenomicN`, multiple_sep: `\";\"`. different filters for chimeric alignments\n\n- None ... no filtering\n- banGenomicN ... Ns are not allowed in the genome sequence around the chimeric junction" + + } + + + , + "chim_main_segment_mult_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `10`. maximum number of multi-alignments for the main chimeric segment", + "help_text": "Type: `integer`, example: `10`. maximum number of multi-alignments for the main chimeric segment. =1 will prohibit multimapping main segments." + + } + + + , + "chim_multimap_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. maximum number of chimeric multi-alignments\n\n- 0 ", + "help_text": "Type: `integer`, example: `0`. maximum number of chimeric multi-alignments\n\n- 0 ... use the old scheme for chimeric detection which only considered unique alignments" + + } + + + , + "chim_multimap_score_range": { + "type": + "integer", + "description": "Type: `integer`, example: `1`. the score range for multi-mapping chimeras below the best chimeric score", + "help_text": "Type: `integer`, example: `1`. the score range for multi-mapping chimeras below the best chimeric score. Only works with --chim_multimap_nmax \u003e 1" + + } + + + , + "chim_nonchim_score_drop_min": { + "type": + "integer", + "description": "Type: `integer`, example: `20`. to trigger chimeric detection, the drop in the best non-chimeric alignment score with respect to the read length has to be greater than this value", + "help_text": "Type: `integer`, example: `20`. to trigger chimeric detection, the drop in the best non-chimeric alignment score with respect to the read length has to be greater than this value" + + } + + + , + "chim_out_junction_format": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. formatting type for the Chimeric", + "help_text": "Type: `integer`, example: `0`. formatting type for the Chimeric.out.junction file\n\n- 0 ... no comment lines/headers\n- 1 ... comment lines at the end of the file: command line and Nreads: total, unique/multi-mapping" + + } + + +} +}, + + + "quantification of annotations" : { + "title": "Quantification of Annotations", + "type": "object", + "description": "No description", + "properties": { + + + "quant_mode": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. types of quantification requested\n\n- - ", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. types of quantification requested\n\n- - ... none\n- TranscriptomeSAM ... output SAM/BAM alignments to transcriptome into a separate file\n- GeneCounts ... count reads per gene" + + } + + + , + "quant_transcriptome_bam_compression": { + "type": + "integer", + "description": "Type: `integer`, example: `1`. -2 to 10 transcriptome BAM compression level\n\n- -2 ", + "help_text": "Type: `integer`, example: `1`. -2 to 10 transcriptome BAM compression level\n\n- -2 ... no BAM output\n- -1 ... default compression (6?)\n- 0 ... no compression\n- 10 ... maximum compression" + + } + + + , + "quant_transcriptome_sam_output": { + "type": + "string", + "description": "Type: `string`, example: `BanSingleEnd_BanIndels_ExtendSoftclip`. alignment filtering for TranscriptomeSAM output\n\n- BanSingleEnd_BanIndels_ExtendSoftclip ", + "help_text": "Type: `string`, example: `BanSingleEnd_BanIndels_ExtendSoftclip`. alignment filtering for TranscriptomeSAM output\n\n- BanSingleEnd_BanIndels_ExtendSoftclip ... prohibit indels and single-end alignments, extend softclips - compatible with RSEM\n- BanSingleEnd ... prohibit single-end alignments, allow indels and softclips\n- BanSingleEnd_ExtendSoftclip ... prohibit single-end alignments, extend softclips, allow indels" + + } + + +} +}, + + + "2-pass mapping" : { + "title": "2-pass Mapping", + "type": "object", + "description": "No description", + "properties": { + + + "twopass_mode": { + "type": + "string", + "description": "Type: `string`. 2-pass mapping mode", + "help_text": "Type: `string`. 2-pass mapping mode.\n\n- None ... 1-pass mapping\n- Basic ... basic 2-pass mapping, with all 1st pass junctions inserted into the genome indices on the fly" + + } + + + , + "twopass1reads_n": { + "type": + "integer", + "description": "Type: `integer`, example: `-1`. number of reads to process for the 1st step", + "help_text": "Type: `integer`, example: `-1`. number of reads to process for the 1st step. Use very large number (or default -1) to map all reads in the first step." + + } + + +} +}, + + + "wasp parameters" : { + "title": "WASP parameters", + "type": "object", + "description": "No description", + "properties": { + + + "wasp_output_mode": { + "type": + "string", + "description": "Type: `string`. WASP allele-specific output type", + "help_text": "Type: `string`. WASP allele-specific output type. This is re-implementation of the original WASP mappability filtering by Bryce van de Geijn, Graham McVicker, Yoav Gilad \u0026 Jonathan K Pritchard. Please cite the original WASP paper: Nature Methods 12, 1061-1063 (2015), https://www.nature.com/articles/nmeth.3582 .\n\n- SAMtag ... add WASP tags to the alignments that pass WASP filtering" + + } + + +} +}, + + + "starsolo (single cell rna-seq) parameters" : { + "title": "STARsolo (single cell RNA-seq) parameters", + "type": "object", + "description": "No description", + "properties": { + + + "solo_type": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. type of single-cell RNA-seq\n\n- CB_UMI_Simple ", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. type of single-cell RNA-seq\n\n- CB_UMI_Simple ... (a.k.a. Droplet) one UMI and one Cell Barcode of fixed length in read2, e.g. Drop-seq and 10X Chromium.\n- CB_UMI_Complex ... multiple Cell Barcodes of varying length, one UMI of fixed length and one adapter sequence of fixed length are allowed in read2 only (e.g. inDrop, ddSeq).\n- CB_samTagOut ... output Cell Barcode as CR and/or CB SAm tag. No UMI counting. --readFilesIn cDNA_read1 [cDNA_read2 if paired-end] CellBarcode_read . Requires --out_sam_type BAM Unsorted [and/or SortedByCoordinate]\n- SmartSeq ... Smart-seq: each cell in a separate FASTQ (paired- or single-end), barcodes are corresponding read-groups, no UMI sequences, alignments deduplicated according to alignment start and end (after extending soft-clipped bases)" + + } + + + , + "solo_cb_type": { + "type": + "string", + "description": "Type: `string`, example: `Sequence`. cell barcode type\n\nSequence: cell barcode is a sequence (standard option)\nString: cell barcode is an arbitrary string", + "help_text": "Type: `string`, example: `Sequence`. cell barcode type\n\nSequence: cell barcode is a sequence (standard option)\nString: cell barcode is an arbitrary string" + + } + + + , + "solo_cb_whitelist": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. file(s) with whitelist(s) of cell barcodes", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. file(s) with whitelist(s) of cell barcodes. Only --solo_type CB_UMI_Complex allows more than one whitelist file.\n\n- None ... no whitelist: all cell barcodes are allowed" + + } + + + , + "solo_cb_start": { + "type": + "integer", + "description": "Type: `integer`, example: `1`. cell barcode start base", + "help_text": "Type: `integer`, example: `1`. cell barcode start base" + + } + + + , + "solo_cb_len": { + "type": + "integer", + "description": "Type: `integer`, example: `16`. cell barcode length", + "help_text": "Type: `integer`, example: `16`. cell barcode length" + + } + + + , + "solo_umi_start": { + "type": + "integer", + "description": "Type: `integer`, example: `17`. UMI start base", + "help_text": "Type: `integer`, example: `17`. UMI start base" + + } + + + , + "solo_umi_len": { + "type": + "integer", + "description": "Type: `integer`, example: `10`. UMI length", + "help_text": "Type: `integer`, example: `10`. UMI length" + + } + + + , + "solo_barcode_read_length": { + "type": + "integer", + "description": "Type: `integer`, example: `1`. length of the barcode read\n\n- 1 ", + "help_text": "Type: `integer`, example: `1`. length of the barcode read\n\n- 1 ... equal to sum of soloCBlen+soloUMIlen\n- 0 ... not defined, do not check" + + } + + + , + "solo_barcode_mate": { + "type": + "integer", + "description": "Type: `integer`, example: `0`. identifies which read mate contains the barcode (CB+UMI) sequence\n\n- 0 ", + "help_text": "Type: `integer`, example: `0`. identifies which read mate contains the barcode (CB+UMI) sequence\n\n- 0 ... barcode sequence is on separate read, which should always be the last file in the --readFilesIn listed\n- 1 ... barcode sequence is a part of mate 1\n- 2 ... barcode sequence is a part of mate 2" + + } + + + , + "solo_cb_position": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. position of Cell Barcode(s) on the barcode read", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. position of Cell Barcode(s) on the barcode read.\n\nPresently only works with --solo_type CB_UMI_Complex, and barcodes are assumed to be on Read2.\nFormat for each barcode: startAnchor_startPosition_endAnchor_endPosition\nstart(end)Anchor defines the Anchor Base for the CB: 0: read start; 1: read end; 2: adapter start; 3: adapter end\nstart(end)Position is the 0-based position with of the CB start(end) with respect to the Anchor Base\nString for different barcodes are separated by space.\nExample: inDrop (Zilionis et al, Nat. Protocols, 2017):\n--solo_cb_position 0_0_2_-1 3_1_3_8" + + } + + + , + "solo_umi_position": { + "type": + "string", + "description": "Type: `string`. position of the UMI on the barcode read, same as soloCBposition\n\nExample: inDrop (Zilionis et al, Nat", + "help_text": "Type: `string`. position of the UMI on the barcode read, same as soloCBposition\n\nExample: inDrop (Zilionis et al, Nat. Protocols, 2017):\n--solo_cb_position 3_9_3_14" + + } + + + , + "solo_adapter_sequence": { + "type": + "string", + "description": "Type: `string`. adapter sequence to anchor barcodes", + "help_text": "Type: `string`. adapter sequence to anchor barcodes. Only one adapter sequence is allowed." + + } + + + , + "solo_adapter_mismatches_nmax": { + "type": + "integer", + "description": "Type: `integer`, example: `1`. maximum number of mismatches allowed in adapter sequence", + "help_text": "Type: `integer`, example: `1`. maximum number of mismatches allowed in adapter sequence." + + } + + + , + "solo_cb_match_wl_type": { + "type": + "string", + "description": "Type: `string`, example: `1MM_multi`. matching the Cell Barcodes to the WhiteList\n\n- Exact ", + "help_text": "Type: `string`, example: `1MM_multi`. matching the Cell Barcodes to the WhiteList\n\n- Exact ... only exact matches allowed\n- 1MM ... only one match in whitelist with 1 mismatched base allowed. Allowed CBs have to have at least one read with exact match.\n- 1MM_multi ... multiple matches in whitelist with 1 mismatched base allowed, posterior probability calculation is used choose one of the matches.\nAllowed CBs have to have at least one read with exact match. This option matches best with CellRanger 2.2.0\n- 1MM_multi_pseudocounts ... same as 1MM_Multi, but pseudocounts of 1 are added to all whitelist barcodes.\n- 1MM_multi_Nbase_pseudocounts ... same as 1MM_multi_pseudocounts, multimatching to WL is allowed for CBs with N-bases. This option matches best with CellRanger \u003e= 3.0.0\n- EditDist_2 ... allow up to edit distance of 3 fpr each of the barcodes. May include one deletion + one insertion. Only works with --solo_type CB_UMI_Complex. Matches to multiple passlist barcdoes are not allowed. Similar to ParseBio Split-seq pipeline." + + } + + + , + "solo_input_sam_attr_barcode_seq": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. when inputting reads from a SAM file (--readsFileType SAM SE/PE), these SAM attributes mark the barcode sequence (in proper order)", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. when inputting reads from a SAM file (--readsFileType SAM SE/PE), these SAM attributes mark the barcode sequence (in proper order).\n\nFor instance, for 10X CellRanger or STARsolo BAMs, use --solo_input_sam_attr_barcode_seq CR UR .\nThis parameter is required when running STARsolo with input from SAM." + + } + + + , + "solo_input_sam_attr_barcode_qual": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. when inputting reads from a SAM file (--readsFileType SAM SE/PE), these SAM attributes mark the barcode qualities (in proper order)", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. when inputting reads from a SAM file (--readsFileType SAM SE/PE), these SAM attributes mark the barcode qualities (in proper order).\n\nFor instance, for 10X CellRanger or STARsolo BAMs, use --solo_input_sam_attr_barcode_qual CY UY .\nIf this parameter is \u0027-\u0027 (default), the quality \u0027H\u0027 will be assigned to all bases." + + } + + + , + "solo_strand": { + "type": + "string", + "description": "Type: `string`, example: `Forward`. strandedness of the solo libraries:\n\n- Unstranded ", + "help_text": "Type: `string`, example: `Forward`. strandedness of the solo libraries:\n\n- Unstranded ... no strand information\n- Forward ... read strand same as the original RNA molecule\n- Reverse ... read strand opposite to the original RNA molecule" + + } + + + , + "solo_features": { + "type": + "string", + "description": "Type: List of `string`, example: `Gene`, multiple_sep: `\";\"`. genomic features for which the UMI counts per Cell Barcode are collected\n\n- Gene ", + "help_text": "Type: List of `string`, example: `Gene`, multiple_sep: `\";\"`. genomic features for which the UMI counts per Cell Barcode are collected\n\n- Gene ... genes: reads match the gene transcript\n- SJ ... splice junctions: reported in SJ.out.tab\n- GeneFull ... full gene (pre-mRNA): count all reads overlapping genes\u0027 exons and introns\n- GeneFull_ExonOverIntron ... full gene (pre-mRNA): count all reads overlapping genes\u0027 exons and introns: prioritize 100% overlap with exons\n- GeneFull_Ex50pAS ... full gene (pre-RNA): count all reads overlapping genes\u0027 exons and introns: prioritize \u003e50% overlap with exons. Do not count reads with 100% exonic overlap in the antisense direction." + + } + + + , + "solo_multi_mappers": { + "type": + "string", + "description": "Type: List of `string`, example: `Unique`, multiple_sep: `\";\"`. counting method for reads mapping to multiple genes\n\n- Unique ", + "help_text": "Type: List of `string`, example: `Unique`, multiple_sep: `\";\"`. counting method for reads mapping to multiple genes\n\n- Unique ... count only reads that map to unique genes\n- Uniform ... uniformly distribute multi-genic UMIs to all genes\n- Rescue ... distribute UMIs proportionally to unique+uniform counts (~ first iteration of EM)\n- PropUnique ... distribute UMIs proportionally to unique mappers, if present, and uniformly if not.\n- EM ... multi-gene UMIs are distributed using Expectation Maximization algorithm" + + } + + + , + "solo_umi_dedup": { + "type": + "string", + "description": "Type: List of `string`, example: `1MM_All`, multiple_sep: `\";\"`. type of UMI deduplication (collapsing) algorithm\n\n- 1MM_All ", + "help_text": "Type: List of `string`, example: `1MM_All`, multiple_sep: `\";\"`. type of UMI deduplication (collapsing) algorithm\n\n- 1MM_All ... all UMIs with 1 mismatch distance to each other are collapsed (i.e. counted once).\n- 1MM_Directional_UMItools ... follows the \"directional\" method from the UMI-tools by Smith, Heger and Sudbery (Genome Research 2017).\n- 1MM_Directional ... same as 1MM_Directional_UMItools, but with more stringent criteria for duplicate UMIs\n- Exact ... only exactly matching UMIs are collapsed.\n- NoDedup ... no deduplication of UMIs, count all reads.\n- 1MM_CR ... CellRanger2-4 algorithm for 1MM UMI collapsing." + + } + + + , + "solo_umi_filtering": { + "type": + "string", + "description": "Type: List of `string`, multiple_sep: `\";\"`. type of UMI filtering (for reads uniquely mapping to genes)\n\n- - ", + "help_text": "Type: List of `string`, multiple_sep: `\";\"`. type of UMI filtering (for reads uniquely mapping to genes)\n\n- - ... basic filtering: remove UMIs with N and homopolymers (similar to CellRanger 2.2.0).\n- MultiGeneUMI ... basic + remove lower-count UMIs that map to more than one gene.\n- MultiGeneUMI_All ... basic + remove all UMIs that map to more than one gene.\n- MultiGeneUMI_CR ... basic + remove lower-count UMIs that map to more than one gene, matching CellRanger \u003e 3.0.0 .\nOnly works with --solo_umi_dedup 1MM_CR" + + } + + + , + "solo_out_file_names": { + "type": + "string", + "description": "Type: List of `string`, example: `Solo.out/;features.tsv;barcodes.tsv;matrix.mtx`, multiple_sep: `\";\"`. file names for STARsolo output:\n\nfile_name_prefix gene_names barcode_sequences cell_feature_count_matrix", + "help_text": "Type: List of `string`, example: `Solo.out/;features.tsv;barcodes.tsv;matrix.mtx`, multiple_sep: `\";\"`. file names for STARsolo output:\n\nfile_name_prefix gene_names barcode_sequences cell_feature_count_matrix" + + } + + + , + "solo_cell_filter": { + "type": + "string", + "description": "Type: List of `string`, example: `CellRanger2.2;3000;0.99;10`, multiple_sep: `\";\"`. cell filtering type and parameters\n\n- None ", + "help_text": "Type: List of `string`, example: `CellRanger2.2;3000;0.99;10`, multiple_sep: `\";\"`. cell filtering type and parameters\n\n- None ... do not output filtered cells\n- TopCells ... only report top cells by UMI count, followed by the exact number of cells\n- CellRanger2.2 ... simple filtering of CellRanger 2.2.\nCan be followed by numbers: number of expected cells, robust maximum percentile for UMI count, maximum to minimum ratio for UMI count\nThe harcoded values are from CellRanger: nExpectedCells=3000; maxPercentile=0.99; maxMinRatio=10\n- EmptyDrops_CR ... EmptyDrops filtering in CellRanger flavor. Please cite the original EmptyDrops paper: A.T.L Lun et al, Genome Biology, 20, 63 (2019): https://genomebiology.biomedcentral.com/articles/10.1186/s13059-019-1662-y\nCan be followed by 10 numeric parameters: nExpectedCells maxPercentile maxMinRatio indMin indMax umiMin umiMinFracMedian candMaxN FDR simN\nThe harcoded values are from CellRanger: 3000 0.99 10 45000 90000 500 0.01 20000 0.01 10000" + + } + + + , + "solo_out_format_features_gene_field3": { + "type": + "string", + "description": "Type: List of `string`, example: `Gene Expression`, multiple_sep: `\";\"`. field 3 in the Gene features", + "help_text": "Type: List of `string`, example: `Gene Expression`, multiple_sep: `\";\"`. field 3 in the Gene features.tsv file. If \"-\", then no 3rd field is output." + + } + + + , + "solo_cell_read_stats": { + "type": + "string", + "description": "Type: `string`. Output reads statistics for each CB\n\n- Standard ", + "help_text": "Type: `string`. Output reads statistics for each CB\n\n- Standard ... standard output" + + } + + +} +}, + + + "nextflow input-output arguments" : { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + + + "publish_dir": { + "type": + "string", + "description": "Type: `string`, required, example: `output/`. Path to an output directory", + "help_text": "Type: `string`, required, example: `output/`. Path to an output directory." + + } + + + , + "param_list": { + "type": + "string", + "description": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel", + "help_text": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel. A `param_list` can either be a list of maps, a csv file, a json file, a yaml file, or simply a yaml blob.\n\n* A list of maps (as-is) where the keys of each map corresponds to the arguments of the pipeline. Example: in a `nextflow.config` file: `param_list: [ [\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027], [\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027] ]`.\n* A csv file should have column names which correspond to the different arguments of this pipeline. Example: `--param_list data.csv` with columns `id,input`.\n* A json or a yaml file should be a list of maps, each of which has keys corresponding to the arguments of the pipeline. Example: `--param_list data.json` with contents `[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]`.\n* A yaml blob can also be passed directly as a string. Example: `--param_list \"[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]\"`.\n\nWhen passing a csv, json or yaml file, relative path names are relativized to the location of the parameter file. No relativation is performed when `param_list` is a list of maps (as-is) or a yaml blob.", + "hidden": true + + } + + +} +} +}, +"allOf": [ + + { + "$ref": "#/definitions/inputs" + }, + + { + "$ref": "#/definitions/outputs" + }, + + { + "$ref": "#/definitions/run parameters" + }, + + { + "$ref": "#/definitions/genome parameters" + }, + + { + "$ref": "#/definitions/splice junctions database" + }, + + { + "$ref": "#/definitions/variation parameters" + }, + + { + "$ref": "#/definitions/read parameters" + }, + + { + "$ref": "#/definitions/read clipping" + }, + + { + "$ref": "#/definitions/limits" + }, + + { + "$ref": "#/definitions/output: general" + }, + + { + "$ref": "#/definitions/output: sam and bam" + }, + + { + "$ref": "#/definitions/bam processing" + }, + + { + "$ref": "#/definitions/output wiggle" + }, + + { + "$ref": "#/definitions/output filtering" + }, + + { + "$ref": "#/definitions/output splice junctions (sj.out.tab)" + }, + + { + "$ref": "#/definitions/output filtering: splice junctions" + }, + + { + "$ref": "#/definitions/scoring" + }, + + { + "$ref": "#/definitions/alignments and seeding" + }, + + { + "$ref": "#/definitions/paired-end reads" + }, + + { + "$ref": "#/definitions/windows, anchors, binning" + }, + + { + "$ref": "#/definitions/chimeric alignments" + }, + + { + "$ref": "#/definitions/quantification of annotations" + }, + + { + "$ref": "#/definitions/2-pass mapping" + }, + + { + "$ref": "#/definitions/wasp parameters" + }, + + { + "$ref": "#/definitions/starsolo (single cell rna-seq) parameters" + }, + + { + "$ref": "#/definitions/nextflow input-output arguments" + } +] +} diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/.config.vsh.yaml b/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/.config.vsh.yaml deleted file mode 100644 index 1acbafd..0000000 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/.config.vsh.yaml +++ /dev/null @@ -1,406 +0,0 @@ -name: "pear" -version: "v0.1.0" -argument_groups: -- name: "Inputs" - arguments: - - type: "file" - name: "--forward_fastq" - alternatives: - - "-f" - description: "Forward paired-end FASTQ file" - info: null - example: - - "forward.fastq" - must_exist: true - create_parent: true - required: true - direction: "input" - multiple: false - multiple_sep: ";" - - type: "file" - name: "--reverse_fastq" - alternatives: - - "-r" - description: "Reverse paired-end FASTQ file" - info: null - example: - - "reverse.fastq" - must_exist: true - create_parent: true - required: true - direction: "input" - multiple: false - multiple_sep: ";" -- name: "Outputs" - arguments: - - type: "file" - name: "--assembled" - description: "The output file containing assembled reads. Can be compressed with\ - \ gzip." - info: null - must_exist: true - create_parent: true - required: true - direction: "output" - multiple: false - multiple_sep: ";" - - type: "file" - name: "--unassembled_forward" - description: "The output file containing forward reads that could not be assembled.\ - \ Can be compressed with gzip." - info: null - must_exist: true - create_parent: true - required: true - direction: "output" - multiple: false - multiple_sep: ";" - - type: "file" - name: "--unassembled_reverse" - description: "The output file containing reverse reads that could not be assembled.\ - \ Can be compressed with gzip." - info: null - must_exist: true - create_parent: true - required: true - direction: "output" - multiple: false - multiple_sep: ";" - - type: "file" - name: "--discarded" - description: "The output file containing reads that were discarded due to too\ - \ low quality or too many uncalled bases. Can be compressed with gzip." - info: null - must_exist: true - create_parent: true - required: true - direction: "output" - multiple: false - multiple_sep: ";" -- name: "Arguments" - arguments: - - type: "double" - name: "--p_value" - alternatives: - - "-p" - description: "Specify a p-value for the statistical test. If the computed p-value\ - \ of a possible assembly exceeds the specified p-value then paired-end read\ - \ will not be assembled. Valid options are: 0.0001, 0.001, 0.01, 0.05 and 1.0.\ - \ Setting 1.0 disables the test.\n" - info: null - example: - - 0.01 - required: false - direction: "input" - multiple: false - multiple_sep: ";" - - type: "integer" - name: "--min_overlap" - alternatives: - - "-v" - description: "Specify the minimum overlap size. The minimum overlap may be set\ - \ to 1 when the statistical test is used. However, further restricting the minimum\ - \ overlap size to a proper value may reduce false-positive assembles.\n" - info: null - example: - - 10 - required: false - direction: "input" - multiple: false - multiple_sep: ";" - - type: "integer" - name: "--max_assembly_length" - alternatives: - - "-m" - description: "Specify the maximum possible length of the assembled sequences.\ - \ Setting this value to 0 disables the restriction and assembled sequences may\ - \ be arbitrary long.\n" - info: null - example: - - 0 - required: false - direction: "input" - multiple: false - multiple_sep: ";" - - type: "integer" - name: "--min_assembly_length" - alternatives: - - "-n" - description: "Specify the minimum possible length of the assembled sequences.\ - \ Setting this value to 0 disables the restriction and assembled sequences may\ - \ be arbitrary short.\n" - info: null - example: - - 0 - required: false - direction: "input" - multiple: false - multiple_sep: ";" - - type: "integer" - name: "--min_trim_length" - alternatives: - - "-t" - description: "Specify the minimum length of reads after trimming the low quality\ - \ part (see option -q)\n" - info: null - example: - - 1 - required: false - direction: "input" - multiple: false - multiple_sep: ";" - - type: "integer" - name: "--quality_threshold" - alternatives: - - "-q" - description: "Specify the quality threshold for trimming the low quality part\ - \ of a read. If the quality scores of two consecutive bases are strictly less\ - \ than the specified threshold, the rest of the read will be trimmed.\n" - info: null - example: - - 0 - required: false - direction: "input" - multiple: false - multiple_sep: ";" - - type: "double" - name: "--max_uncalled_base" - alternatives: - - "-u" - description: "Specify the maximal proportion of uncalled bases in a read. Setting\ - \ this value to 0 will cause PEAR to discard all reads containing uncalled bases.\ - \ The other extreme setting is 1 which causes PEAR to process all reads independent\ - \ on the number of uncalled bases.\n" - info: null - example: - - 1.0 - required: false - direction: "input" - multiple: false - multiple_sep: ";" - - type: "integer" - name: "--test_method" - alternatives: - - "-g" - description: "Specify the type of statistical test. Two options are available.\ - \ 1: Given the minimum allowed overlap, test using the highest OES. Note that\ - \ due to its discrete nature, this test usually yields a lower p-value for the\ - \ assembled read than the cut- off (specified by -p). For example, setting the\ - \ cut-off to 0.05 using this test, the assembled reads might have an actual\ - \ p-value of 0.02.\n2. Use the acceptance probability (m.a.p). This test methods\ - \ computes the same probability as test method 1. However, it assumes that the\ - \ minimal overlap is the observed overlap with the highest OES, instead of the\ - \ one specified by -v. Therefore, this is not a valid statistical test and the\ - \ 'p-value' is in fact the maximal probability for accepting the assembly. Nevertheless,\ - \ we observed in practice that for the case the actual overlap sizes are relatively\ - \ small, test 2 can correctly assemble more reads with only slightly higher\ - \ false-positive rate.\n" - info: null - example: - - 1 - required: false - direction: "input" - multiple: false - multiple_sep: ";" - - type: "boolean_true" - name: "--emperical_freqs" - alternatives: - - "-e" - description: "Disable empirical base frequencies.\n" - info: null - direction: "input" - - type: "integer" - name: "--score_method" - alternatives: - - "-s" - description: "Specify the scoring method. 1. OES with +1 for match and -1 for\ - \ mismatch. 2: Assembly score (AS). Use +1 for match and -1 for mismatch multiplied\ - \ by base quality scores. 3: Ignore quality scores and use +1 for a match and\ - \ -1 for a mismatch.\n" - info: null - example: - - 2 - required: false - direction: "input" - multiple: false - multiple_sep: ";" - - type: "integer" - name: "--phred_base" - alternatives: - - "-b" - description: "Base PHRED quality score.\n" - info: null - example: - - 33 - required: false - direction: "input" - multiple: false - multiple_sep: ";" - - type: "integer" - name: "--cap" - alternatives: - - "-c" - description: "Specify the upper bound for the resulting quality score. If set\ - \ to zero, capping is disabled.\n" - info: null - example: - - 40 - required: false - direction: "input" - multiple: false - multiple_sep: ";" - - type: "boolean_true" - name: "--nbase" - alternatives: - - "-z" - description: "When merging a base-pair that consists of two non-equal bases out\ - \ of which none is degenerate, set the merged base to N and use the highest\ - \ quality score of the two bases\n" - info: null - direction: "input" -resources: -- type: "bash_script" - path: "script.sh" - is_executable: true -description: "PEAR is an ultrafast, memory-efficient and highly accurate pair-end\ - \ read merger. It is fully parallelized and can run with as low as just a few kilobytes\ - \ of memory.\n\nPEAR evaluates all possible paired-end read overlaps and without\ - \ requiring the target fragment size as input. In addition, it implements a statistical\ - \ test for minimizing false-positive results. Together with a highly optimized implementation,\ - \ it can merge millions of paired end reads within a couple of minutes on a standard\ - \ desktop computer.\n" -test_resources: -- type: "bash_script" - path: "test.sh" - is_executable: true -- type: "file" - path: "test_data" -info: null -status: "enabled" -requirements: - commands: - - "ps" -keywords: -- "pair-end" -- "read" -- "merge" -license: "CC-BY-NC-SA-3.0" -references: - doi: - - "10.1093/bioinformatics/btt593" -links: - repository: "https://github.com/tseemann/PEAR" - homepage: "https://cme.h-its.org/exelixis/web/software/pear" - documentation: "https://cme.h-its.org/exelixis/web/software/pear/doc.html" -runners: -- type: "executable" - id: "executable" - docker_setup_strategy: "ifneedbepullelsecachedbuild" -- type: "nextflow" - id: "nextflow" - directives: - tag: "$id" - auto: - simplifyInput: true - simplifyOutput: false - transcript: false - publish: false - config: - labels: - mem1gb: "memory = 1000000000.B" - mem2gb: "memory = 2000000000.B" - mem5gb: "memory = 5000000000.B" - mem10gb: "memory = 10000000000.B" - mem20gb: "memory = 20000000000.B" - mem50gb: "memory = 50000000000.B" - mem100gb: "memory = 100000000000.B" - mem200gb: "memory = 200000000000.B" - mem500gb: "memory = 500000000000.B" - mem1tb: "memory = 1000000000000.B" - mem2tb: "memory = 2000000000000.B" - mem5tb: "memory = 5000000000000.B" - mem10tb: "memory = 10000000000000.B" - mem20tb: "memory = 20000000000000.B" - mem50tb: "memory = 50000000000000.B" - mem100tb: "memory = 100000000000000.B" - mem200tb: "memory = 200000000000000.B" - mem500tb: "memory = 500000000000000.B" - mem1gib: "memory = 1073741824.B" - mem2gib: "memory = 2147483648.B" - mem4gib: "memory = 4294967296.B" - mem8gib: "memory = 8589934592.B" - mem16gib: "memory = 17179869184.B" - mem32gib: "memory = 34359738368.B" - mem64gib: "memory = 68719476736.B" - mem128gib: "memory = 137438953472.B" - mem256gib: "memory = 274877906944.B" - mem512gib: "memory = 549755813888.B" - mem1tib: "memory = 1099511627776.B" - mem2tib: "memory = 2199023255552.B" - mem4tib: "memory = 4398046511104.B" - mem8tib: "memory = 8796093022208.B" - mem16tib: "memory = 17592186044416.B" - mem32tib: "memory = 35184372088832.B" - mem64tib: "memory = 70368744177664.B" - mem128tib: "memory = 140737488355328.B" - mem256tib: "memory = 281474976710656.B" - mem512tib: "memory = 562949953421312.B" - cpu1: "cpus = 1" - cpu2: "cpus = 2" - cpu5: "cpus = 5" - cpu10: "cpus = 10" - cpu20: "cpus = 20" - cpu50: "cpus = 50" - cpu100: "cpus = 100" - cpu200: "cpus = 200" - cpu500: "cpus = 500" - cpu1000: "cpus = 1000" - debug: false - container: "docker" -engines: -- type: "docker" - id: "docker" - image: "quay.io/biocontainers/pear:0.9.6--h9d449c0_10" - target_registry: "images.viash-hub.com" - target_tag: "v0.1.0" - namespace_separator: "/" - setup: - - type: "docker" - run: - - "version=$(pear -h | grep 'PEAR v' | sed 's/PEAR v//' | sed 's/ .*//') && \\\ - \necho \"pear: $version\" > /var/software_versions.txt\n" - entrypoint: [] - cmd: null -- type: "native" - id: "native" -build_info: - config: "src/pear/config.vsh.yaml" - runner: "nextflow" - engine: "docker|native" - output: "target/nextflow/pear" - executable: "target/nextflow/pear/main.nf" - viash_version: "0.9.0-RC6" - git_commit: "b84b29747d0635f2ac83ea63b496be9a9edb6724" - git_remote: "https://github.com/viash-hub/biobox" -package_config: - name: "biobox" - version: "v0.1.0" - description: "A collection of bioinformatics tools for working with sequence data.\n" - info: null - viash_version: "0.9.0-RC6" - source: "src" - target: "target" - config_mods: - - ".requirements.commands := ['ps']\n" - - ".engines += { type: \"native\" }" - - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'" - - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" - keywords: - - "bioinformatics" - - "modules" - - "sequencing" - license: "MIT" - organization: "vsh" - links: - repository: "https://github.com/viash-hub/biobox" - issue_tracker: "https://github.com/viash-hub/biobox/issues" diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/main.nf b/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/main.nf deleted file mode 100644 index af0476c..0000000 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/main.nf +++ /dev/null @@ -1,3821 +0,0 @@ -// pear v0.1.0 -// -// This wrapper script is auto-generated by viash 0.9.0-RC6 and is thus a -// derivative work thereof. This software comes with ABSOLUTELY NO WARRANTY from -// Data Intuitive. -// -// The component may contain files which fall under a different license. The -// authors of this component should specify the license in the header of such -// files, or include a separate license file detailing the licenses of all included -// files. - -//////////////////////////// -// VDSL3 helper functions // -//////////////////////////// - -// helper file: 'src/main/resources/io/viash/runners/nextflow/arguments/_checkArgumentType.nf' -class UnexpectedArgumentTypeException extends Exception { - String errorIdentifier - String stage - String plainName - String expectedClass - String foundClass - - // ${key ? " in module '$key'" : ""}${id ? " id '$id'" : ""} - UnexpectedArgumentTypeException(String errorIdentifier, String stage, String plainName, String expectedClass, String foundClass) { - super("Error${errorIdentifier ? " $errorIdentifier" : ""}:${stage ? " $stage" : "" } argument '${plainName}' has the wrong type. " + - "Expected type: ${expectedClass}. Found type: ${foundClass}") - this.errorIdentifier = errorIdentifier - this.stage = stage - this.plainName = plainName - this.expectedClass = expectedClass - this.foundClass = foundClass - } -} - -/** - * Checks if the given value is of the expected type. If not, an exception is thrown. - * - * @param stage The stage of the argument (input or output) - * @param par The parameter definition - * @param value The value to check - * @param errorIdentifier The identifier to use in the error message - * @return The value, if it is of the expected type - * @throws UnexpectedArgumentTypeException If the value is not of the expected type -*/ -def _checkArgumentType(String stage, Map par, Object value, String errorIdentifier) { - // expectedClass will only be != null if value is not of the expected type - def expectedClass = null - def foundClass = null - - // todo: split if need be - - if (!par.required && value == null) { - expectedClass = null - } else if (par.multiple) { - if (value !instanceof Collection) { - value = [value] - } - - // split strings - value = value.collectMany{ val -> - if (val instanceof String) { - // collect() to ensure that the result is a List and not simply an array - val.split(par.multiple_sep).collect() - } else { - [val] - } - } - - // process globs - if (par.type == "file" && par.direction == "input") { - value = value.collect{ it instanceof String ? file(it, hidden: true) : it }.flatten() - } - - // check types of elements in list - try { - value = value.collect { listVal -> - _checkArgumentType(stage, par + [multiple: false], listVal, errorIdentifier) - } - } catch (UnexpectedArgumentTypeException e) { - expectedClass = "List[${e.expectedClass}]" - foundClass = "List[${e.foundClass}]" - } - } else if (par.type == "string") { - // cast to string if need be - if (value instanceof GString) { - value = value.toString() - } - expectedClass = value instanceof String ? null : "String" - } else if (par.type == "integer") { - // cast to integer if need be - if (value instanceof String) { - try { - value = value.toInteger() - } catch (NumberFormatException e) { - // do nothing - } - } - if (value instanceof java.math.BigInteger) { - value = value.intValue() - } - expectedClass = value instanceof Integer ? null : "Integer" - } else if (par.type == "long") { - // cast to long if need be - if (value instanceof String) { - try { - value = value.toLong() - } catch (NumberFormatException e) { - // do nothing - } - } - if (value instanceof Integer) { - value = value.toLong() - } - expectedClass = value instanceof Long ? null : "Long" - } else if (par.type == "double") { - // cast to double if need be - if (value instanceof String) { - try { - value = value.toDouble() - } catch (NumberFormatException e) { - // do nothing - } - } - if (value instanceof java.math.BigDecimal) { - value = value.doubleValue() - } - if (value instanceof Float) { - value = value.toDouble() - } - expectedClass = value instanceof Double ? null : "Double" - } else if (par.type == "boolean" | par.type == "boolean_true" | par.type == "boolean_false") { - // cast to boolean if need be - if (value instanceof String) { - def valueLower = value.toLowerCase() - if (valueLower == "true") { - value = true - } else if (valueLower == "false") { - value = false - } - } - expectedClass = value instanceof Boolean ? null : "Boolean" - } else if (par.type == "file" && (par.direction == "input" || stage == "output")) { - // cast to path if need be - if (value instanceof String) { - value = file(value, hidden: true) - } - if (value instanceof File) { - value = value.toPath() - } - expectedClass = value instanceof Path ? null : "Path" - } else if (par.type == "file" && stage == "input" && par.direction == "output") { - // cast to string if need be - if (value instanceof GString) { - value = value.toString() - } - expectedClass = value instanceof String ? null : "String" - } else { - // didn't find a match for par.type - expectedClass = par.type - } - - if (expectedClass != null) { - if (foundClass == null) { - foundClass = value.getClass().getName() - } - throw new UnexpectedArgumentTypeException(errorIdentifier, stage, par.plainName, expectedClass, foundClass) - } - - return value -} -// helper file: 'src/main/resources/io/viash/runners/nextflow/arguments/_processInputValues.nf' -Map _processInputValues(Map inputs, Map config, String id, String key) { - if (!workflow.stubRun) { - config.allArguments.each { arg -> - if (arg.required) { - assert inputs.containsKey(arg.plainName) && inputs.get(arg.plainName) != null : - "Error in module '${key}' id '${id}': required input argument '${arg.plainName}' is missing" - } - } - - inputs = inputs.collectEntries { name, value -> - def par = config.allArguments.find { it.plainName == name && (it.direction == "input" || it.type == "file") } - assert par != null : "Error in module '${key}' id '${id}': '${name}' is not a valid input argument" - - value = _checkArgumentType("input", par, value, "in module '$key' id '$id'") - - [ name, value ] - } - } - return inputs -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/arguments/_processOutputValues.nf' -Map _processOutputValues(Map outputs, Map config, String id, String key) { - if (!workflow.stubRun) { - config.allArguments.each { arg -> - if (arg.direction == "output" && arg.required) { - assert outputs.containsKey(arg.plainName) && outputs.get(arg.plainName) != null : - "Error in module '${key}' id '${id}': required output argument '${arg.plainName}' is missing" - } - } - - outputs = outputs.collectEntries { name, value -> - def par = config.allArguments.find { it.plainName == name && it.direction == "output" } - assert par != null : "Error in module '${key}' id '${id}': '${name}' is not a valid output argument" - - value = _checkArgumentType("output", par, value, "in module '$key' id '$id'") - - [ name, value ] - } - } - return outputs -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/IDChecker.nf' -class IDChecker { - final def items = [] as Set - - @groovy.transform.WithWriteLock - boolean observe(String item) { - if (items.contains(item)) { - return false - } else { - items << item - return true - } - } - - @groovy.transform.WithReadLock - boolean contains(String item) { - return items.contains(item) - } - - @groovy.transform.WithReadLock - Set getItems() { - return items.clone() - } -} -// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_checkUniqueIds.nf' - -/** - * Check if the ids are unique across parameter sets - * - * @param parameterSets a list of parameter sets. - */ -private void _checkUniqueIds(List>> parameterSets) { - def ppIds = parameterSets.collect{it[0]} - assert ppIds.size() == ppIds.unique().size() : "All argument sets should have unique ids. Detected ids: $ppIds" -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_getChild.nf' - -// helper functions for reading params from file // -def _getChild(parent, child) { - if (child.contains("://") || java.nio.file.Paths.get(child).isAbsolute()) { - child - } else { - def parentAbsolute = java.nio.file.Paths.get(parent).toAbsolutePath().toString() - parentAbsolute.replaceAll('/[^/]*$', "/") + child - } -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_parseParamList.nf' -/** - * Figure out the param list format based on the file extension - * - * @param param_list A String containing the path to the parameter list file. - * - * @return A String containing the format of the parameter list file. - */ -def _paramListGuessFormat(param_list) { - if (param_list !instanceof String) { - "asis" - } else if (param_list.endsWith(".csv")) { - "csv" - } else if (param_list.endsWith(".json") || param_list.endsWith(".jsn")) { - "json" - } else if (param_list.endsWith(".yaml") || param_list.endsWith(".yml")) { - "yaml" - } else { - "yaml_blob" - } -} - - -/** - * Read the param list - * - * @param param_list One of the following: - * - A String containing the path to the parameter list file (csv, json or yaml), - * - A yaml blob of a list of maps (yaml_blob), - * - Or a groovy list of maps (asis). - * @param config A Map of the Viash configuration. - * - * @return A List of Maps containing the parameters. - */ -def _parseParamList(param_list, Map config) { - // first determine format by extension - def paramListFormat = _paramListGuessFormat(param_list) - - def paramListPath = (paramListFormat != "asis" && paramListFormat != "yaml_blob") ? - file(param_list, hidden: true) : - null - - // get the correct parser function for the detected params_list format - def paramSets = [] - if (paramListFormat == "asis") { - paramSets = param_list - } else if (paramListFormat == "yaml_blob") { - paramSets = readYamlBlob(param_list) - } else if (paramListFormat == "yaml") { - paramSets = readYaml(paramListPath) - } else if (paramListFormat == "json") { - paramSets = readJson(paramListPath) - } else if (paramListFormat == "csv") { - paramSets = readCsv(paramListPath) - } else { - error "Format of provided --param_list not recognised.\n" + - "Found: '$paramListFormat'.\n" + - "Expected: a csv file, a json file, a yaml file,\n" + - "a yaml blob or a groovy list of maps." - } - - // data checks - assert paramSets instanceof List: "--param_list should contain a list of maps" - for (value in paramSets) { - assert value instanceof Map: "--param_list should contain a list of maps" - } - - // id is argument - def idIsArgument = config.allArguments.any{it.plainName == "id"} - - // Reformat from List to List> by adding the ID as first element of a Tuple2 - paramSets = paramSets.collect({ data -> - def id = data.id - if (!idIsArgument) { - data = data.findAll{k, v -> k != "id"} - } - [id, data] - }) - - // Split parameters with 'multiple: true' - paramSets = paramSets.collect({ id, data -> - data = _splitParams(data, config) - [id, data] - }) - - // The paths of input files inside a param_list file may have been specified relatively to the - // location of the param_list file. These paths must be made absolute. - if (paramListPath) { - paramSets = paramSets.collect({ id, data -> - def new_data = data.collectEntries{ parName, parValue -> - def par = config.allArguments.find{it.plainName == parName} - if (par && par.type == "file" && par.direction == "input") { - if (parValue instanceof Collection) { - parValue = parValue.collectMany{path -> - def x = _resolveSiblingIfNotAbsolute(path, paramListPath) - x instanceof Collection ? x : [x] - } - } else { - parValue = _resolveSiblingIfNotAbsolute(parValue, paramListPath) - } - } - [parName, parValue] - } - [id, new_data] - }) - } - - return paramSets -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_splitParams.nf' -/** - * Split parameters for arguments that accept multiple values using their separator - * - * @param paramList A Map containing parameters to split. - * @param config A Map of the Viash configuration. This Map can be generated from the config file - * using the readConfig() function. - * - * @return A Map of parameters where the parameter values have been split into a list using - * their seperator. - */ -Map _splitParams(Map parValues, Map config){ - def parsedParamValues = parValues.collectEntries { parName, parValue -> - def parameterSettings = config.allArguments.find({it.plainName == parName}) - - if (!parameterSettings) { - // if argument is not found, do not alter - return [parName, parValue] - } - if (parameterSettings.multiple) { // Check if parameter can accept multiple values - if (parValue instanceof Collection) { - parValue = parValue.collect{it instanceof String ? it.split(parameterSettings.multiple_sep) : it } - } else if (parValue instanceof String) { - parValue = parValue.split(parameterSettings.multiple_sep) - } else if (parValue == null) { - parValue = [] - } else { - parValue = [ parValue ] - } - parValue = parValue.flatten() - } - // For all parameters check if multiple values are only passed for - // arguments that allow it. Quietly simplify lists of length 1. - if (!parameterSettings.multiple && parValue instanceof Collection) { - assert parValue.size() == 1 : - "Error: argument ${parName} has too many values.\n" + - " Expected amount: 1. Found: ${parValue.size()}" - parValue = parValue[0] - } - [parName, parValue] - } - return parsedParamValues -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/channelFromParams.nf' -/** - * Parse nextflow parameters based on settings defined in a viash config. - * Return a list of parameter sets, each parameter set corresponding to - * an event in a nextflow channel. The output from this function can be used - * with Channel.fromList to create a nextflow channel with Vdsl3 formatted - * events. - * - * This function performs: - * - A filtering of the params which can be found in the config file. - * - Process the params_list argument which allows a user to to initialise - * a Vsdl3 channel with multiple parameter sets. Possible formats are - * csv, json, yaml, or simply a yaml_blob. A csv should have column names - * which correspond to the different arguments of this pipeline. A json or a yaml - * file should be a list of maps, each of which has keys corresponding to the - * arguments of the pipeline. A yaml blob can also be passed directly as a parameter. - * When passing a csv, json or yaml, relative path names are relativized to the - * location of the parameter file. - * - Combine the parameter sets into a vdsl3 Channel. - * - * @param params Input parameters. Can optionaly contain a 'param_list' key that - * provides a list of arguments that can be split up into multiple events - * in the output channel possible formats of param_lists are: a csv file, - * json file, a yaml file or a yaml blob. Each parameters set (event) must - * have a unique ID. - * @param config A Map of the Viash configuration. This Map can be generated from the config file - * using the readConfig() function. - * - * @return A list of parameters with the first element of the event being - * the event ID and the second element containing a map of the parsed parameters. - */ - -private List>> _paramsToParamSets(Map params, Map config){ - // todo: fetch key from run args - def key_ = config.name - - /* parse regular parameters (not in param_list) */ - /*************************************************/ - def globalParams = config.allArguments - .findAll { params.containsKey(it.plainName) } - .collectEntries { [ it.plainName, params[it.plainName] ] } - def globalID = params.get("id", null) - - /* process params_list arguments */ - /*********************************/ - def paramList = params.containsKey("param_list") && params.param_list != null ? - params.param_list : [] - // if (paramList instanceof String) { - // paramList = [paramList] - // } - // def paramSets = paramList.collectMany{ _parseParamList(it, config) } - // TODO: be able to process param_list when it is a list of strings - def paramSets = _parseParamList(paramList, config) - if (paramSets.isEmpty()) { - paramSets = [[null, [:]]] - } - - /* combine arguments into channel */ - /**********************************/ - def processedParams = paramSets.indexed().collect{ index, tup -> - // Process ID - def id = tup[0] ?: globalID - - if (workflow.stubRun && !id) { - // if stub run, explicitly add an id if missing - id = "stub${index}" - } - assert id != null: "Each parameter set should have at least an 'id'" - - // Process params - def parValues = globalParams + tup[1] - // // Remove parameters which are null, if the default is also null - // parValues = parValues.collectEntries{paramName, paramValue -> - // parameterSettings = config.functionality.allArguments.find({it.plainName == paramName}) - // if ( paramValue != null || parameterSettings.get("default", null) != null ) { - // [paramName, paramValue] - // } - // } - parValues = parValues.collectEntries { name, value -> - def par = config.allArguments.find { it.plainName == name && (it.direction == "input" || it.type == "file") } - assert par != null : "Error in module '${key_}' id '${id}': '${name}' is not a valid input argument" - - if (par == null) { - return [:] - } - value = _checkArgumentType("input", par, value, "in module '$key_' id '$id'") - - [ name, value ] - } - - [id, parValues] - } - - // Check if ids (first element of each list) is unique - _checkUniqueIds(processedParams) - return processedParams -} - -/** - * Parse nextflow parameters based on settings defined in a viash config - * and return a nextflow channel. - * - * @param params Input parameters. Can optionaly contain a 'param_list' key that - * provides a list of arguments that can be split up into multiple events - * in the output channel possible formats of param_lists are: a csv file, - * json file, a yaml file or a yaml blob. Each parameters set (event) must - * have a unique ID. - * @param config A Map of the Viash configuration. This Map can be generated from the config file - * using the readConfig() function. - * - * @return A nextflow Channel with events. Events are formatted as a tuple that contains - * first contains the ID of the event and as second element holds a parameter map. - * - * - */ -def channelFromParams(Map params, Map config) { - def processedParams = _paramsToParamSets(params, config) - return Channel.fromList(processedParams) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/checkUniqueIds.nf' -def checkUniqueIds(Map args) { - def stopOnError = args.stopOnError == null ? args.stopOnError : true - - def idChecker = new IDChecker() - - return filter { tup -> - if (!idChecker.observe(tup[0])) { - if (stopOnError) { - error "Duplicate id: ${tup[0]}" - } else { - log.warn "Duplicate id: ${tup[0]}, removing duplicate entry" - return false - } - } - return true - } -} -// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/preprocessInputs.nf' -// This helper file will be deprecated soon -preprocessInputsDeprecationWarningPrinted = false - -def preprocessInputsDeprecationWarning() { - if (!preprocessInputsDeprecationWarningPrinted) { - preprocessInputsDeprecationWarningPrinted = true - System.err.println("Warning: preprocessInputs() is deprecated and will be removed in Viash 0.9.0.") - } -} - -/** - * Generate a nextflow Workflow that allows processing a channel of - * Vdsl3 formatted events and apply a Viash config to them: - * - Gather default parameters from the Viash config and make - * sure that they are correctly formatted (see applyConfig method). - * - Format the input parameters (also using the applyConfig method). - * - Apply the default parameter to the input parameters. - * - Do some assertions: - * ~ Check if the event IDs in the channel are unique. - * - * The events in the channel are formatted as tuples, with the - * first element of the tuples being a unique id of the parameter set, - * and the second element containg the the parameters themselves. - * Optional extra elements of the tuples will be passed to the output as is. - * - * @param args A map that must contain a 'config' key that points - * to a parsed config (see readConfig()). Optionally, a - * 'key' key can be provided which can be used to create a unique - * name for the workflow process. - * - * @return A workflow that allows processing a channel of Vdsl3 formatted events - * and apply a Viash config to them. - */ -def preprocessInputs(Map args) { - preprocessInputsDeprecationWarning() - - def config = args.config - assert config instanceof Map : - "Error in preprocessInputs: config must be a map. " + - "Expected class: Map. Found: config.getClass() is ${config.getClass()}" - def key_ = args.key ?: config.name - - // Get different parameter types (used throughout this function) - def defaultArgs = config.allArguments - .findAll { it.containsKey("default") } - .collectEntries { [ it.plainName, it.default ] } - - map { tup -> - def id = tup[0] - def data = tup[1] - def passthrough = tup.drop(2) - - def new_data = (defaultArgs + data).collectEntries { name, value -> - def par = config.allArguments.find { it.plainName == name && (it.direction == "input" || it.type == "file") } - - if (par != null) { - value = _checkArgumentType("input", par, value, "in module '$key_' id '$id'") - } - - [ name, value ] - } - - [ id, new_data ] + passthrough - } -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/runComponents.nf' -/** - * Run a list of components on a stream of data. - * - * @param components: list of Viash VDSL3 modules to run - * @param fromState: a closure, a map or a list of keys to extract from the input data. - * If a closure, it will be called with the id, the data and the component config. - * @param toState: a closure, a map or a list of keys to extract from the output data - * If a closure, it will be called with the id, the output data, the old state and the component config. - * @param filter: filter function to apply to the input. - * It will be called with the id, the data and the component config. - * @param id: id to use for the output data - * If a closure, it will be called with the id, the data and the component config. - * @param auto: auto options to pass to the components - * - * @return: a workflow that runs the components - **/ -def runComponents(Map args) { - log.warn("runComponents is deprecated, use runEach instead") - assert args.components: "runComponents should be passed a list of components to run" - - def components_ = args.components - if (components_ !instanceof List) { - components_ = [ components_ ] - } - assert components_.size() > 0: "pass at least one component to runComponents" - - def fromState_ = args.fromState - def toState_ = args.toState - def filter_ = args.filter - def id_ = args.id - - workflow runComponentsWf { - take: input_ch - main: - - // generate one channel per method - out_chs = components_.collect{ comp_ -> - def comp_config = comp_.config - - def filter_ch = filter_ - ? input_ch | filter{tup -> - filter_(tup[0], tup[1], comp_config) - } - : input_ch - def id_ch = id_ - ? filter_ch | map{tup -> - // def new_id = id_(tup[0], tup[1], comp_config) - def new_id = tup[0] - if (id_ instanceof String) { - new_id = id_ - } else if (id_ instanceof Closure) { - new_id = id_(new_id, tup[1], comp_config) - } - [new_id] + tup.drop(1) - } - : filter_ch - def data_ch = id_ch | map{tup -> - def new_data = tup[1] - if (fromState_ instanceof Map) { - new_data = fromState_.collectEntries{ key0, key1 -> - [key0, new_data[key1]] - } - } else if (fromState_ instanceof List) { - new_data = fromState_.collectEntries{ key -> - [key, new_data[key]] - } - } else if (fromState_ instanceof Closure) { - new_data = fromState_(tup[0], new_data, comp_config) - } - tup.take(1) + [new_data] + tup.drop(1) - } - def out_ch = data_ch - | comp_.run( - auto: (args.auto ?: [:]) + [simplifyInput: false, simplifyOutput: false] - ) - def post_ch = toState_ - ? out_ch | map{tup -> - def output = tup[1] - def old_state = tup[2] - def new_state = null - if (toState_ instanceof Map) { - new_state = old_state + toState_.collectEntries{ key0, key1 -> - [key0, output[key1]] - } - } else if (toState_ instanceof List) { - new_state = old_state + toState_.collectEntries{ key -> - [key, output[key]] - } - } else if (toState_ instanceof Closure) { - new_state = toState_(tup[0], output, old_state, comp_config) - } - [tup[0], new_state] + tup.drop(3) - } - : out_ch - - post_ch - } - - // mix all results - output_ch = - (out_chs.size == 1) - ? out_chs[0] - : out_chs[0].mix(*out_chs.drop(1)) - - emit: output_ch - } - - return runComponentsWf -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/runEach.nf' -/** - * Run a list of components on a stream of data. - * - * @param components: list of Viash VDSL3 modules to run - * @param fromState: a closure, a map or a list of keys to extract from the input data. - * If a closure, it will be called with the id, the data and the component itself. - * @param toState: a closure, a map or a list of keys to extract from the output data - * If a closure, it will be called with the id, the output data, the old state and the component itself. - * @param filter: filter function to apply to the input. - * It will be called with the id, the data and the component itself. - * @param id: id to use for the output data - * If a closure, it will be called with the id, the data and the component itself. - * @param auto: auto options to pass to the components - * - * @return: a workflow that runs the components - **/ -def runEach(Map args) { - assert args.components: "runEach should be passed a list of components to run" - - def components_ = args.components - if (components_ !instanceof List) { - components_ = [ components_ ] - } - assert components_.size() > 0: "pass at least one component to runEach" - - def fromState_ = args.fromState - def toState_ = args.toState - def filter_ = args.filter - def id_ = args.id - - workflow runEachWf { - take: input_ch - main: - - // generate one channel per method - out_chs = components_.collect{ comp_ -> - def filter_ch = filter_ - ? input_ch | filter{tup -> - filter_(tup[0], tup[1], comp_) - } - : input_ch - def id_ch = id_ - ? filter_ch | map{tup -> - def new_id = id_ - if (new_id instanceof Closure) { - new_id = new_id(tup[0], tup[1], comp_) - } - assert new_id instanceof String : "Error in runEach: id should be a String or a Closure that returns a String. Expected: id instanceof String. Found: ${new_id.getClass()}" - [new_id] + tup.drop(1) - } - : filter_ch - def data_ch = id_ch | map{tup -> - def new_data = tup[1] - if (fromState_ instanceof Map) { - new_data = fromState_.collectEntries{ key0, key1 -> - [key0, new_data[key1]] - } - } else if (fromState_ instanceof List) { - new_data = fromState_.collectEntries{ key -> - [key, new_data[key]] - } - } else if (fromState_ instanceof Closure) { - new_data = fromState_(tup[0], new_data, comp_) - } - tup.take(1) + [new_data] + tup.drop(1) - } - def out_ch = data_ch - | comp_.run( - auto: (args.auto ?: [:]) + [simplifyInput: false, simplifyOutput: false] - ) - def post_ch = toState_ - ? out_ch | map{tup -> - def output = tup[1] - def old_state = tup[2] - def new_state = null - if (toState_ instanceof Map) { - new_state = old_state + toState_.collectEntries{ key0, key1 -> - [key0, output[key1]] - } - } else if (toState_ instanceof List) { - new_state = old_state + toState_.collectEntries{ key -> - [key, output[key]] - } - } else if (toState_ instanceof Closure) { - new_state = toState_(tup[0], output, old_state, comp_) - } - [tup[0], new_state] + tup.drop(3) - } - : out_ch - - post_ch - } - - // mix all results - output_ch = - (out_chs.size == 1) - ? out_chs[0] - : out_chs[0].mix(*out_chs.drop(1)) - - emit: output_ch - } - - return runEachWf -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/safeJoin.nf' -/** - * Join sourceChannel to targetChannel - * - * This function joins the sourceChannel to the targetChannel. - * However, each id in the targetChannel must be present in the - * sourceChannel. If _meta.join_id exists in the targetChannel, that is - * used as an id instead. If the id doesn't match any id in the sourceChannel, - * an error is thrown. - */ - -def safeJoin(targetChannel, sourceChannel, key) { - def sourceIDs = new IDChecker() - - def sourceCheck = sourceChannel - | map { tup -> - sourceIDs.observe(tup[0]) - tup - } - def targetCheck = targetChannel - | map { tup -> - def id = tup[0] - - if (!sourceIDs.contains(id)) { - error ( - "Error in module '${key}' when merging output with original state.\n" + - " Reason: output with id '${id}' could not be joined with source channel.\n" + - " If the IDs in the output channel differ from the input channel,\n" + - " please set `tup[1]._meta.join_id to the original ID.\n" + - " Original IDs in input channel: ['${sourceIDs.getItems().join("', '")}'].\n" + - " Unexpected ID in the output channel: '${id}'.\n" + - " Example input event: [\"id\", [input: file(...)]],\n" + - " Example output event: [\"newid\", [output: file(...), _meta: [join_id: \"id\"]]]" - ) - } - // TODO: add link to our documentation on how to fix this - - tup - } - - sourceCheck.cross(targetChannel) - | map{ left, right -> - right + left.drop(1) - } -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/config/_processArgument.nf' -def _processArgument(arg) { - arg.multiple = arg.multiple != null ? arg.multiple : false - arg.required = arg.required != null ? arg.required : false - arg.direction = arg.direction != null ? arg.direction : "input" - arg.multiple_sep = arg.multiple_sep != null ? arg.multiple_sep : ";" - arg.plainName = arg.name.replaceAll("^-*", "") - - if (arg.type == "file") { - arg.must_exist = arg.must_exist != null ? arg.must_exist : true - arg.create_parent = arg.create_parent != null ? arg.create_parent : true - } - - // add default values to output files which haven't already got a default - if (arg.type == "file" && arg.direction == "output" && arg.default == null) { - def mult = arg.multiple ? "_*" : "" - def extSearch = "" - if (arg.default != null) { - extSearch = arg.default - } else if (arg.example != null) { - extSearch = arg.example - } - if (extSearch instanceof List) { - extSearch = extSearch[0] - } - def extSearchResult = extSearch.find("\\.[^\\.]+\$") - def ext = extSearchResult != null ? extSearchResult : "" - arg.default = "\$id.\$key.${arg.plainName}${mult}${ext}" - if (arg.multiple) { - arg.default = [arg.default] - } - } - - if (!arg.multiple) { - if (arg.default != null && arg.default instanceof List) { - arg.default = arg.default[0] - } - if (arg.example != null && arg.example instanceof List) { - arg.example = arg.example[0] - } - } - - if (arg.type == "boolean_true") { - arg.default = false - } - if (arg.type == "boolean_false") { - arg.default = true - } - - arg -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/config/addGlobalParams.nf' -def addGlobalArguments(config) { - def localConfig = [ - "argument_groups": [ - [ - "name": "Nextflow input-output arguments", - "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", - "arguments" : [ - [ - 'name': '--publish_dir', - 'required': true, - 'type': 'string', - 'description': 'Path to an output directory.', - 'example': 'output/', - 'multiple': false - ], - [ - 'name': '--param_list', - 'required': false, - 'type': 'string', - 'description': '''Allows inputting multiple parameter sets to initialise a Nextflow channel. A `param_list` can either be a list of maps, a csv file, a json file, a yaml file, or simply a yaml blob. - | - |* A list of maps (as-is) where the keys of each map corresponds to the arguments of the pipeline. Example: in a `nextflow.config` file: `param_list: [ ['id': 'foo', 'input': 'foo.txt'], ['id': 'bar', 'input': 'bar.txt'] ]`. - |* A csv file should have column names which correspond to the different arguments of this pipeline. Example: `--param_list data.csv` with columns `id,input`. - |* A json or a yaml file should be a list of maps, each of which has keys corresponding to the arguments of the pipeline. Example: `--param_list data.json` with contents `[ {'id': 'foo', 'input': 'foo.txt'}, {'id': 'bar', 'input': 'bar.txt'} ]`. - |* A yaml blob can also be passed directly as a string. Example: `--param_list "[ {'id': 'foo', 'input': 'foo.txt'}, {'id': 'bar', 'input': 'bar.txt'} ]"`. - | - |When passing a csv, json or yaml file, relative path names are relativized to the location of the parameter file. No relativation is performed when `param_list` is a list of maps (as-is) or a yaml blob.'''.stripMargin(), - 'example': 'my_params.yaml', - 'multiple': false, - 'hidden': true - ] - // TODO: allow multiple: true in param_list? - // TODO: allow to specify a --param_list_regex to filter the param_list? - // TODO: allow to specify a --param_list_from_state to remap entries in the param_list? - ] - ] - ] - ] - - return processConfig(_mergeMap(config, localConfig)) -} - -def _mergeMap(Map lhs, Map rhs) { - return rhs.inject(lhs.clone()) { map, entry -> - if (map[entry.key] instanceof Map && entry.value instanceof Map) { - map[entry.key] = _mergeMap(map[entry.key], entry.value) - } else if (map[entry.key] instanceof Collection && entry.value instanceof Collection) { - map[entry.key] += entry.value - } else { - map[entry.key] = entry.value - } - return map - } -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/config/generateHelp.nf' -def _generateArgumentHelp(param) { - // alternatives are not supported - // def names = param.alternatives ::: List(param.name) - - def unnamedProps = [ - ["required parameter", param.required], - ["multiple values allowed", param.multiple], - ["output", param.direction.toLowerCase() == "output"], - ["file must exist", param.type == "file" && param.must_exist] - ].findAll{it[1]}.collect{it[0]} - - def dflt = null - if (param.default != null) { - if (param.default instanceof List) { - dflt = param.default.join(param.multiple_sep != null ? param.multiple_sep : ", ") - } else { - dflt = param.default.toString() - } - } - def example = null - if (param.example != null) { - if (param.example instanceof List) { - example = param.example.join(param.multiple_sep != null ? param.multiple_sep : ", ") - } else { - example = param.example.toString() - } - } - def min = param.min?.toString() - def max = param.max?.toString() - - def escapeChoice = { choice -> - def s1 = choice.replaceAll("\\n", "\\\\n") - def s2 = s1.replaceAll("\"", """\\\"""") - s2.contains(",") || s2 != choice ? "\"" + s2 + "\"" : s2 - } - def choices = param.choices == null ? - null : - "[ " + param.choices.collect{escapeChoice(it.toString())}.join(", ") + " ]" - - def namedPropsStr = [ - ["type", ([param.type] + unnamedProps).join(", ")], - ["default", dflt], - ["example", example], - ["choices", choices], - ["min", min], - ["max", max] - ] - .findAll{it[1]} - .collect{"\n " + it[0] + ": " + it[1].replaceAll("\n", "\\n")} - .join("") - - def descStr = param.description == null ? - "" : - _paragraphWrap("\n" + param.description.trim(), 80 - 8).join("\n ") - - "\n --" + param.plainName + - namedPropsStr + - descStr -} - -// Based on Helper.generateHelp() in Helper.scala -def _generateHelp(config) { - def fun = config - - // PART 1: NAME AND VERSION - def nameStr = fun.name + - (fun.version == null ? "" : " " + fun.version) - - // PART 2: DESCRIPTION - def descrStr = fun.description == null ? - "" : - "\n\n" + _paragraphWrap(fun.description.trim(), 80).join("\n") - - // PART 3: Usage - def usageStr = fun.usage == null ? - "" : - "\n\nUsage:\n" + fun.usage.trim() - - // PART 4: Options - def argGroupStrs = fun.allArgumentGroups.collect{argGroup -> - def name = argGroup.name - def descriptionStr = argGroup.description == null ? - "" : - "\n " + _paragraphWrap(argGroup.description.trim(), 80-4).join("\n ") + "\n" - def arguments = argGroup.arguments.collect{arg -> - arg instanceof String ? fun.allArguments.find{it.plainName == arg} : arg - }.findAll{it != null} - def argumentStrs = arguments.collect{param -> _generateArgumentHelp(param)} - - "\n\n$name:" + - descriptionStr + - argumentStrs.join("\n") - } - - // FINAL: combine - def out = nameStr + - descrStr + - usageStr + - argGroupStrs.join("") - - return out -} - -// based on Format._paragraphWrap -def _paragraphWrap(str, maxLength) { - def outLines = [] - str.split("\n").each{par -> - def words = par.split("\\s").toList() - - def word = null - def line = words.pop() - while(!words.isEmpty()) { - word = words.pop() - if (line.length() + word.length() + 1 <= maxLength) { - line = line + " " + word - } else { - outLines.add(line) - line = word - } - } - if (words.isEmpty()) { - outLines.add(line) - } - } - return outLines -} - -def helpMessage(config) { - if (params.containsKey("help") && params.help) { - def mergedConfig = addGlobalArguments(config) - def helpStr = _generateHelp(mergedConfig) - println(helpStr) - exit 0 - } -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/config/processConfig.nf' -def processConfig(config) { - // set defaults for arguments - config.arguments = - (config.arguments ?: []).collect{_processArgument(it)} - - // set defaults for argument_group arguments - config.argument_groups = - (config.argument_groups ?: []).collect{grp -> - grp.arguments = (grp.arguments ?: []).collect{_processArgument(it)} - grp - } - - // create combined arguments list - config.allArguments = - config.arguments + - config.argument_groups.collectMany{it.arguments} - - // add missing argument groups (based on Functionality::allArgumentGroups()) - def argGroups = config.argument_groups - if (argGroups.any{it.name.toLowerCase() == "arguments"}) { - argGroups = argGroups.collect{ grp -> - if (grp.name.toLowerCase() == "arguments") { - grp = grp + [ - arguments: grp.arguments + config.arguments - ] - } - grp - } - } else { - argGroups = argGroups + [ - name: "Arguments", - arguments: config.arguments - ] - } - config.allArgumentGroups = argGroups - - config -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/config/readConfig.nf' - -def readConfig(file) { - def config = readYaml(file ?: moduleDir.resolve("config.vsh.yaml")) - processConfig(config) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/_resolveSiblingIfNotAbsolute.nf' -/** - * Resolve a path relative to the current file. - * - * @param str The path to resolve, as a String. - * @param parentPath The path to resolve relative to, as a Path. - * - * @return The path that may have been resovled, as a Path. - */ -def _resolveSiblingIfNotAbsolute(str, parentPath) { - if (str !instanceof String) { - return str - } - if (!_stringIsAbsolutePath(str)) { - return parentPath.resolveSibling(str) - } else { - return file(str, hidden: true) - } -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/_stringIsAbsolutePath.nf' -/** - * Check whether a path as a string is absolute. - * - * In the past, we tried using `file(., relative: true).isAbsolute()`, - * but the 'relative' option was added in 22.10.0. - * - * @param path The path to check, as a String. - * - * @return Whether the path is absolute, as a boolean. - */ -def _stringIsAbsolutePath(path) { - def _resolve_URL_PROTOCOL = ~/^([a-zA-Z][a-zA-Z0-9]*:)?\\/.+/ - - assert path instanceof String - return _resolve_URL_PROTOCOL.matcher(path).matches() -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/collectTraces.nf' -class CustomTraceObserver implements nextflow.trace.TraceObserver { - List traces - - CustomTraceObserver(List traces) { - this.traces = traces - } - - @Override - void onProcessComplete(nextflow.processor.TaskHandler handler, nextflow.trace.TraceRecord trace) { - def trace2 = trace.store.clone() - trace2.script = null - traces.add(trace2) - } - - @Override - void onProcessCached(nextflow.processor.TaskHandler handler, nextflow.trace.TraceRecord trace) { - def trace2 = trace.store.clone() - trace2.script = null - traces.add(trace2) - } -} - -def collectTraces() { - def traces = Collections.synchronizedList([]) - - // add custom trace observer which stores traces in the traces object - session.observers.add(new CustomTraceObserver(traces)) - - traces -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/deepClone.nf' -/** - * Performs a deep clone of the given object. - * @param x an object - */ -def deepClone(x) { - iterateMap(x, {it instanceof Cloneable ? it.clone() : it}) -} -// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/getPublishDir.nf' -def getPublishDir() { - return params.containsKey("publish_dir") ? params.publish_dir : - params.containsKey("publishDir") ? params.publishDir : - null -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/getRootDir.nf' - -// Recurse upwards until we find a '.build.yaml' file -def _findBuildYamlFile(pathPossiblySymlink) { - def path = pathPossiblySymlink.toRealPath() - def child = path.resolve(".build.yaml") - if (java.nio.file.Files.isDirectory(path) && java.nio.file.Files.exists(child)) { - return child - } else { - def parent = path.getParent() - if (parent == null) { - return null - } else { - return _findBuildYamlFile(parent) - } - } -} - -// get the root of the target folder -def getRootDir() { - def dir = _findBuildYamlFile(meta.resources_dir) - assert dir != null: "Could not find .build.yaml in the folder structure" - dir.getParent() -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/iterateMap.nf' -/** - * Recursively apply a function over the leaves of an object. - * @param obj The object to iterate over. - * @param fun The function to apply to each value. - * @return The object with the function applied to each value. - */ -def iterateMap(obj, fun) { - if (obj instanceof List && obj !instanceof String) { - return obj.collect{item -> - iterateMap(item, fun) - } - } else if (obj instanceof Map) { - return obj.collectEntries{key, item -> - [key.toString(), iterateMap(item, fun)] - } - } else { - return fun(obj) - } -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/niceView.nf' -/** - * A view for printing the event of each channel as a YAML blob. - * This is useful for debugging. - */ -def niceView() { - workflow niceViewWf { - take: input - main: - output = input - | view{toYamlBlob(it)} - emit: output - } - return niceViewWf -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readCsv.nf' - -def readCsv(file_path) { - def output = [] - def inputFile = file_path !instanceof Path ? file(file_path, hidden: true) : file_path - - // todo: allow escaped quotes in string - // todo: allow single quotes? - def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''') - def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''') - - def br = java.nio.file.Files.newBufferedReader(inputFile) - - def row = -1 - def header = null - while (br.ready() && header == null) { - def line = br.readLine() - row++ - if (!line.startsWith("#")) { - header = splitRegex.split(line, -1).collect{field -> - m = removeQuote.matcher(field) - m.find() ? m.replaceFirst('$1') : field - } - } - } - assert header != null: "CSV file should contain a header" - - while (br.ready()) { - def line = br.readLine() - row++ - if (line == null) { - br.close() - break - } - - if (!line.startsWith("#")) { - def predata = splitRegex.split(line, -1) - def data = predata.collect{field -> - if (field == "") { - return null - } - def m = removeQuote.matcher(field) - if (m.find()) { - return m.replaceFirst('$1') - } else { - return field - } - } - assert header.size() == data.size(): "Row $row should contain the same number as fields as the header" - - def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null} - output.add(dataMap) - } - } - - output -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readJson.nf' -def readJson(file_path) { - def inputFile = file_path !instanceof Path ? file(file_path, hidden: true) : file_path - def jsonSlurper = new groovy.json.JsonSlurper() - jsonSlurper.parse(inputFile) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readJsonBlob.nf' -def readJsonBlob(str) { - def jsonSlurper = new groovy.json.JsonSlurper() - jsonSlurper.parseText(str) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readTaggedYaml.nf' -// Custom constructor to modify how certain objects are parsed from YAML -class CustomConstructor extends org.yaml.snakeyaml.constructor.Constructor { - Path root - - class ConstructPath extends org.yaml.snakeyaml.constructor.AbstractConstruct { - public Object construct(org.yaml.snakeyaml.nodes.Node node) { - String filename = (String) constructScalar(node); - if (root != null) { - return root.resolve(filename); - } - return java.nio.file.Paths.get(filename); - } - } - - CustomConstructor(org.yaml.snakeyaml.LoaderOptions options, Path root) { - super(options) - this.root = root - // Handling !file tag and parse it back to a File type - this.yamlConstructors.put(new org.yaml.snakeyaml.nodes.Tag("!file"), new ConstructPath()) - } -} - -def readTaggedYaml(Path path) { - def options = new org.yaml.snakeyaml.LoaderOptions() - def constructor = new CustomConstructor(options, path.getParent()) - def yaml = new org.yaml.snakeyaml.Yaml(constructor) - return yaml.load(path.text) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readYaml.nf' -def readYaml(file_path) { - def inputFile = file_path !instanceof Path ? file(file_path, hidden: true) : file_path - def yamlSlurper = new org.yaml.snakeyaml.Yaml() - yamlSlurper.load(inputFile) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readYamlBlob.nf' -def readYamlBlob(str) { - def yamlSlurper = new org.yaml.snakeyaml.Yaml() - yamlSlurper.load(str) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/toJsonBlob.nf' -String toJsonBlob(data) { - return groovy.json.JsonOutput.toJson(data) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/toTaggedYamlBlob.nf' -// Custom representer to modify how certain objects are represented in YAML -class CustomRepresenter extends org.yaml.snakeyaml.representer.Representer { - Path relativizer - - class RepresentPath implements org.yaml.snakeyaml.representer.Represent { - public String getFileName(Object obj) { - if (obj instanceof File) { - obj = ((File) obj).toPath(); - } - if (obj !instanceof Path) { - throw new IllegalArgumentException("Object: " + obj + " is not a Path or File"); - } - def path = (Path) obj; - - if (relativizer != null) { - return relativizer.relativize(path).toString() - } else { - return path.toString() - } - } - - public org.yaml.snakeyaml.nodes.Node representData(Object data) { - String filename = getFileName(data); - def tag = new org.yaml.snakeyaml.nodes.Tag("!file"); - return representScalar(tag, filename); - } - } - CustomRepresenter(org.yaml.snakeyaml.DumperOptions options, Path relativizer) { - super(options) - this.relativizer = relativizer - this.representers.put(sun.nio.fs.UnixPath, new RepresentPath()) - this.representers.put(Path, new RepresentPath()) - this.representers.put(File, new RepresentPath()) - } -} - -String toTaggedYamlBlob(data) { - return toRelativeTaggedYamlBlob(data, null) -} -String toRelativeTaggedYamlBlob(data, Path relativizer) { - def options = new org.yaml.snakeyaml.DumperOptions() - options.setDefaultFlowStyle(org.yaml.snakeyaml.DumperOptions.FlowStyle.BLOCK) - def representer = new CustomRepresenter(options, relativizer) - def yaml = new org.yaml.snakeyaml.Yaml(representer, options) - return yaml.dump(data) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/toYamlBlob.nf' -String toYamlBlob(data) { - def options = new org.yaml.snakeyaml.DumperOptions() - options.setDefaultFlowStyle(org.yaml.snakeyaml.DumperOptions.FlowStyle.BLOCK) - options.setPrettyFlow(true) - def yaml = new org.yaml.snakeyaml.Yaml(options) - def cleanData = iterateMap(data, { it instanceof Path ? it.toString() : it }) - return yaml.dump(cleanData) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/writeJson.nf' -void writeJson(data, file) { - assert data: "writeJson: data should not be null" - assert file: "writeJson: file should not be null" - file.write(toJsonBlob(data)) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/writeYaml.nf' -void writeYaml(data, file) { - assert data: "writeYaml: data should not be null" - assert file: "writeYaml: file should not be null" - file.write(toYamlBlob(data)) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/states/findStates.nf' -def findStates(Map params, Map config) { - def auto_config = deepClone(config) - def auto_params = deepClone(params) - - auto_config = auto_config.clone() - // override arguments - auto_config.argument_groups = [] - auto_config.arguments = [ - [ - type: "string", - name: "--id", - description: "A dummy identifier", - required: false - ], - [ - type: "file", - name: "--input_states", - example: "/path/to/input/directory/**/state.yaml", - description: "Path to input directory containing the datasets to be integrated.", - required: true, - multiple: true, - multiple_sep: ";" - ], - [ - type: "string", - name: "--filter", - example: "foo/.*/state.yaml", - description: "Regex to filter state files by path.", - required: false - ], - // to do: make this a yaml blob? - [ - type: "string", - name: "--rename_keys", - example: ["newKey1:oldKey1", "newKey2:oldKey2"], - description: "Rename keys in the detected input files. This is useful if the input files do not match the set of input arguments of the workflow.", - required: false, - multiple: true, - multiple_sep: ";" - ], - [ - type: "string", - name: "--settings", - example: '{"output_dataset": "dataset.h5ad", "k": 10}', - description: "Global arguments as a JSON glob to be passed to all components.", - required: false - ] - ] - if (!(auto_params.containsKey("id"))) { - auto_params["id"] = "auto" - } - - // run auto config through processConfig once more - auto_config = processConfig(auto_config) - - workflow findStatesWf { - helpMessage(auto_config) - - output_ch = - channelFromParams(auto_params, auto_config) - | flatMap { autoId, args -> - - def globalSettings = args.settings ? readYamlBlob(args.settings) : [:] - - // look for state files in input dir - def stateFiles = args.input_states - - // filter state files by regex - if (args.filter) { - stateFiles = stateFiles.findAll{ stateFile -> - def stateFileStr = stateFile.toString() - def matcher = stateFileStr =~ args.filter - matcher.matches()} - } - - // read in states - def states = stateFiles.collect { stateFile -> - def state_ = readTaggedYaml(stateFile) - [state_.id, state_] - } - - // construct renameMap - if (args.rename_keys) { - def renameMap = args.rename_keys.collectEntries{renameString -> - def split = renameString.split(";") - assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey,newKey:oldKey'" - split - } - - // rename keys in state, only let states through which have all keys - // also add global settings - states = states.collectMany{id, state -> - def newState = [:] - - for (key in renameMap.keySet()) { - def origKey = renameMap[key] - if (!(state.containsKey(origKey))) { - return [] - } - newState[key] = state[origKey] - } - - [[id, globalSettings + newState]] - } - } - - states - } - emit: - output_ch - } - - return findStatesWf -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/states/joinStates.nf' -def joinStates(Closure apply_) { - workflow joinStatesWf { - take: input_ch - main: - output_ch = input_ch - | toSortedList - | filter{ it.size() > 0 } - | map{ tups -> - def ids = tups.collect{it[0]} - def states = tups.collect{it[1]} - apply_(ids, states) - } - - emit: output_ch - } - return joinStatesWf -} -// helper file: 'src/main/resources/io/viash/runners/nextflow/states/publishStates.nf' -def collectFiles(obj) { - if (obj instanceof java.io.File || obj instanceof Path) { - return [obj] - } else if (obj instanceof List && obj !instanceof String) { - return obj.collectMany{item -> - collectFiles(item) - } - } else if (obj instanceof Map) { - return obj.collectMany{key, item -> - collectFiles(item) - } - } else { - return [] - } -} - -/** - * Recurse through a state and collect all input files and their target output filenames. - * @param obj The state to recurse through. - * @param prefix The prefix to prepend to the output filenames. - */ -def collectInputOutputPaths(obj, prefix) { - if (obj instanceof File || obj instanceof Path) { - def path = obj instanceof Path ? obj : obj.toPath() - def ext = path.getFileName().toString().find("\\.[^\\.]+\$") ?: "" - def newFilename = prefix + ext - return [[obj, newFilename]] - } else if (obj instanceof List && obj !instanceof String) { - return obj.withIndex().collectMany{item, ix -> - collectInputOutputPaths(item, prefix + "_" + ix) - } - } else if (obj instanceof Map) { - return obj.collectMany{key, item -> - collectInputOutputPaths(item, prefix + "." + key) - } - } else { - return [] - } -} - -def publishStates(Map args) { - def key_ = args.get("key") - def yamlTemplate_ = args.get("output_state", args.get("outputState", '$id.$key.state.yaml')) - - assert key_ != null : "publishStates: key must be specified" - - workflow publishStatesWf { - take: input_ch - main: - input_ch - | map { tup -> - def id_ = tup[0] - def state_ = tup[1] - - // the input files and the target output filenames - def inputoutputFilenames_ = collectInputOutputPaths(state_, id_ + "." + key_).transpose() - def inputFiles_ = inputoutputFilenames_[0] - def outputFilenames_ = inputoutputFilenames_[1] - - def yamlFilename = yamlTemplate_ - .replaceAll('\\$id', id_) - .replaceAll('\\$key', key_) - - // TODO: do the pathnames in state_ match up with the outputFilenames_? - - // convert state to yaml blob - def yamlBlob_ = toRelativeTaggedYamlBlob([id: id_] + state_, java.nio.file.Paths.get(yamlFilename)) - - [id_, yamlBlob_, yamlFilename, inputFiles_, outputFilenames_] - } - | publishStatesProc - emit: input_ch - } - return publishStatesWf -} -process publishStatesProc { - // todo: check publishpath? - publishDir path: "${getPublishDir()}/", mode: "copy" - tag "$id" - input: - tuple val(id), val(yamlBlob), val(yamlFile), path(inputFiles, stageAs: "_inputfile?/*"), val(outputFiles) - output: - tuple val(id), path{[yamlFile] + outputFiles} - script: - def copyCommands = [ - inputFiles instanceof List ? inputFiles : [inputFiles], - outputFiles instanceof List ? outputFiles : [outputFiles] - ] - .transpose() - .collectMany{infile, outfile -> - if (infile.toString() != outfile.toString()) { - [ - "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"", - "cp -r '${infile.toString()}' '${outfile.toString()}'" - ] - } else { - // no need to copy if infile is the same as outfile - [] - } - } - """ -mkdir -p "\$(dirname '${yamlFile}')" -echo "Storing state as yaml" -echo '${yamlBlob}' > '${yamlFile}' -echo "Copying output files to destination folder" -${copyCommands.join("\n ")} -""" -} - - -// this assumes that the state contains no other values other than those specified in the config -def publishStatesByConfig(Map args) { - def config = args.get("config") - assert config != null : "publishStatesByConfig: config must be specified" - - def key_ = args.get("key", config.name) - assert key_ != null : "publishStatesByConfig: key must be specified" - - workflow publishStatesSimpleWf { - take: input_ch - main: - input_ch - | map { tup -> - def id_ = tup[0] - def state_ = tup[1] // e.g. [output: new File("myoutput.h5ad"), k: 10] - def origState_ = tup[2] // e.g. [output: '$id.$key.foo.h5ad'] - - // TODO: allow overriding the state.yaml template - // TODO TODO: if auto.publish == "state", add output_state as an argument - def yamlTemplate = params.containsKey("output_state") ? params.output_state : '$id.$key.state.yaml' - def yamlFilename = yamlTemplate - .replaceAll('\\$id', id_) - .replaceAll('\\$key', key_) - def yamlDir = java.nio.file.Paths.get(yamlFilename).getParent() - - // the processed state is a list of [key, value, inputPath, outputFilename] tuples, where - // - key is a String - // - value is any object that can be serialized to a Yaml (so a String/Integer/Long/Double/Boolean, a List, a Map, or a Path) - // - inputPath is a List[Path] - // - outputFilename is a List[String] - // - (key, value) are the tuples that will be saved to the state.yaml file - // - (inputPath, outputFilename) are the files that will be copied from src to dest (relative to the state.yaml) - def processedState = - config.allArguments - .findAll { it.direction == "output" } - .collectMany { par -> - def plainName_ = par.plainName - // if the state does not contain the key, it's an - // optional argument for which the component did - // not generate any output - if (!state_.containsKey(plainName_)) { - return [] - } - def value = state_[plainName_] - // if the parameter is not a file, it should be stored - // in the state as-is, but is not something that needs - // to be copied from the source path to the dest path - if (par.type != "file") { - return [[key: plainName_, value: value, inputPath: [], outputFilename: []]] - } - // if the orig state does not contain this filename, - // it's an optional argument for which the user specified - // that it should not be returned as a state - if (!origState_.containsKey(plainName_)) { - return [] - } - def filenameTemplate = origState_[plainName_] - // if the pararameter is multiple: true, fetch the template - if (par.multiple && filenameTemplate instanceof List) { - filenameTemplate = filenameTemplate[0] - } - // instantiate the template - def filename = filenameTemplate - .replaceAll('\\$id', id_) - .replaceAll('\\$key', key_) - if (par.multiple) { - // if the parameter is multiple: true, the filename - // should contain a wildcard '*' that is replaced with - // the index of the file - assert filename.contains("*") : "Module '${key_}' id '${id_}': Multiple output files specified, but no wildcard '*' in the filename: ${filename}" - def outputPerFile = value.withIndex().collect{ val, ix -> - def filename_ix = filename.replace("*", ix.toString()) - def value_ = java.nio.file.Paths.get(filename_ix) - // if id contains a slash - if (yamlDir != null) { - value_ = yamlDir.relativize(value_) - } - def inputPath = val instanceof File ? val.toPath() : val - [value: value_, inputPath: inputPath, outputFilename: filename_ix] - } - def transposedOutputs = ["value", "inputPath", "outputFilename"].collectEntries{ key -> - [key, outputPerFile.collect{dic -> dic[key]}] - } - return [[key: plainName_] + transposedOutputs] - } else { - def value_ = java.nio.file.Paths.get(filename) - // if id contains a slash - if (yamlDir != null) { - value_ = yamlDir.relativize(value_) - } - def inputPath = value instanceof File ? value.toPath() : value - return [[key: plainName_, value: value_, inputPath: [inputPath], outputFilename: [filename]]] - } - } - - def updatedState_ = processedState.collectEntries{[it.key, it.value]} - def inputPaths = processedState.collectMany{it.inputPath} - def outputFilenames = processedState.collectMany{it.outputFilename} - - // convert state to yaml blob - def yamlBlob_ = toTaggedYamlBlob([id: id_] + updatedState_) - - [id_, yamlBlob_, yamlFilename, inputPaths, outputFilenames] - } - | publishStatesProc - emit: input_ch - } - return publishStatesSimpleWf -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/states/setState.nf' -def setState(fun) { - assert fun instanceof Closure || fun instanceof Map || fun instanceof List : - "Error in setState: Expected process argument to be a Closure, a Map, or a List. Found: class ${fun.getClass()}" - - // if fun is a List, convert to map - if (fun instanceof List) { - // check whether fun is a list[string] - assert fun.every{it instanceof CharSequence} : "Error in setState: argument is a List, but not all elements are Strings" - fun = fun.collectEntries{[it, it]} - } - - // if fun is a map, convert to closure - if (fun instanceof Map) { - // check whether fun is a map[string, string] - assert fun.values().every{it instanceof CharSequence} : "Error in setState: argument is a Map, but not all values are Strings" - assert fun.keySet().every{it instanceof CharSequence} : "Error in setState: argument is a Map, but not all keys are Strings" - def funMap = fun.clone() - // turn the map into a closure to be used later on - fun = { id_, state_ -> - assert state_ instanceof Map : "Error in setState: the state is not a Map" - funMap.collectMany{newkey, origkey -> - if (state_.containsKey(origkey)) { - [[newkey, state_[origkey]]] - } else { - [] - } - }.collectEntries() - } - } - - map { tup -> - def id = tup[0] - def state = tup[1] - def unfilteredState = fun(id, state) - def newState = unfilteredState.findAll{key, val -> val != null} - [id, newState] + tup.drop(2) - } -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/processAuto.nf' -// TODO: unit test processAuto -def processAuto(Map auto) { - // remove null values - auto = auto.findAll{k, v -> v != null} - - // check for unexpected keys - def expectedKeys = ["simplifyInput", "simplifyOutput", "transcript", "publish"] - def unexpectedKeys = auto.keySet() - expectedKeys - assert unexpectedKeys.isEmpty(), "unexpected keys in auto: '${unexpectedKeys.join("', '")}'" - - // check auto.simplifyInput - assert auto.simplifyInput instanceof Boolean, "auto.simplifyInput must be a boolean" - - // check auto.simplifyOutput - assert auto.simplifyOutput instanceof Boolean, "auto.simplifyOutput must be a boolean" - - // check auto.transcript - assert auto.transcript instanceof Boolean, "auto.transcript must be a boolean" - - // check auto.publish - assert auto.publish instanceof Boolean || auto.publish == "state", "auto.publish must be a boolean or 'state'" - - return auto.subMap(expectedKeys) -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/processDirectives.nf' -def assertMapKeys(map, expectedKeys, requiredKeys, mapName) { - assert map instanceof Map : "Expected argument '$mapName' to be a Map. Found: class ${map.getClass()}" - map.forEach { key, val -> - assert key in expectedKeys : "Unexpected key '$key' in ${mapName ? mapName + " " : ""}map" - } - requiredKeys.forEach { requiredKey -> - assert map.containsKey(requiredKey) : "Missing required key '$key' in ${mapName ? mapName + " " : ""}map" - } -} - -// TODO: unit test processDirectives -def processDirectives(Map drctv) { - // remove null values - drctv = drctv.findAll{k, v -> v != null} - - // check for unexpected keys - def expectedKeys = [ - "accelerator", "afterScript", "beforeScript", "cache", "conda", "container", "containerOptions", "cpus", "disk", "echo", "errorStrategy", "executor", "machineType", "maxErrors", "maxForks", "maxRetries", "memory", "module", "penv", "pod", "publishDir", "queue", "label", "scratch", "storeDir", "stageInMode", "stageOutMode", "tag", "time" - ] - def unexpectedKeys = drctv.keySet() - expectedKeys - assert unexpectedKeys.isEmpty() : "Unexpected keys in process directive: '${unexpectedKeys.join("', '")}'" - - /* DIRECTIVE accelerator - accepted examples: - - [ limit: 4, type: "nvidia-tesla-k80" ] - */ - if (drctv.containsKey("accelerator")) { - assertMapKeys(drctv["accelerator"], ["type", "limit", "request", "runtime"], [], "accelerator") - } - - /* DIRECTIVE afterScript - accepted examples: - - "source /cluster/bin/cleanup" - */ - if (drctv.containsKey("afterScript")) { - assert drctv["afterScript"] instanceof CharSequence - } - - /* DIRECTIVE beforeScript - accepted examples: - - "source /cluster/bin/setup" - */ - if (drctv.containsKey("beforeScript")) { - assert drctv["beforeScript"] instanceof CharSequence - } - - /* DIRECTIVE cache - accepted examples: - - true - - false - - "deep" - - "lenient" - */ - if (drctv.containsKey("cache")) { - assert drctv["cache"] instanceof CharSequence || drctv["cache"] instanceof Boolean - if (drctv["cache"] instanceof CharSequence) { - assert drctv["cache"] in ["deep", "lenient"] : "Unexpected value for cache" - } - } - - /* DIRECTIVE conda - accepted examples: - - "bwa=0.7.15" - - "bwa=0.7.15 fastqc=0.11.5" - - ["bwa=0.7.15", "fastqc=0.11.5"] - */ - if (drctv.containsKey("conda")) { - if (drctv["conda"] instanceof List) { - drctv["conda"] = drctv["conda"].join(" ") - } - assert drctv["conda"] instanceof CharSequence - } - - /* DIRECTIVE container - accepted examples: - - "foo/bar:tag" - - [ registry: "reg", image: "im", tag: "ta" ] - is transformed to "reg/im:ta" - - [ image: "im" ] - is transformed to "im:latest" - */ - if (drctv.containsKey("container")) { - assert drctv["container"] instanceof Map || drctv["container"] instanceof CharSequence - if (drctv["container"] instanceof Map) { - def m = drctv["container"] - assertMapKeys(m, [ "registry", "image", "tag" ], ["image"], "container") - def part1 = - System.getenv('OVERRIDE_CONTAINER_REGISTRY') ? System.getenv('OVERRIDE_CONTAINER_REGISTRY') + "/" : - params.containsKey("override_container_registry") ? params["override_container_registry"] + "/" : // todo: remove? - m.registry ? m.registry + "/" : - "" - def part2 = m.image - def part3 = m.tag ? ":" + m.tag : ":latest" - drctv["container"] = part1 + part2 + part3 - } - } - - /* DIRECTIVE containerOptions - accepted examples: - - "--foo bar" - - ["--foo bar", "-f b"] - */ - if (drctv.containsKey("containerOptions")) { - if (drctv["containerOptions"] instanceof List) { - drctv["containerOptions"] = drctv["containerOptions"].join(" ") - } - assert drctv["containerOptions"] instanceof CharSequence - } - - /* DIRECTIVE cpus - accepted examples: - - 1 - - 10 - */ - if (drctv.containsKey("cpus")) { - assert drctv["cpus"] instanceof Integer - } - - /* DIRECTIVE disk - accepted examples: - - "1 GB" - - "2TB" - - "3.2KB" - - "10.B" - */ - if (drctv.containsKey("disk")) { - assert drctv["disk"] instanceof CharSequence - // assert drctv["disk"].matches("[0-9]+(\\.[0-9]*)? *[KMGTPEZY]?B") - // ^ does not allow closures - } - - /* DIRECTIVE echo - accepted examples: - - true - - false - */ - if (drctv.containsKey("echo")) { - assert drctv["echo"] instanceof Boolean - } - - /* DIRECTIVE errorStrategy - accepted examples: - - "terminate" - - "finish" - */ - if (drctv.containsKey("errorStrategy")) { - assert drctv["errorStrategy"] instanceof CharSequence - assert drctv["errorStrategy"] in ["terminate", "finish", "ignore", "retry"] : "Unexpected value for errorStrategy" - } - - /* DIRECTIVE executor - accepted examples: - - "local" - - "sge" - */ - if (drctv.containsKey("executor")) { - assert drctv["executor"] instanceof CharSequence - assert drctv["executor"] in ["local", "sge", "uge", "lsf", "slurm", "pbs", "pbspro", "moab", "condor", "nqsii", "ignite", "k8s", "awsbatch", "google-pipelines"] : "Unexpected value for executor" - } - - /* DIRECTIVE machineType - accepted examples: - - "n1-highmem-8" - */ - if (drctv.containsKey("machineType")) { - assert drctv["machineType"] instanceof CharSequence - } - - /* DIRECTIVE maxErrors - accepted examples: - - 1 - - 3 - */ - if (drctv.containsKey("maxErrors")) { - assert drctv["maxErrors"] instanceof Integer - } - - /* DIRECTIVE maxForks - accepted examples: - - 1 - - 3 - */ - if (drctv.containsKey("maxForks")) { - assert drctv["maxForks"] instanceof Integer - } - - /* DIRECTIVE maxRetries - accepted examples: - - 1 - - 3 - */ - if (drctv.containsKey("maxRetries")) { - assert drctv["maxRetries"] instanceof Integer - } - - /* DIRECTIVE memory - accepted examples: - - "1 GB" - - "2TB" - - "3.2KB" - - "10.B" - */ - if (drctv.containsKey("memory")) { - assert drctv["memory"] instanceof CharSequence - // assert drctv["memory"].matches("[0-9]+(\\.[0-9]*)? *[KMGTPEZY]?B") - // ^ does not allow closures - } - - /* DIRECTIVE module - accepted examples: - - "ncbi-blast/2.2.27" - - "ncbi-blast/2.2.27:t_coffee/10.0" - - ["ncbi-blast/2.2.27", "t_coffee/10.0"] - */ - if (drctv.containsKey("module")) { - if (drctv["module"] instanceof List) { - drctv["module"] = drctv["module"].join(":") - } - assert drctv["module"] instanceof CharSequence - } - - /* DIRECTIVE penv - accepted examples: - - "smp" - */ - if (drctv.containsKey("penv")) { - assert drctv["penv"] instanceof CharSequence - } - - /* DIRECTIVE pod - accepted examples: - - [ label: "key", value: "val" ] - - [ annotation: "key", value: "val" ] - - [ env: "key", value: "val" ] - - [ [label: "l", value: "v"], [env: "e", value: "v"]] - */ - if (drctv.containsKey("pod")) { - if (drctv["pod"] instanceof Map) { - drctv["pod"] = [ drctv["pod"] ] - } - assert drctv["pod"] instanceof List - drctv["pod"].forEach { pod -> - assert pod instanceof Map - // TODO: should more checks be added? - // See https://www.nextflow.io/docs/latest/process.html?highlight=directives#pod - // e.g. does it contain 'label' and 'value', or 'annotation' and 'value', or ...? - } - } - - /* DIRECTIVE publishDir - accepted examples: - - [] - - [ [ path: "foo", enabled: true ], [ path: "bar", enabled: false ] ] - - "/path/to/dir" - is transformed to [[ path: "/path/to/dir" ]] - - [ path: "/path/to/dir", mode: "cache" ] - is transformed to [[ path: "/path/to/dir", mode: "cache" ]] - */ - // TODO: should we also look at params["publishDir"]? - if (drctv.containsKey("publishDir")) { - def pblsh = drctv["publishDir"] - - // check different options - assert pblsh instanceof List || pblsh instanceof Map || pblsh instanceof CharSequence - - // turn into list if not already so - // for some reason, 'if (!pblsh instanceof List) pblsh = [ pblsh ]' doesn't work. - pblsh = pblsh instanceof List ? pblsh : [ pblsh ] - - // check elements of publishDir - pblsh = pblsh.collect{ elem -> - // turn into map if not already so - elem = elem instanceof CharSequence ? [ path: elem ] : elem - - // check types and keys - assert elem instanceof Map : "Expected publish argument '$elem' to be a String or a Map. Found: class ${elem.getClass()}" - assertMapKeys(elem, [ "path", "mode", "overwrite", "pattern", "saveAs", "enabled" ], ["path"], "publishDir") - - // check elements in map - assert elem.containsKey("path") - assert elem["path"] instanceof CharSequence - if (elem.containsKey("mode")) { - assert elem["mode"] instanceof CharSequence - assert elem["mode"] in [ "symlink", "rellink", "link", "copy", "copyNoFollow", "move" ] - } - if (elem.containsKey("overwrite")) { - assert elem["overwrite"] instanceof Boolean - } - if (elem.containsKey("pattern")) { - assert elem["pattern"] instanceof CharSequence - } - if (elem.containsKey("saveAs")) { - assert elem["saveAs"] instanceof CharSequence //: "saveAs as a Closure is currently not supported. Surround your closure with single quotes to get the desired effect. Example: '\{ foo \}'" - } - if (elem.containsKey("enabled")) { - assert elem["enabled"] instanceof Boolean - } - - // return final result - elem - } - // store final directive - drctv["publishDir"] = pblsh - } - - /* DIRECTIVE queue - accepted examples: - - "long" - - "short,long" - - ["short", "long"] - */ - if (drctv.containsKey("queue")) { - if (drctv["queue"] instanceof List) { - drctv["queue"] = drctv["queue"].join(",") - } - assert drctv["queue"] instanceof CharSequence - } - - /* DIRECTIVE label - accepted examples: - - "big_mem" - - "big_cpu" - - ["big_mem", "big_cpu"] - */ - if (drctv.containsKey("label")) { - if (drctv["label"] instanceof CharSequence) { - drctv["label"] = [ drctv["label"] ] - } - assert drctv["label"] instanceof List - drctv["label"].forEach { label -> - assert label instanceof CharSequence - // assert label.matches("[a-zA-Z0-9]([a-zA-Z0-9_]*[a-zA-Z0-9])?") - // ^ does not allow closures - } - } - - /* DIRECTIVE scratch - accepted examples: - - true - - "/path/to/scratch" - - '$MY_PATH_TO_SCRATCH' - - "ram-disk" - */ - if (drctv.containsKey("scratch")) { - assert drctv["scratch"] == true || drctv["scratch"] instanceof CharSequence - } - - /* DIRECTIVE storeDir - accepted examples: - - "/path/to/storeDir" - */ - if (drctv.containsKey("storeDir")) { - assert drctv["storeDir"] instanceof CharSequence - } - - /* DIRECTIVE stageInMode - accepted examples: - - "copy" - - "link" - */ - if (drctv.containsKey("stageInMode")) { - assert drctv["stageInMode"] instanceof CharSequence - assert drctv["stageInMode"] in ["copy", "link", "symlink", "rellink"] - } - - /* DIRECTIVE stageOutMode - accepted examples: - - "copy" - - "link" - */ - if (drctv.containsKey("stageOutMode")) { - assert drctv["stageOutMode"] instanceof CharSequence - assert drctv["stageOutMode"] in ["copy", "move", "rsync"] - } - - /* DIRECTIVE tag - accepted examples: - - "foo" - - '$id' - */ - if (drctv.containsKey("tag")) { - assert drctv["tag"] instanceof CharSequence - } - - /* DIRECTIVE time - accepted examples: - - "1h" - - "2days" - - "1day 6hours 3minutes 30seconds" - */ - if (drctv.containsKey("time")) { - assert drctv["time"] instanceof CharSequence - // todo: validation regex? - } - - return drctv -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/processWorkflowArgs.nf' -def processWorkflowArgs(Map args, Map defaultWfArgs, Map meta) { - // override defaults with args - def workflowArgs = defaultWfArgs + args - - // check whether 'key' exists - assert workflowArgs.containsKey("key") : "Error in module '${meta.config.name}': key is a required argument" - - // if 'key' is a closure, apply it to the original key - if (workflowArgs["key"] instanceof Closure) { - workflowArgs["key"] = workflowArgs["key"](meta.config.name) - } - def key = workflowArgs["key"] - assert key instanceof CharSequence : "Expected process argument 'key' to be a String. Found: class ${key.getClass()}" - assert key ==~ /^[a-zA-Z_]\w*$/ : "Error in module '$key': Expected process argument 'key' to consist of only letters, digits or underscores. Found: ${key}" - - // check for any unexpected keys - def expectedKeys = ["key", "directives", "auto", "map", "mapId", "mapData", "mapPassthrough", "filter", "runIf", "fromState", "toState", "args", "renameKeys", "debug"] - def unexpectedKeys = workflowArgs.keySet() - expectedKeys - assert unexpectedKeys.isEmpty() : "Error in module '$key': unexpected arguments to the '.run()' function: '${unexpectedKeys.join("', '")}'" - - // check whether directives exists and apply defaults - assert workflowArgs.containsKey("directives") : "Error in module '$key': directives is a required argument" - assert workflowArgs["directives"] instanceof Map : "Error in module '$key': Expected process argument 'directives' to be a Map. Found: class ${workflowArgs['directives'].getClass()}" - workflowArgs["directives"] = processDirectives(defaultWfArgs.directives + workflowArgs["directives"]) - - // check whether directives exists and apply defaults - assert workflowArgs.containsKey("auto") : "Error in module '$key': auto is a required argument" - assert workflowArgs["auto"] instanceof Map : "Error in module '$key': Expected process argument 'auto' to be a Map. Found: class ${workflowArgs['auto'].getClass()}" - workflowArgs["auto"] = processAuto(defaultWfArgs.auto + workflowArgs["auto"]) - - // auto define publish, if so desired - if (workflowArgs.auto.publish == true && (workflowArgs.directives.publishDir != null ? workflowArgs.directives.publishDir : [:]).isEmpty()) { - // can't assert at this level thanks to the no_publish profile - // assert params.containsKey("publishDir") || params.containsKey("publish_dir") : - // "Error in module '${workflowArgs['key']}': if auto.publish is true, params.publish_dir needs to be defined.\n" + - // " Example: params.publish_dir = \"./output/\"" - def publishDir = getPublishDir() - - if (publishDir != null) { - workflowArgs.directives.publishDir = [[ - path: publishDir, - saveAs: "{ it.startsWith('.') ? null : it }", // don't publish hidden files, by default - mode: "copy" - ]] - } - } - - // auto define transcript, if so desired - if (workflowArgs.auto.transcript == true) { - // can't assert at this level thanks to the no_publish profile - // assert params.containsKey("transcriptsDir") || params.containsKey("transcripts_dir") || params.containsKey("publishDir") || params.containsKey("publish_dir") : - // "Error in module '${workflowArgs['key']}': if auto.transcript is true, either params.transcripts_dir or params.publish_dir needs to be defined.\n" + - // " Example: params.transcripts_dir = \"./transcripts/\"" - def transcriptsDir = - params.containsKey("transcripts_dir") ? params.transcripts_dir : - params.containsKey("transcriptsDir") ? params.transcriptsDir : - params.containsKey("publish_dir") ? params.publish_dir + "/_transcripts" : - params.containsKey("publishDir") ? params.publishDir + "/_transcripts" : - null - if (transcriptsDir != null) { - def timestamp = nextflow.Nextflow.getSession().getWorkflowMetadata().start.format('yyyy-MM-dd_HH-mm-ss') - def transcriptsPublishDir = [ - path: "$transcriptsDir/$timestamp/\${task.process.replaceAll(':', '-')}/\${id}/", - saveAs: "{ it.startsWith('.') ? it.replaceAll('^.', '') : null }", - mode: "copy" - ] - def publishDirs = workflowArgs.directives.publishDir != null ? workflowArgs.directives.publishDir : null ? workflowArgs.directives.publishDir : [] - workflowArgs.directives.publishDir = publishDirs + transcriptsPublishDir - } - } - - // if this is a stubrun, remove certain directives? - if (workflow.stubRun) { - workflowArgs.directives.keySet().removeAll(["publishDir", "cpus", "memory", "label"]) - } - - for (nam in ["map", "mapId", "mapData", "mapPassthrough", "filter", "runIf"]) { - if (workflowArgs.containsKey(nam) && workflowArgs[nam]) { - assert workflowArgs[nam] instanceof Closure : "Error in module '$key': Expected process argument '$nam' to be null or a Closure. Found: class ${workflowArgs[nam].getClass()}" - } - } - - // TODO: should functions like 'map', 'mapId', 'mapData', 'mapPassthrough' be deprecated as well? - for (nam in ["map", "mapData", "mapPassthrough", "renameKeys"]) { - if (workflowArgs.containsKey(nam) && workflowArgs[nam] != null) { - log.warn "module '$key': workflow argument '$nam' is deprecated and will be removed in Viash 0.9.0. Please use 'fromState' and 'toState' instead." - } - } - - // check fromState - workflowArgs["fromState"] = _processFromState(workflowArgs.get("fromState"), key, meta.config) - - // check toState - workflowArgs["toState"] = _processToState(workflowArgs.get("toState"), key, meta.config) - - // return output - return workflowArgs -} - -def _processFromState(fromState, key_, config_) { - assert fromState == null || fromState instanceof Closure || fromState instanceof Map || fromState instanceof List : - "Error in module '$key_': Expected process argument 'fromState' to be null, a Closure, a Map, or a List. Found: class ${fromState.getClass()}" - if (fromState == null) { - return null - } - - // if fromState is a List, convert to map - if (fromState instanceof List) { - // check whether fromstate is a list[string] - assert fromState.every{it instanceof CharSequence} : "Error in module '$key_': fromState is a List, but not all elements are Strings" - fromState = fromState.collectEntries{[it, it]} - } - - // if fromState is a map, convert to closure - if (fromState instanceof Map) { - // check whether fromstate is a map[string, string] - assert fromState.values().every{it instanceof CharSequence} : "Error in module '$key_': fromState is a Map, but not all values are Strings" - assert fromState.keySet().every{it instanceof CharSequence} : "Error in module '$key_': fromState is a Map, but not all keys are Strings" - def fromStateMap = fromState.clone() - def requiredInputNames = meta.config.allArguments.findAll{it.required && it.direction == "Input"}.collect{it.plainName} - // turn the map into a closure to be used later on - fromState = { it -> - def state = it[1] - assert state instanceof Map : "Error in module '$key_': the state is not a Map" - def data = fromStateMap.collectMany{newkey, origkey -> - // check whether newkey corresponds to a required argument - if (state.containsKey(origkey)) { - [[newkey, state[origkey]]] - } else if (!requiredInputNames.contains(origkey)) { - [] - } else { - throw new Exception("Error in module '$key_': fromState key '$origkey' not found in current state") - } - }.collectEntries() - data - } - } - - return fromState -} - -def _processToState(toState, key_, config_) { - if (toState == null) { - toState = { tup -> tup[1] } - } - - // toState should be a closure, map[string, string], or list[string] - assert toState instanceof Closure || toState instanceof Map || toState instanceof List : - "Error in module '$key_': Expected process argument 'toState' to be a Closure, a Map, or a List. Found: class ${toState.getClass()}" - - // if toState is a List, convert to map - if (toState instanceof List) { - // check whether toState is a list[string] - assert toState.every{it instanceof CharSequence} : "Error in module '$key_': toState is a List, but not all elements are Strings" - toState = toState.collectEntries{[it, it]} - } - - // if toState is a map, convert to closure - if (toState instanceof Map) { - // check whether toState is a map[string, string] - assert toState.values().every{it instanceof CharSequence} : "Error in module '$key_': toState is a Map, but not all values are Strings" - assert toState.keySet().every{it instanceof CharSequence} : "Error in module '$key_': toState is a Map, but not all keys are Strings" - def toStateMap = toState.clone() - def requiredOutputNames = config_.allArguments.findAll{it.required && it.direction == "Output"}.collect{it.plainName} - // turn the map into a closure to be used later on - toState = { it -> - def output = it[1] - def state = it[2] - assert output instanceof Map : "Error in module '$key_': the output is not a Map" - assert state instanceof Map : "Error in module '$key_': the state is not a Map" - def extraEntries = toStateMap.collectMany{newkey, origkey -> - // check whether newkey corresponds to a required argument - if (output.containsKey(origkey)) { - [[newkey, output[origkey]]] - } else if (!requiredOutputNames.contains(origkey)) { - [] - } else { - throw new Exception("Error in module '$key_': toState key '$origkey' not found in current output") - } - }.collectEntries() - state + extraEntries - } - } - - return toState -} - -// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/workflowFactory.nf' -def _debug(workflowArgs, debugKey) { - if (workflowArgs.debug) { - view { "process '${workflowArgs.key}' $debugKey tuple: $it" } - } else { - map { it } - } -} - -// depends on: innerWorkflowFactory -def workflowFactory(Map args, Map defaultWfArgs, Map meta) { - def workflowArgs = processWorkflowArgs(args, defaultWfArgs, meta) - def key_ = workflowArgs["key"] - - workflow workflowInstance { - take: input_ - - main: - def chModified = input_ - | checkUniqueIds([:]) - | _debug(workflowArgs, "input") - | map { tuple -> - tuple = deepClone(tuple) - - if (workflowArgs.map) { - tuple = workflowArgs.map(tuple) - } - if (workflowArgs.mapId) { - tuple[0] = workflowArgs.mapId(tuple[0]) - } - if (workflowArgs.mapData) { - tuple[1] = workflowArgs.mapData(tuple[1]) - } - if (workflowArgs.mapPassthrough) { - tuple = tuple.take(2) + workflowArgs.mapPassthrough(tuple.drop(2)) - } - - // check tuple - assert tuple instanceof List : - "Error in module '${key_}': element in channel should be a tuple [id, data, ...otherargs...]\n" + - " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + - " Expected class: List. Found: tuple.getClass() is ${tuple.getClass()}" - assert tuple.size() >= 2 : - "Error in module '${key_}': expected length of tuple in input channel to be two or greater.\n" + - " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + - " Found: tuple.size() == ${tuple.size()}" - - // check id field - if (tuple[0] instanceof GString) { - tuple[0] = tuple[0].toString() - } - assert tuple[0] instanceof CharSequence : - "Error in module '${key_}': first element of tuple in channel should be a String\n" + - " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + - " Found: ${tuple[0]}" - - // match file to input file - if (workflowArgs.auto.simplifyInput && (tuple[1] instanceof Path || tuple[1] instanceof List)) { - def inputFiles = meta.config.allArguments - .findAll { it.type == "file" && it.direction == "input" } - - assert inputFiles.size() == 1 : - "Error in module '${key_}' id '${tuple[0]}'.\n" + - " Anonymous file inputs are only allowed when the process has exactly one file input.\n" + - " Expected: inputFiles.size() == 1. Found: inputFiles.size() is ${inputFiles.size()}" - - tuple[1] = [[ inputFiles[0].plainName, tuple[1] ]].collectEntries() - } - - // check data field - assert tuple[1] instanceof Map : - "Error in module '${key_}' id '${tuple[0]}': second element of tuple in channel should be a Map\n" + - " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + - " Expected class: Map. Found: tuple[1].getClass() is ${tuple[1].getClass()}" - - // rename keys of data field in tuple - if (workflowArgs.renameKeys) { - assert workflowArgs.renameKeys instanceof Map : - "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + - " Example: renameKeys: ['new_key': 'old_key'].\n" + - " Expected class: Map. Found: renameKeys.getClass() is ${workflowArgs.renameKeys.getClass()}" - assert tuple[1] instanceof Map : - "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + - " Expected class: Map. Found: tuple[1].getClass() is ${tuple[1].getClass()}" - - // TODO: allow renameKeys to be a function? - workflowArgs.renameKeys.each { newKey, oldKey -> - assert newKey instanceof CharSequence : - "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + - " Example: renameKeys: ['new_key': 'old_key'].\n" + - " Expected class of newKey: String. Found: newKey.getClass() is ${newKey.getClass()}" - assert oldKey instanceof CharSequence : - "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + - " Example: renameKeys: ['new_key': 'old_key'].\n" + - " Expected class of oldKey: String. Found: oldKey.getClass() is ${oldKey.getClass()}" - assert tuple[1].containsKey(oldKey) : - "Error renaming data keys in module '${key}' id '${tuple[0]}'.\n" + - " Key '$oldKey' is missing in the data map. tuple[1].keySet() is '${tuple[1].keySet()}'" - tuple[1].put(newKey, tuple[1][oldKey]) - } - tuple[1].keySet().removeAll(workflowArgs.renameKeys.collect{ newKey, oldKey -> oldKey }) - } - tuple - } - - def chModifiedFiltered = workflowArgs.filter ? - chModified | filter{workflowArgs.filter(it)} : - chModified - - def chRun = null - def chPassthrough = null - if (workflowArgs.runIf) { - def runIfBranch = chModifiedFiltered.branch{ tup -> - run: workflowArgs.runIf(tup[0], tup[1]) - passthrough: true - } - chRun = runIfBranch.run - chPassthrough = runIfBranch.passthrough - } else { - chRun = chModifiedFiltered - chPassthrough = Channel.empty() - } - - def chArgs = workflowArgs.fromState ? - chRun | map{ - def new_data = workflowArgs.fromState(it.take(2)) - [it[0], new_data] - } : - chRun | map {tup -> tup.take(2)} - - // fill in defaults - def chArgsWithDefaults = chArgs - | map { tuple -> - def id_ = tuple[0] - def data_ = tuple[1] - - // TODO: could move fromState to here - - // fetch default params from functionality - def defaultArgs = meta.config.allArguments - .findAll { it.containsKey("default") } - .collectEntries { [ it.plainName, it.default ] } - - // fetch overrides in params - def paramArgs = meta.config.allArguments - .findAll { par -> - def argKey = key_ + "__" + par.plainName - params.containsKey(argKey) - } - .collectEntries { [ it.plainName, params[key_ + "__" + it.plainName] ] } - - // fetch overrides in data - def dataArgs = meta.config.allArguments - .findAll { data_.containsKey(it.plainName) } - .collectEntries { [ it.plainName, data_[it.plainName] ] } - - // combine params - def combinedArgs = defaultArgs + paramArgs + workflowArgs.args + dataArgs - - // remove arguments with explicit null values - combinedArgs - .removeAll{_, val -> val == null || val == "viash_no_value" || val == "force_null"} - - combinedArgs = _processInputValues(combinedArgs, meta.config, id_, key_) - - [id_, combinedArgs] + tuple.drop(2) - } - - // TODO: move some of the _meta.join_id wrangling to the safeJoin() function. - def chInitialOutput = chArgsWithDefaults - | _debug(workflowArgs, "processed") - // run workflow - | innerWorkflowFactory(workflowArgs) - // check output tuple - | map { id_, output_ -> - - // see if output map contains metadata - def meta_ = - output_ instanceof Map && output_.containsKey("_meta") ? - output_["_meta"] : - [:] - def join_id = meta_.join_id ?: id_ - - // remove metadata - output_ = output_.findAll{k, v -> k != "_meta"} - - // check value types - output_ = _processOutputValues(output_, meta.config, id_, key_) - - // simplify output if need be - if (workflowArgs.auto.simplifyOutput && output_.size() == 1) { - output_ = output_.values()[0] - } - - [join_id, id_, output_] - } - // | view{"chInitialOutput: ${it.take(3)}"} - - // join the output [prev_id, new_id, output] with the previous state [prev_id, state, ...] - def chNewState = safeJoin(chInitialOutput, chModifiedFiltered, key_) - // input tuple format: [join_id, id, output, prev_state, ...] - // output tuple format: [join_id, id, new_state, ...] - | map{ tup -> - def new_state = workflowArgs.toState(tup.drop(1).take(3)) - tup.take(2) + [new_state] + tup.drop(4) - } - - if (workflowArgs.auto.publish == "state") { - def chPublish = chNewState - // input tuple format: [join_id, id, new_state, ...] - // output tuple format: [join_id, id, new_state] - | map{ tup -> - tup.take(3) - } - - safeJoin(chPublish, chArgsWithDefaults, key_) - // input tuple format: [join_id, id, new_state, orig_state, ...] - // output tuple format: [id, new_state, orig_state] - | map { tup -> - tup.drop(1).take(3) - } - | publishStatesByConfig(key: key_, config: meta.config) - } - - // remove join_id and meta - chReturn = chNewState - | map { tup -> - // input tuple format: [join_id, id, new_state, ...] - // output tuple format: [id, new_state, ...] - tup.drop(1) - } - | _debug(workflowArgs, "output") - | concat(chPassthrough) - - emit: chReturn - } - - def wf = workflowInstance.cloneWithName(key_) - - // add factory function - wf.metaClass.run = { runArgs -> - workflowFactory(runArgs, workflowArgs, meta) - } - // add config to module for later introspection - wf.metaClass.config = meta.config - - return wf -} - -nextflow.enable.dsl=2 - -// START COMPONENT-SPECIFIC CODE - -// create meta object -meta = [ - "resources_dir": moduleDir.toRealPath().normalize(), - "config": processConfig(readJsonBlob('''{ - "name" : "pear", - "version" : "v0.1.0", - "argument_groups" : [ - { - "name" : "Inputs", - "arguments" : [ - { - "type" : "file", - "name" : "--forward_fastq", - "alternatives" : [ - "-f" - ], - "description" : "Forward paired-end FASTQ file", - "example" : [ - "forward.fastq" - ], - "must_exist" : true, - "create_parent" : true, - "required" : true, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "file", - "name" : "--reverse_fastq", - "alternatives" : [ - "-r" - ], - "description" : "Reverse paired-end FASTQ file", - "example" : [ - "reverse.fastq" - ], - "must_exist" : true, - "create_parent" : true, - "required" : true, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - } - ] - }, - { - "name" : "Outputs", - "arguments" : [ - { - "type" : "file", - "name" : "--assembled", - "description" : "The output file containing assembled reads. Can be compressed with gzip.", - "must_exist" : true, - "create_parent" : true, - "required" : true, - "direction" : "output", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "file", - "name" : "--unassembled_forward", - "description" : "The output file containing forward reads that could not be assembled. Can be compressed with gzip.", - "must_exist" : true, - "create_parent" : true, - "required" : true, - "direction" : "output", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "file", - "name" : "--unassembled_reverse", - "description" : "The output file containing reverse reads that could not be assembled. Can be compressed with gzip.", - "must_exist" : true, - "create_parent" : true, - "required" : true, - "direction" : "output", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "file", - "name" : "--discarded", - "description" : "The output file containing reads that were discarded due to too low quality or too many uncalled bases. Can be compressed with gzip.", - "must_exist" : true, - "create_parent" : true, - "required" : true, - "direction" : "output", - "multiple" : false, - "multiple_sep" : ";" - } - ] - }, - { - "name" : "Arguments", - "arguments" : [ - { - "type" : "double", - "name" : "--p_value", - "alternatives" : [ - "-p" - ], - "description" : "Specify a p-value for the statistical test. If the computed p-value of a possible assembly exceeds the specified p-value then paired-end read will not be assembled. Valid options are: 0.0001, 0.001, 0.01, 0.05 and 1.0. Setting 1.0 disables the test.\n", - "example" : [ - 0.01 - ], - "required" : false, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "integer", - "name" : "--min_overlap", - "alternatives" : [ - "-v" - ], - "description" : "Specify the minimum overlap size. The minimum overlap may be set to 1 when the statistical test is used. However, further restricting the minimum overlap size to a proper value may reduce false-positive assembles.\n", - "example" : [ - 10 - ], - "required" : false, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "integer", - "name" : "--max_assembly_length", - "alternatives" : [ - "-m" - ], - "description" : "Specify the maximum possible length of the assembled sequences. Setting this value to 0 disables the restriction and assembled sequences may be arbitrary long.\n", - "example" : [ - 0 - ], - "required" : false, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "integer", - "name" : "--min_assembly_length", - "alternatives" : [ - "-n" - ], - "description" : "Specify the minimum possible length of the assembled sequences. Setting this value to 0 disables the restriction and assembled sequences may be arbitrary short.\n", - "example" : [ - 0 - ], - "required" : false, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "integer", - "name" : "--min_trim_length", - "alternatives" : [ - "-t" - ], - "description" : "Specify the minimum length of reads after trimming the low quality part (see option -q)\n", - "example" : [ - 1 - ], - "required" : false, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "integer", - "name" : "--quality_threshold", - "alternatives" : [ - "-q" - ], - "description" : "Specify the quality threshold for trimming the low quality part of a read. If the quality scores of two consecutive bases are strictly less than the specified threshold, the rest of the read will be trimmed.\n", - "example" : [ - 0 - ], - "required" : false, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "double", - "name" : "--max_uncalled_base", - "alternatives" : [ - "-u" - ], - "description" : "Specify the maximal proportion of uncalled bases in a read. Setting this value to 0 will cause PEAR to discard all reads containing uncalled bases. The other extreme setting is 1 which causes PEAR to process all reads independent on the number of uncalled bases.\n", - "example" : [ - 1.0 - ], - "required" : false, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "integer", - "name" : "--test_method", - "alternatives" : [ - "-g" - ], - "description" : "Specify the type of statistical test. Two options are available. 1: Given the minimum allowed overlap, test using the highest OES. Note that due to its discrete nature, this test usually yields a lower p-value for the assembled read than the cut- off (specified by -p). For example, setting the cut-off to 0.05 using this test, the assembled reads might have an actual p-value of 0.02.\n2. Use the acceptance probability (m.a.p). This test methods computes the same probability as test method 1. However, it assumes that the minimal overlap is the observed overlap with the highest OES, instead of the one specified by -v. Therefore, this is not a valid statistical test and the 'p-value' is in fact the maximal probability for accepting the assembly. Nevertheless, we observed in practice that for the case the actual overlap sizes are relatively small, test 2 can correctly assemble more reads with only slightly higher false-positive rate.\n", - "example" : [ - 1 - ], - "required" : false, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "boolean_true", - "name" : "--emperical_freqs", - "alternatives" : [ - "-e" - ], - "description" : "Disable empirical base frequencies.\n", - "direction" : "input" - }, - { - "type" : "integer", - "name" : "--score_method", - "alternatives" : [ - "-s" - ], - "description" : "Specify the scoring method. 1. OES with +1 for match and -1 for mismatch. 2: Assembly score (AS). Use +1 for match and -1 for mismatch multiplied by base quality scores. 3: Ignore quality scores and use +1 for a match and -1 for a mismatch.\n", - "example" : [ - 2 - ], - "required" : false, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "integer", - "name" : "--phred_base", - "alternatives" : [ - "-b" - ], - "description" : "Base PHRED quality score.\n", - "example" : [ - 33 - ], - "required" : false, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "integer", - "name" : "--cap", - "alternatives" : [ - "-c" - ], - "description" : "Specify the upper bound for the resulting quality score. If set to zero, capping is disabled.\n", - "example" : [ - 40 - ], - "required" : false, - "direction" : "input", - "multiple" : false, - "multiple_sep" : ";" - }, - { - "type" : "boolean_true", - "name" : "--nbase", - "alternatives" : [ - "-z" - ], - "description" : "When merging a base-pair that consists of two non-equal bases out of which none is degenerate, set the merged base to N and use the highest quality score of the two bases\n", - "direction" : "input" - } - ] - } - ], - "resources" : [ - { - "type" : "bash_script", - "path" : "script.sh", - "is_executable" : true - } - ], - "description" : "PEAR is an ultrafast, memory-efficient and highly accurate pair-end read merger. It is fully parallelized and can run with as low as just a few kilobytes of memory.\n\nPEAR evaluates all possible paired-end read overlaps and without requiring the target fragment size as input. In addition, it implements a statistical test for minimizing false-positive results. Together with a highly optimized implementation, it can merge millions of paired end reads within a couple of minutes on a standard desktop computer.\n", - "test_resources" : [ - { - "type" : "bash_script", - "path" : "test.sh", - "is_executable" : true - }, - { - "type" : "file", - "path" : "test_data" - } - ], - "status" : "enabled", - "requirements" : { - "commands" : [ - "ps" - ] - }, - "keywords" : [ - "pair-end", - "read", - "merge" - ], - "license" : "CC-BY-NC-SA-3.0", - "references" : { - "doi" : [ - "10.1093/bioinformatics/btt593" - ] - }, - "links" : { - "repository" : "https://github.com/tseemann/PEAR", - "homepage" : "https://cme.h-its.org/exelixis/web/software/pear", - "documentation" : "https://cme.h-its.org/exelixis/web/software/pear/doc.html" - }, - "runners" : [ - { - "type" : "executable", - "id" : "executable", - "docker_setup_strategy" : "ifneedbepullelsecachedbuild" - }, - { - "type" : "nextflow", - "id" : "nextflow", - "directives" : { - "tag" : "$id" - }, - "auto" : { - "simplifyInput" : true, - "simplifyOutput" : false, - "transcript" : false, - "publish" : false - }, - "config" : { - "labels" : { - "mem1gb" : "memory = 1000000000.B", - "mem2gb" : "memory = 2000000000.B", - "mem5gb" : "memory = 5000000000.B", - "mem10gb" : "memory = 10000000000.B", - "mem20gb" : "memory = 20000000000.B", - "mem50gb" : "memory = 50000000000.B", - "mem100gb" : "memory = 100000000000.B", - "mem200gb" : "memory = 200000000000.B", - "mem500gb" : "memory = 500000000000.B", - "mem1tb" : "memory = 1000000000000.B", - "mem2tb" : "memory = 2000000000000.B", - "mem5tb" : "memory = 5000000000000.B", - "mem10tb" : "memory = 10000000000000.B", - "mem20tb" : "memory = 20000000000000.B", - "mem50tb" : "memory = 50000000000000.B", - "mem100tb" : "memory = 100000000000000.B", - "mem200tb" : "memory = 200000000000000.B", - "mem500tb" : "memory = 500000000000000.B", - "mem1gib" : "memory = 1073741824.B", - "mem2gib" : "memory = 2147483648.B", - "mem4gib" : "memory = 4294967296.B", - "mem8gib" : "memory = 8589934592.B", - "mem16gib" : "memory = 17179869184.B", - "mem32gib" : "memory = 34359738368.B", - "mem64gib" : "memory = 68719476736.B", - "mem128gib" : "memory = 137438953472.B", - "mem256gib" : "memory = 274877906944.B", - "mem512gib" : "memory = 549755813888.B", - "mem1tib" : "memory = 1099511627776.B", - "mem2tib" : "memory = 2199023255552.B", - "mem4tib" : "memory = 4398046511104.B", - "mem8tib" : "memory = 8796093022208.B", - "mem16tib" : "memory = 17592186044416.B", - "mem32tib" : "memory = 35184372088832.B", - "mem64tib" : "memory = 70368744177664.B", - "mem128tib" : "memory = 140737488355328.B", - "mem256tib" : "memory = 281474976710656.B", - "mem512tib" : "memory = 562949953421312.B", - "cpu1" : "cpus = 1", - "cpu2" : "cpus = 2", - "cpu5" : "cpus = 5", - "cpu10" : "cpus = 10", - "cpu20" : "cpus = 20", - "cpu50" : "cpus = 50", - "cpu100" : "cpus = 100", - "cpu200" : "cpus = 200", - "cpu500" : "cpus = 500", - "cpu1000" : "cpus = 1000" - } - }, - "debug" : false, - "container" : "docker" - } - ], - "engines" : [ - { - "type" : "docker", - "id" : "docker", - "image" : "quay.io/biocontainers/pear:0.9.6--h9d449c0_10", - "target_registry" : "images.viash-hub.com", - "target_tag" : "v0.1.0", - "namespace_separator" : "/", - "setup" : [ - { - "type" : "docker", - "run" : [ - "version=$(pear -h | grep 'PEAR v' | sed 's/PEAR v//' | sed 's/ .*//') && \\\\\necho \\"pear: $version\\" > /var/software_versions.txt\n" - ] - } - ] - }, - { - "type" : "native", - "id" : "native" - } - ], - "build_info" : { - "config" : "/workdir/root/repo/src/pear/config.vsh.yaml", - "runner" : "nextflow", - "engine" : "docker|native", - "output" : "target/nextflow/pear", - "viash_version" : "0.9.0-RC6", - "git_commit" : "b84b29747d0635f2ac83ea63b496be9a9edb6724", - "git_remote" : "https://github.com/viash-hub/biobox" - }, - "package_config" : { - "name" : "biobox", - "version" : "v0.1.0", - "description" : "A collection of bioinformatics tools for working with sequence data.\n", - "viash_version" : "0.9.0-RC6", - "source" : "src", - "target" : "target", - "config_mods" : [ - ".requirements.commands := ['ps']\n", - ".engines += { type: \\"native\\" }", - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'", - ".engines[.type == 'docker'].target_tag := 'v0.1.0'" - ], - "keywords" : [ - "bioinformatics", - "modules", - "sequencing" - ], - "license" : "MIT", - "organization" : "vsh", - "links" : { - "repository" : "https://github.com/viash-hub/biobox", - "issue_tracker" : "https://github.com/viash-hub/biobox/issues" - } - } -}''')) -] - -// resolve dependencies dependencies (if any) - - -// inner workflow -// inner workflow hook -def innerWorkflowFactory(args) { - def rawScript = '''set -e -tempscript=".viash_script.sh" -cat > "$tempscript" << VIASHMAIN -#!/bin/bash - -## VIASH START -# The following code has been auto-generated by Viash. -$( if [ ! -z ${VIASH_PAR_FORWARD_FASTQ+x} ]; then echo "${VIASH_PAR_FORWARD_FASTQ}" | sed "s#'#'\\"'\\"'#g;s#.*#par_forward_fastq='&'#" ; else echo "# par_forward_fastq="; fi ) -$( if [ ! -z ${VIASH_PAR_REVERSE_FASTQ+x} ]; then echo "${VIASH_PAR_REVERSE_FASTQ}" | sed "s#'#'\\"'\\"'#g;s#.*#par_reverse_fastq='&'#" ; else echo "# par_reverse_fastq="; fi ) -$( if [ ! -z ${VIASH_PAR_ASSEMBLED+x} ]; then echo "${VIASH_PAR_ASSEMBLED}" | sed "s#'#'\\"'\\"'#g;s#.*#par_assembled='&'#" ; else echo "# par_assembled="; fi ) -$( if [ ! -z ${VIASH_PAR_UNASSEMBLED_FORWARD+x} ]; then echo "${VIASH_PAR_UNASSEMBLED_FORWARD}" | sed "s#'#'\\"'\\"'#g;s#.*#par_unassembled_forward='&'#" ; else echo "# par_unassembled_forward="; fi ) -$( if [ ! -z ${VIASH_PAR_UNASSEMBLED_REVERSE+x} ]; then echo "${VIASH_PAR_UNASSEMBLED_REVERSE}" | sed "s#'#'\\"'\\"'#g;s#.*#par_unassembled_reverse='&'#" ; else echo "# par_unassembled_reverse="; fi ) -$( if [ ! -z ${VIASH_PAR_DISCARDED+x} ]; then echo "${VIASH_PAR_DISCARDED}" | sed "s#'#'\\"'\\"'#g;s#.*#par_discarded='&'#" ; else echo "# par_discarded="; fi ) -$( if [ ! -z ${VIASH_PAR_P_VALUE+x} ]; then echo "${VIASH_PAR_P_VALUE}" | sed "s#'#'\\"'\\"'#g;s#.*#par_p_value='&'#" ; else echo "# par_p_value="; fi ) -$( if [ ! -z ${VIASH_PAR_MIN_OVERLAP+x} ]; then echo "${VIASH_PAR_MIN_OVERLAP}" | sed "s#'#'\\"'\\"'#g;s#.*#par_min_overlap='&'#" ; else echo "# par_min_overlap="; fi ) -$( if [ ! -z ${VIASH_PAR_MAX_ASSEMBLY_LENGTH+x} ]; then echo "${VIASH_PAR_MAX_ASSEMBLY_LENGTH}" | sed "s#'#'\\"'\\"'#g;s#.*#par_max_assembly_length='&'#" ; else echo "# par_max_assembly_length="; fi ) -$( if [ ! -z ${VIASH_PAR_MIN_ASSEMBLY_LENGTH+x} ]; then echo "${VIASH_PAR_MIN_ASSEMBLY_LENGTH}" | sed "s#'#'\\"'\\"'#g;s#.*#par_min_assembly_length='&'#" ; else echo "# par_min_assembly_length="; fi ) -$( if [ ! -z ${VIASH_PAR_MIN_TRIM_LENGTH+x} ]; then echo "${VIASH_PAR_MIN_TRIM_LENGTH}" | sed "s#'#'\\"'\\"'#g;s#.*#par_min_trim_length='&'#" ; else echo "# par_min_trim_length="; fi ) -$( if [ ! -z ${VIASH_PAR_QUALITY_THRESHOLD+x} ]; then echo "${VIASH_PAR_QUALITY_THRESHOLD}" | sed "s#'#'\\"'\\"'#g;s#.*#par_quality_threshold='&'#" ; else echo "# par_quality_threshold="; fi ) -$( if [ ! -z ${VIASH_PAR_MAX_UNCALLED_BASE+x} ]; then echo "${VIASH_PAR_MAX_UNCALLED_BASE}" | sed "s#'#'\\"'\\"'#g;s#.*#par_max_uncalled_base='&'#" ; else echo "# par_max_uncalled_base="; fi ) -$( if [ ! -z ${VIASH_PAR_TEST_METHOD+x} ]; then echo "${VIASH_PAR_TEST_METHOD}" | sed "s#'#'\\"'\\"'#g;s#.*#par_test_method='&'#" ; else echo "# par_test_method="; fi ) -$( if [ ! -z ${VIASH_PAR_EMPERICAL_FREQS+x} ]; then echo "${VIASH_PAR_EMPERICAL_FREQS}" | sed "s#'#'\\"'\\"'#g;s#.*#par_emperical_freqs='&'#" ; else echo "# par_emperical_freqs="; fi ) -$( if [ ! -z ${VIASH_PAR_SCORE_METHOD+x} ]; then echo "${VIASH_PAR_SCORE_METHOD}" | sed "s#'#'\\"'\\"'#g;s#.*#par_score_method='&'#" ; else echo "# par_score_method="; fi ) -$( if [ ! -z ${VIASH_PAR_PHRED_BASE+x} ]; then echo "${VIASH_PAR_PHRED_BASE}" | sed "s#'#'\\"'\\"'#g;s#.*#par_phred_base='&'#" ; else echo "# par_phred_base="; fi ) -$( if [ ! -z ${VIASH_PAR_CAP+x} ]; then echo "${VIASH_PAR_CAP}" | sed "s#'#'\\"'\\"'#g;s#.*#par_cap='&'#" ; else echo "# par_cap="; fi ) -$( if [ ! -z ${VIASH_PAR_NBASE+x} ]; then echo "${VIASH_PAR_NBASE}" | sed "s#'#'\\"'\\"'#g;s#.*#par_nbase='&'#" ; else echo "# par_nbase="; fi ) -$( if [ ! -z ${VIASH_META_NAME+x} ]; then echo "${VIASH_META_NAME}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_name='&'#" ; else echo "# meta_name="; fi ) -$( if [ ! -z ${VIASH_META_FUNCTIONALITY_NAME+x} ]; then echo "${VIASH_META_FUNCTIONALITY_NAME}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_functionality_name='&'#" ; else echo "# meta_functionality_name="; fi ) -$( if [ ! -z ${VIASH_META_RESOURCES_DIR+x} ]; then echo "${VIASH_META_RESOURCES_DIR}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_resources_dir='&'#" ; else echo "# meta_resources_dir="; fi ) -$( if [ ! -z ${VIASH_META_EXECUTABLE+x} ]; then echo "${VIASH_META_EXECUTABLE}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_executable='&'#" ; else echo "# meta_executable="; fi ) -$( if [ ! -z ${VIASH_META_CONFIG+x} ]; then echo "${VIASH_META_CONFIG}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_config='&'#" ; else echo "# meta_config="; fi ) -$( if [ ! -z ${VIASH_META_TEMP_DIR+x} ]; then echo "${VIASH_META_TEMP_DIR}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_temp_dir='&'#" ; else echo "# meta_temp_dir="; fi ) -$( if [ ! -z ${VIASH_META_CPUS+x} ]; then echo "${VIASH_META_CPUS}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_cpus='&'#" ; else echo "# meta_cpus="; fi ) -$( if [ ! -z ${VIASH_META_MEMORY_B+x} ]; then echo "${VIASH_META_MEMORY_B}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_b='&'#" ; else echo "# meta_memory_b="; fi ) -$( if [ ! -z ${VIASH_META_MEMORY_KB+x} ]; then echo "${VIASH_META_MEMORY_KB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_kb='&'#" ; else echo "# meta_memory_kb="; fi ) -$( if [ ! -z ${VIASH_META_MEMORY_MB+x} ]; then echo "${VIASH_META_MEMORY_MB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_mb='&'#" ; else echo "# meta_memory_mb="; fi ) -$( if [ ! -z ${VIASH_META_MEMORY_GB+x} ]; then echo "${VIASH_META_MEMORY_GB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_gb='&'#" ; else echo "# meta_memory_gb="; fi ) -$( if [ ! -z ${VIASH_META_MEMORY_TB+x} ]; then echo "${VIASH_META_MEMORY_TB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_tb='&'#" ; else echo "# meta_memory_tb="; fi ) -$( if [ ! -z ${VIASH_META_MEMORY_PB+x} ]; then echo "${VIASH_META_MEMORY_PB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_pb='&'#" ; else echo "# meta_memory_pb="; fi ) -$( if [ ! -z ${VIASH_META_MEMORY_KIB+x} ]; then echo "${VIASH_META_MEMORY_KIB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_kib='&'#" ; else echo "# meta_memory_kib="; fi ) -$( if [ ! -z ${VIASH_META_MEMORY_MIB+x} ]; then echo "${VIASH_META_MEMORY_MIB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_mib='&'#" ; else echo "# meta_memory_mib="; fi ) -$( if [ ! -z ${VIASH_META_MEMORY_GIB+x} ]; then echo "${VIASH_META_MEMORY_GIB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_gib='&'#" ; else echo "# meta_memory_gib="; fi ) -$( if [ ! -z ${VIASH_META_MEMORY_TIB+x} ]; then echo "${VIASH_META_MEMORY_TIB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_tib='&'#" ; else echo "# meta_memory_tib="; fi ) -$( if [ ! -z ${VIASH_META_MEMORY_PIB+x} ]; then echo "${VIASH_META_MEMORY_PIB}" | sed "s#'#'\\"'\\"'#g;s#.*#meta_memory_pib='&'#" ; else echo "# meta_memory_pib="; fi ) - -## VIASH END - -[[ "\\$par_emperical_freqs" == "false" ]] && unset par_emperical_freqs -[[ "\\$par_nbase" == "false" ]] && unset par_nbase - -if [[ "\\${par_forward_fastq##*.}" == "gz" ]]; then - gunzip \\$par_forward_fastq - par_forward_fastq=\\${par_forward_fastq%.*} -fi -if [[ "\\${par_reverse_fastq##*.}" == "gz" ]]; then - gunzip \\$par_reverse_fastq - par_reverse_fastq=\\${par_reverse_fastq%.*} -fi - -output_dir=\\$(mktemp -d -p "\\$meta_temp_dir" "pear.XXXXXX") - -pear \\\\ - -f "\\$par_forward_fastq" \\\\ - -r "\\$par_reverse_fastq" \\\\ - -o "\\$output_dir" \\\\ - \\${par_p_value:+-p "\\${par_p_value}"} \\\\ - \\${par_min_overlap:+-v "\\${par_min_overlap}"} \\\\ - \\${par_max_assembly_length:+-m "\\${par_max_assembly_length}"} \\\\ - \\${par_min_assembly_length:+-n "\\${par_min_assembly_length}"} \\\\ - \\${par_min_trim_length:+-t "\\${par_min_trim_length}"} \\\\ - \\${par_quality_threshold:+-q "\\${par_quality_threshold}"} \\\\ - \\${par_max_uncalled_base:+-u "\\${par_max_uncalled_base}"} \\\\ - \\${par_test_method:+-g "\\${par_test_method}"} \\\\ - \\${par_score_method:+-s "\\${par_score_method}"} \\\\ - \\${par_phred_base:+-b "\\${par_phred_base}"} \\\\ - \\${meta_memory_mb:+--memory "\\${meta_memory_mb}M"} \\\\ - \\${par_cap:+-c "\\${par_cap}"} \\\\ - \\${meta_cpus:+-j "\\${meta_cpus}"} \\\\ - \\${par_emperical_freqs:+-e} \\\\ - \\${par_nbase:+-z} - - -if [[ "\\${par_assembled##*.}" == "gz" ]]; then - gzip -9 -c \\${output_dir}.assembled.fastq > \\${par_assembled} -else - mv \\${output_dir}.assembled.fastq \\${par_assembled} -fi - -if [[ "\\${par_unassembled_forward##*.}" == "gz" ]]; then - gzip -9 -c \\${output_dir}.unassembled.forward.fastq > \\${par_unassembled_forward} -else - mv \\${output_dir}.unassembled.forward.fastq \\${par_unassembled_forward} -fi - -if [[ "\\${par_unassembled_reverse##*.}" == "gz" ]]; then - gzip -9 -c \\${output_dir}.unassembled.reverse.fastq > \\${par_unassembled_reverse} -else - mv \\${output_dir}.unassembled.reverse.fastq \\${par_unassembled_reverse} -fi - -if [[ "\\${par_discarded##*.}" == "gz" ]]; then - gzip -9 -c \\${output_dir}.discarded.fastq > \\${par_discarded} -else - mv \\${output_dir}.discarded.fastq \\${par_discarded} -fi -VIASHMAIN -bash "$tempscript" -''' - - return vdsl3WorkflowFactory(args, meta, rawScript) -} - - - -/** - * Generate a workflow for VDSL3 modules. - * - * This function is called by the workflowFactory() function. - * - * Input channel: [id, input_map] - * Output channel: [id, output_map] - * - * Internally, this workflow will convert the input channel - * to a format which the Nextflow module will be able to handle. - */ -def vdsl3WorkflowFactory(Map args, Map meta, String rawScript) { - def key = args["key"] - def processObj = null - - workflow processWf { - take: input_ - main: - - if (processObj == null) { - processObj = _vdsl3ProcessFactory(args, meta, rawScript) - } - - output_ = input_ - | map { tuple -> - def id = tuple[0] - def data_ = tuple[1] - - if (workflow.stubRun) { - // add id if missing - data_ = [id: 'stub'] + data_ - } - - // process input files separately - def inputPaths = meta.config.allArguments - .findAll { it.type == "file" && it.direction == "input" } - .collect { par -> - def val = data_.containsKey(par.plainName) ? data_[par.plainName] : [] - def inputFiles = [] - if (val == null) { - inputFiles = [] - } else if (val instanceof List) { - inputFiles = val - } else if (val instanceof Path) { - inputFiles = [ val ] - } else { - inputFiles = [] - } - if (!workflow.stubRun) { - // throw error when an input file doesn't exist - inputFiles.each{ file -> - assert file.exists() : - "Error in module '${key}' id '${id}' argument '${par.plainName}'.\n" + - " Required input file does not exist.\n" + - " Path: '$file'.\n" + - " Expected input file to exist" - } - } - inputFiles - } - - // remove input files - def argsExclInputFiles = meta.config.allArguments - .findAll { (it.type != "file" || it.direction != "input") && data_.containsKey(it.plainName) } - .collectEntries { par -> - def parName = par.plainName - def val = data_[parName] - if (par.multiple && val instanceof Collection) { - val = val.join(par.multiple_sep) - } - if (par.direction == "output" && par.type == "file") { - val = val.replaceAll('\\$id', id).replaceAll('\\$key', key) - } - [parName, val] - } - - [ id ] + inputPaths + [ argsExclInputFiles, meta.resources_dir ] - } - | processObj - | map { output -> - def outputFiles = meta.config.allArguments - .findAll { it.type == "file" && it.direction == "output" } - .indexed() - .collectEntries{ index, par -> - def out = output[index + 1] - // strip dummy '.exitcode' file from output (see nextflow-io/nextflow#2678) - if (!out instanceof List || out.size() <= 1) { - if (par.multiple) { - out = [] - } else { - assert !par.required : - "Error in module '${key}' id '${output[0]}' argument '${par.plainName}'.\n" + - " Required output file is missing" - out = null - } - } else if (out.size() == 2 && !par.multiple) { - out = out[1] - } else { - out = out.drop(1) - } - [ par.plainName, out ] - } - - // drop null outputs - outputFiles.removeAll{it.value == null} - - [ output[0], outputFiles ] - } - emit: output_ - } - - return processWf -} - -// depends on: session? -def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { - // autodetect process key - def wfKey = workflowArgs["key"] - def procKeyPrefix = "${wfKey}_process" - def scriptMeta = nextflow.script.ScriptMeta.current() - def existing = scriptMeta.getProcessNames().findAll{it.startsWith(procKeyPrefix)} - def numbers = existing.collect{it.replace(procKeyPrefix, "0").toInteger()} - def newNumber = (numbers + [-1]).max() + 1 - - def procKey = newNumber == 0 ? procKeyPrefix : "$procKeyPrefix$newNumber" - - if (newNumber > 0) { - log.warn "Key for module '${wfKey}' is duplicated.\n", - "If you run a component multiple times in the same workflow,\n" + - "it's recommended you set a unique key for every call,\n" + - "for example: ${wfKey}.run(key: \"foo\")." - } - - // subset directives and convert to list of tuples - def drctv = workflowArgs.directives - - // TODO: unit test the two commands below - // convert publish array into tags - def valueToStr = { val -> - // ignore closures - if (val instanceof CharSequence) { - if (!val.matches('^[{].*[}]$')) { - '"' + val + '"' - } else { - val - } - } else if (val instanceof List) { - "[" + val.collect{valueToStr(it)}.join(", ") + "]" - } else if (val instanceof Map) { - "[" + val.collect{k, v -> k + ": " + valueToStr(v)}.join(", ") + "]" - } else { - val.inspect() - } - } - - // multiple entries allowed: label, publishdir - def drctvStrs = drctv.collect { key, value -> - if (key in ["label", "publishDir"]) { - value.collect{ val -> - if (val instanceof Map) { - "\n$key " + val.collect{ k, v -> k + ": " + valueToStr(v) }.join(", ") - } else if (val == null) { - "" - } else { - "\n$key " + valueToStr(val) - } - }.join() - } else if (value instanceof Map) { - "\n$key " + value.collect{ k, v -> k + ": " + valueToStr(v) }.join(", ") - } else { - "\n$key " + valueToStr(value) - } - }.join() - - def inputPaths = meta.config.allArguments - .findAll { it.type == "file" && it.direction == "input" } - .collect { ', path(viash_par_' + it.plainName + ', stageAs: "_viash_par/' + it.plainName + '_?/*")' } - .join() - - def outputPaths = meta.config.allArguments - .findAll { it.type == "file" && it.direction == "output" } - .collect { par -> - // insert dummy into every output (see nextflow-io/nextflow#2678) - if (!par.multiple) { - ', path{[".exitcode", args.' + par.plainName + ']}' - } else { - ', path{[".exitcode"] + args.' + par.plainName + '}' - } - } - .join() - - // TODO: move this functionality somewhere else? - if (workflowArgs.auto.transcript) { - outputPaths = outputPaths + ', path{[".exitcode", ".command*"]}' - } else { - outputPaths = outputPaths + ', path{[".exitcode"]}' - } - - // create dirs for output files (based on BashWrapper.createParentFiles) - def createParentStr = meta.config.allArguments - .findAll { it.type == "file" && it.direction == "output" && it.create_parent } - .collect { par -> - "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent \\\"\" + (args[\"${par.plainName}\"] instanceof String ? args[\"${par.plainName}\"] : args[\"${par.plainName}\"].join('\" \"')) + \"\\\"\" : \"\" }" - } - .join("\n") - - // construct inputFileExports - def inputFileExports = meta.config.allArguments - .findAll { it.type == "file" && it.direction.toLowerCase() == "input" } - .collect { par -> - def viash_par_contents = "(viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName})" - "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}=\\\"\" + ${viash_par_contents} + \"\\\"\"}" - } - - // NOTE: if using docker, use /tmp instead of tmpDir! - def tmpDir = java.nio.file.Paths.get( - System.getenv('NXF_TEMP') ?: - System.getenv('VIASH_TEMP') ?: - System.getenv('VIASH_TMPDIR') ?: - System.getenv('VIASH_TEMPDIR') ?: - System.getenv('VIASH_TMP') ?: - System.getenv('TEMP') ?: - System.getenv('TMPDIR') ?: - System.getenv('TEMPDIR') ?: - System.getenv('TMP') ?: - '/tmp' - ).toAbsolutePath() - - // construct stub - def stub = meta.config.allArguments - .findAll { it.type == "file" && it.direction == "output" } - .collect { par -> - "\${ args.containsKey(\"${par.plainName}\") ? \"touch2 \\\"\" + (args[\"${par.plainName}\"] instanceof String ? args[\"${par.plainName}\"].replace(\"_*\", \"_0\") : args[\"${par.plainName}\"].join('\" \"')) + \"\\\"\" : \"\" }" - } - .join("\n") - - // escape script - def escapedScript = rawScript.replace('\\', '\\\\').replace('$', '\\$').replace('"""', '\\"\\"\\"') - - // publishdir assert - def assertStr = (workflowArgs.auto.publish == true) || workflowArgs.auto.transcript ? - """\nassert task.publishDir.size() > 0: "if auto.publish is true, params.publish_dir needs to be defined.\\n Example: --publish_dir './output/'" """ : - "" - - // generate process string - def procStr = - """nextflow.enable.dsl=2 - | - |process $procKey {$drctvStrs - |input: - | tuple val(id)$inputPaths, val(args), path(resourcesDir, stageAs: ".viash_meta_resources") - |output: - | tuple val("\$id")$outputPaths, optional: true - |stub: - |\"\"\" - |touch2() { mkdir -p "\\\$(dirname "\\\$1")" && touch "\\\$1" ; } - |$stub - |\"\"\" - |script:$assertStr - |def escapeText = { s -> s.toString().replaceAll('([`"])', '\\\\\\\\\$1') } - |def parInject = args - | .findAll{key, value -> value != null} - | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}=\\\"\${escapeText(value)}\\\""} - | .join("\\n") - |\"\"\" - |# meta exports - |export VIASH_META_RESOURCES_DIR="\${resourcesDir}" - |export VIASH_META_TEMP_DIR="${['docker', 'podman', 'charliecloud'].any{ it == workflow.containerEngine } ? '/tmp' : tmpDir}" - |export VIASH_META_NAME="${meta.config.name}" - |# export VIASH_META_EXECUTABLE="\\\$VIASH_META_RESOURCES_DIR/\\\$VIASH_META_NAME" - |export VIASH_META_CONFIG="\\\$VIASH_META_RESOURCES_DIR/.config.vsh.yaml" - |\${task.cpus ? "export VIASH_META_CPUS=\$task.cpus" : "" } - |\${task.memory?.bytes != null ? "export VIASH_META_MEMORY_B=\$task.memory.bytes" : "" } - |if [ ! -z \\\${VIASH_META_MEMORY_B+x} ]; then - | export VIASH_META_MEMORY_KB=\\\$(( (\\\$VIASH_META_MEMORY_B+999) / 1000 )) - | export VIASH_META_MEMORY_MB=\\\$(( (\\\$VIASH_META_MEMORY_KB+999) / 1000 )) - | export VIASH_META_MEMORY_GB=\\\$(( (\\\$VIASH_META_MEMORY_MB+999) / 1000 )) - | export VIASH_META_MEMORY_TB=\\\$(( (\\\$VIASH_META_MEMORY_GB+999) / 1000 )) - | export VIASH_META_MEMORY_PB=\\\$(( (\\\$VIASH_META_MEMORY_TB+999) / 1000 )) - | export VIASH_META_MEMORY_KIB=\\\$(( (\\\$VIASH_META_MEMORY_B+1023) / 1024 )) - | export VIASH_META_MEMORY_MIB=\\\$(( (\\\$VIASH_META_MEMORY_KIB+1023) / 1024 )) - | export VIASH_META_MEMORY_GIB=\\\$(( (\\\$VIASH_META_MEMORY_MIB+1023) / 1024 )) - | export VIASH_META_MEMORY_TIB=\\\$(( (\\\$VIASH_META_MEMORY_GIB+1023) / 1024 )) - | export VIASH_META_MEMORY_PIB=\\\$(( (\\\$VIASH_META_MEMORY_TIB+1023) / 1024 )) - |fi - | - |# meta synonyms - |export VIASH_TEMP="\\\$VIASH_META_TEMP_DIR" - |export TEMP_DIR="\\\$VIASH_META_TEMP_DIR" - | - |# create output dirs if need be - |function mkdir_parent { - | for file in "\\\$@"; do - | mkdir -p "\\\$(dirname "\\\$file")" - | done - |} - |$createParentStr - | - |# argument exports${inputFileExports.join()} - |\$parInject - | - |# process script - |${escapedScript} - |\"\"\" - |} - |""".stripMargin() - - // TODO: print on debug - // if (workflowArgs.debug == true) { - // println("######################\n$procStr\n######################") - // } - - // write process to temp file - def tempFile = java.nio.file.Files.createTempFile("viash-process-${procKey}-", ".nf") - addShutdownHook { java.nio.file.Files.deleteIfExists(tempFile) } - tempFile.text = procStr - - // create process from temp file - def binding = new nextflow.script.ScriptBinding([:]) - def session = nextflow.Nextflow.getSession() - def parser = new nextflow.script.ScriptParser(session) - .setModule(true) - .setBinding(binding) - def moduleScript = parser.runScript(tempFile) - .getScript() - - // register module in meta - def module = new nextflow.script.IncludeDef.Module(name: procKey) - scriptMeta.addModule(moduleScript, module.name, module.alias) - - // retrieve and return process from meta - return scriptMeta.getProcess(procKey) -} - -// defaults -meta["defaults"] = [ - // key to be used to trace the process and determine output names - key: null, - - // fixed arguments to be passed to script - args: [:], - - // default directives - directives: readJsonBlob('''{ - "container" : { - "registry" : "images.viash-hub.com", - "image" : "vsh/biobox/pear", - "tag" : "v0.1.0" - }, - "tag" : "$id" -}'''), - - // auto settings - auto: readJsonBlob('''{ - "simplifyInput" : true, - "simplifyOutput" : false, - "transcript" : false, - "publish" : false -}'''), - - // Apply a map over the incoming tuple - // Example: `{ tup -> [ tup[0], [input: tup[1].output] ] + tup.drop(2) }` - map: null, - - // Apply a map over the ID element of a tuple (i.e. the first element) - // Example: `{ id -> id + "_foo" }` - mapId: null, - - // Apply a map over the data element of a tuple (i.e. the second element) - // Example: `{ data -> [ input: data.output ] }` - mapData: null, - - // Apply a map over the passthrough elements of a tuple (i.e. the tuple excl. the first two elements) - // Example: `{ pt -> pt.drop(1) }` - mapPassthrough: null, - - // Filter the channel - // Example: `{ tup -> tup[0] == "foo" }` - filter: null, - - // Choose whether or not to run the component on the tuple if the condition is true. - // Otherwise, the tuple will be passed through. - // Example: `{ tup -> tup[0] != "skip_this" }` - runIf: null, - - // Rename keys in the data field of the tuple (i.e. the second element) - // Will likely be deprecated in favour of `fromState`. - // Example: `[ "new_key": "old_key" ]` - renameKeys: null, - - // Fetch data from the state and pass it to the module without altering the current state. - // - // `fromState` should be `null`, `List[String]`, `Map[String, String]` or a function. - // - // - If it is `null`, the state will be passed to the module as is. - // - If it is a `List[String]`, the data will be the values of the state at the given keys. - // - If it is a `Map[String, String]`, the data will be the values of the state at the given keys, with the keys renamed according to the map. - // - If it is a function, the tuple (`[id, state]`) in the channel will be passed to the function, and the result will be used as the data. - // - // Example: `{ id, state -> [input: state.fastq_file] }` - // Default: `null` - fromState: null, - - // Determine how the state should be updated after the module has been run. - // - // `toState` should be `null`, `List[String]`, `Map[String, String]` or a function. - // - // - If it is `null`, the state will be replaced with the output of the module. - // - If it is a `List[String]`, the state will be updated with the values of the data at the given keys. - // - If it is a `Map[String, String]`, the state will be updated with the values of the data at the given keys, with the keys renamed according to the map. - // - If it is a function, a tuple (`[id, output, state]`) will be passed to the function, and the result will be used as the new state. - // - // Example: `{ id, output, state -> state + [counts: state.output] }` - // Default: `{ id, output, state -> output }` - toState: null, - - // Whether or not to print debug messages - // Default: `false` - debug: false -] - -// initialise default workflow -meta["workflow"] = workflowFactory([key: meta.config.name], meta.defaults, meta) - -// add workflow to environment -nextflow.script.ScriptMeta.current().addDefinition(meta.workflow) - -// anonymous workflow for running this module as a standalone -workflow { - // add id argument if it's not already in the config - // TODO: deep copy - def newConfig = deepClone(meta.config) - def newParams = deepClone(params) - - def argsContainsId = newConfig.allArguments.any{it.plainName == "id"} - if (!argsContainsId) { - def idArg = [ - 'name': '--id', - 'required': false, - 'type': 'string', - 'description': 'A unique id for every entry.', - 'multiple': false - ] - newConfig.arguments.add(0, idArg) - newConfig = processConfig(newConfig) - } - if (!newParams.containsKey("id")) { - newParams.id = "run" - } - - helpMessage(newConfig) - - channelFromParams(newParams, newConfig) - // make sure id is not in the state if id is not in the args - | map {id, state -> - if (!argsContainsId) { - [id, state.findAll{k, v -> k != "id"}] - } else { - [id, state] - } - } - | meta.workflow.run( - auto: [ publish: "state" ] - ) -} - -// END COMPONENT-SPECIFIC CODE diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/nextflow.config b/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/nextflow.config deleted file mode 100644 index b4a0ff1..0000000 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/nextflow.config +++ /dev/null @@ -1,125 +0,0 @@ -manifest { - name = 'pear' - mainScript = 'main.nf' - nextflowVersion = '!>=20.12.1-edge' - version = 'v0.1.0' - description = 'PEAR is an ultrafast, memory-efficient and highly accurate pair-end read merger. It is fully parallelized and can run with as low as just a few kilobytes of memory.\n\nPEAR evaluates all possible paired-end read overlaps and without requiring the target fragment size as input. In addition, it implements a statistical test for minimizing false-positive results. Together with a highly optimized implementation, it can merge millions of paired end reads within a couple of minutes on a standard desktop computer.\n' -} - -process.container = 'nextflow/bash:latest' - -// detect tempdir -tempDir = java.nio.file.Paths.get( - System.getenv('NXF_TEMP') ?: - System.getenv('VIASH_TEMP') ?: - System.getenv('TEMPDIR') ?: - System.getenv('TMPDIR') ?: - '/tmp' -).toAbsolutePath() - -profiles { - no_publish { - process { - withName: '.*' { - publishDir = [ - enabled: false - ] - } - } - } - mount_temp { - docker.temp = tempDir - podman.temp = tempDir - charliecloud.temp = tempDir - } - docker { - docker.enabled = true - // docker.userEmulation = true - singularity.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false - } - singularity { - singularity.enabled = true - singularity.autoMounts = true - docker.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false - } - podman { - podman.enabled = true - docker.enabled = false - singularity.enabled = false - shifter.enabled = false - charliecloud.enabled = false - } - shifter { - shifter.enabled = true - docker.enabled = false - singularity.enabled = false - podman.enabled = false - charliecloud.enabled = false - } - charliecloud { - charliecloud.enabled = true - docker.enabled = false - singularity.enabled = false - podman.enabled = false - shifter.enabled = false - } -} - -process{ - withLabel: mem1gb { memory = 1000000000.B } - withLabel: mem2gb { memory = 2000000000.B } - withLabel: mem5gb { memory = 5000000000.B } - withLabel: mem10gb { memory = 10000000000.B } - withLabel: mem20gb { memory = 20000000000.B } - withLabel: mem50gb { memory = 50000000000.B } - withLabel: mem100gb { memory = 100000000000.B } - withLabel: mem200gb { memory = 200000000000.B } - withLabel: mem500gb { memory = 500000000000.B } - withLabel: mem1tb { memory = 1000000000000.B } - withLabel: mem2tb { memory = 2000000000000.B } - withLabel: mem5tb { memory = 5000000000000.B } - withLabel: mem10tb { memory = 10000000000000.B } - withLabel: mem20tb { memory = 20000000000000.B } - withLabel: mem50tb { memory = 50000000000000.B } - withLabel: mem100tb { memory = 100000000000000.B } - withLabel: mem200tb { memory = 200000000000000.B } - withLabel: mem500tb { memory = 500000000000000.B } - withLabel: mem1gib { memory = 1073741824.B } - withLabel: mem2gib { memory = 2147483648.B } - withLabel: mem4gib { memory = 4294967296.B } - withLabel: mem8gib { memory = 8589934592.B } - withLabel: mem16gib { memory = 17179869184.B } - withLabel: mem32gib { memory = 34359738368.B } - withLabel: mem64gib { memory = 68719476736.B } - withLabel: mem128gib { memory = 137438953472.B } - withLabel: mem256gib { memory = 274877906944.B } - withLabel: mem512gib { memory = 549755813888.B } - withLabel: mem1tib { memory = 1099511627776.B } - withLabel: mem2tib { memory = 2199023255552.B } - withLabel: mem4tib { memory = 4398046511104.B } - withLabel: mem8tib { memory = 8796093022208.B } - withLabel: mem16tib { memory = 17592186044416.B } - withLabel: mem32tib { memory = 35184372088832.B } - withLabel: mem64tib { memory = 70368744177664.B } - withLabel: mem128tib { memory = 140737488355328.B } - withLabel: mem256tib { memory = 281474976710656.B } - withLabel: mem512tib { memory = 562949953421312.B } - withLabel: cpu1 { cpus = 1 } - withLabel: cpu2 { cpus = 2 } - withLabel: cpu5 { cpus = 5 } - withLabel: cpu10 { cpus = 10 } - withLabel: cpu20 { cpus = 20 } - withLabel: cpu50 { cpus = 50 } - withLabel: cpu100 { cpus = 100 } - withLabel: cpu200 { cpus = 200 } - withLabel: cpu500 { cpus = 500 } - withLabel: cpu1000 { cpus = 1000 } -} - - diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/nextflow_schema.json b/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/nextflow_schema.json deleted file mode 100644 index 77dee5c..0000000 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/nextflow_schema.json +++ /dev/null @@ -1,284 +0,0 @@ -{ -"$schema": "http://json-schema.org/draft-07/schema", -"title": "pear", -"description": "PEAR is an ultrafast, memory-efficient and highly accurate pair-end read merger. It is fully parallelized and can run with as low as just a few kilobytes of memory.\n\nPEAR evaluates all possible paired-end read overlaps and without requiring the target fragment size as input. In addition, it implements a statistical test for minimizing false-positive results. Together with a highly optimized implementation, it can merge millions of paired end reads within a couple of minutes on a standard desktop computer.\n", -"type": "object", -"definitions": { - - - - "inputs" : { - "title": "Inputs", - "type": "object", - "description": "No description", - "properties": { - - - "forward_fastq": { - "type": - "string", - "description": "Type: `file`, required, example: `forward.fastq`. Forward paired-end FASTQ file", - "help_text": "Type: `file`, required, example: `forward.fastq`. Forward paired-end FASTQ file" - - } - - - , - "reverse_fastq": { - "type": - "string", - "description": "Type: `file`, required, example: `reverse.fastq`. Reverse paired-end FASTQ file", - "help_text": "Type: `file`, required, example: `reverse.fastq`. Reverse paired-end FASTQ file" - - } - - -} -}, - - - "outputs" : { - "title": "Outputs", - "type": "object", - "description": "No description", - "properties": { - - - "assembled": { - "type": - "string", - "description": "Type: `file`, required, default: `$id.$key.assembled.assembled`. The output file containing assembled reads", - "help_text": "Type: `file`, required, default: `$id.$key.assembled.assembled`. The output file containing assembled reads. Can be compressed with gzip." - , - "default": "$id.$key.assembled.assembled" - } - - - , - "unassembled_forward": { - "type": - "string", - "description": "Type: `file`, required, default: `$id.$key.unassembled_forward.unassembled_forward`. The output file containing forward reads that could not be assembled", - "help_text": "Type: `file`, required, default: `$id.$key.unassembled_forward.unassembled_forward`. The output file containing forward reads that could not be assembled. Can be compressed with gzip." - , - "default": "$id.$key.unassembled_forward.unassembled_forward" - } - - - , - "unassembled_reverse": { - "type": - "string", - "description": "Type: `file`, required, default: `$id.$key.unassembled_reverse.unassembled_reverse`. The output file containing reverse reads that could not be assembled", - "help_text": "Type: `file`, required, default: `$id.$key.unassembled_reverse.unassembled_reverse`. The output file containing reverse reads that could not be assembled. Can be compressed with gzip." - , - "default": "$id.$key.unassembled_reverse.unassembled_reverse" - } - - - , - "discarded": { - "type": - "string", - "description": "Type: `file`, required, default: `$id.$key.discarded.discarded`. The output file containing reads that were discarded due to too low quality or too many uncalled bases", - "help_text": "Type: `file`, required, default: `$id.$key.discarded.discarded`. The output file containing reads that were discarded due to too low quality or too many uncalled bases. Can be compressed with gzip." - , - "default": "$id.$key.discarded.discarded" - } - - -} -}, - - - "arguments" : { - "title": "Arguments", - "type": "object", - "description": "No description", - "properties": { - - - "p_value": { - "type": - "number", - "description": "Type: `double`, example: `0.01`. Specify a p-value for the statistical test", - "help_text": "Type: `double`, example: `0.01`. Specify a p-value for the statistical test. If the computed p-value of a possible assembly exceeds the specified p-value then paired-end read will not be assembled. Valid options are: 0.0001, 0.001, 0.01, 0.05 and 1.0. Setting 1.0 disables the test.\n" - - } - - - , - "min_overlap": { - "type": - "integer", - "description": "Type: `integer`, example: `10`. Specify the minimum overlap size", - "help_text": "Type: `integer`, example: `10`. Specify the minimum overlap size. The minimum overlap may be set to 1 when the statistical test is used. However, further restricting the minimum overlap size to a proper value may reduce false-positive assembles.\n" - - } - - - , - "max_assembly_length": { - "type": - "integer", - "description": "Type: `integer`, example: `0`. Specify the maximum possible length of the assembled sequences", - "help_text": "Type: `integer`, example: `0`. Specify the maximum possible length of the assembled sequences. Setting this value to 0 disables the restriction and assembled sequences may be arbitrary long.\n" - - } - - - , - "min_assembly_length": { - "type": - "integer", - "description": "Type: `integer`, example: `0`. Specify the minimum possible length of the assembled sequences", - "help_text": "Type: `integer`, example: `0`. Specify the minimum possible length of the assembled sequences. Setting this value to 0 disables the restriction and assembled sequences may be arbitrary short.\n" - - } - - - , - "min_trim_length": { - "type": - "integer", - "description": "Type: `integer`, example: `1`. Specify the minimum length of reads after trimming the low quality part (see option -q)\n", - "help_text": "Type: `integer`, example: `1`. Specify the minimum length of reads after trimming the low quality part (see option -q)\n" - - } - - - , - "quality_threshold": { - "type": - "integer", - "description": "Type: `integer`, example: `0`. Specify the quality threshold for trimming the low quality part of a read", - "help_text": "Type: `integer`, example: `0`. Specify the quality threshold for trimming the low quality part of a read. If the quality scores of two consecutive bases are strictly less than the specified threshold, the rest of the read will be trimmed.\n" - - } - - - , - "max_uncalled_base": { - "type": - "number", - "description": "Type: `double`, example: `1.0`. Specify the maximal proportion of uncalled bases in a read", - "help_text": "Type: `double`, example: `1.0`. Specify the maximal proportion of uncalled bases in a read. Setting this value to 0 will cause PEAR to discard all reads containing uncalled bases. The other extreme setting is 1 which causes PEAR to process all reads independent on the number of uncalled bases.\n" - - } - - - , - "test_method": { - "type": - "integer", - "description": "Type: `integer`, example: `1`. Specify the type of statistical test", - "help_text": "Type: `integer`, example: `1`. Specify the type of statistical test. Two options are available. 1: Given the minimum allowed overlap, test using the highest OES. Note that due to its discrete nature, this test usually yields a lower p-value for the assembled read than the cut- off (specified by -p). For example, setting the cut-off to 0.05 using this test, the assembled reads might have an actual p-value of 0.02.\n2. Use the acceptance probability (m.a.p). This test methods computes the same probability as test method 1. However, it assumes that the minimal overlap is the observed overlap with the highest OES, instead of the one specified by -v. Therefore, this is not a valid statistical test and the \u0027p-value\u0027 is in fact the maximal probability for accepting the assembly. Nevertheless, we observed in practice that for the case the actual overlap sizes are relatively small, test 2 can correctly assemble more reads with only slightly higher false-positive rate.\n" - - } - - - , - "emperical_freqs": { - "type": - "boolean", - "description": "Type: `boolean_true`, default: `false`. Disable empirical base frequencies", - "help_text": "Type: `boolean_true`, default: `false`. Disable empirical base frequencies.\n" - , - "default": "False" - } - - - , - "score_method": { - "type": - "integer", - "description": "Type: `integer`, example: `2`. Specify the scoring method", - "help_text": "Type: `integer`, example: `2`. Specify the scoring method. 1. OES with +1 for match and -1 for mismatch. 2: Assembly score (AS). Use +1 for match and -1 for mismatch multiplied by base quality scores. 3: Ignore quality scores and use +1 for a match and -1 for a mismatch.\n" - - } - - - , - "phred_base": { - "type": - "integer", - "description": "Type: `integer`, example: `33`. Base PHRED quality score", - "help_text": "Type: `integer`, example: `33`. Base PHRED quality score.\n" - - } - - - , - "cap": { - "type": - "integer", - "description": "Type: `integer`, example: `40`. Specify the upper bound for the resulting quality score", - "help_text": "Type: `integer`, example: `40`. Specify the upper bound for the resulting quality score. If set to zero, capping is disabled.\n" - - } - - - , - "nbase": { - "type": - "boolean", - "description": "Type: `boolean_true`, default: `false`. When merging a base-pair that consists of two non-equal bases out of which none is degenerate, set the merged base to N and use the highest quality score of the two bases\n", - "help_text": "Type: `boolean_true`, default: `false`. When merging a base-pair that consists of two non-equal bases out of which none is degenerate, set the merged base to N and use the highest quality score of the two bases\n" - , - "default": "False" - } - - -} -}, - - - "nextflow input-output arguments" : { - "title": "Nextflow input-output arguments", - "type": "object", - "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", - "properties": { - - - "publish_dir": { - "type": - "string", - "description": "Type: `string`, required, example: `output/`. Path to an output directory", - "help_text": "Type: `string`, required, example: `output/`. Path to an output directory." - - } - - - , - "param_list": { - "type": - "string", - "description": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel", - "help_text": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel. A `param_list` can either be a list of maps, a csv file, a json file, a yaml file, or simply a yaml blob.\n\n* A list of maps (as-is) where the keys of each map corresponds to the arguments of the pipeline. Example: in a `nextflow.config` file: `param_list: [ [\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027], [\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027] ]`.\n* A csv file should have column names which correspond to the different arguments of this pipeline. Example: `--param_list data.csv` with columns `id,input`.\n* A json or a yaml file should be a list of maps, each of which has keys corresponding to the arguments of the pipeline. Example: `--param_list data.json` with contents `[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]`.\n* A yaml blob can also be passed directly as a string. Example: `--param_list \"[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]\"`.\n\nWhen passing a csv, json or yaml file, relative path names are relativized to the location of the parameter file. No relativation is performed when `param_list` is a list of maps (as-is) or a yaml blob.", - "hidden": true - - } - - -} -} -}, -"allOf": [ - - { - "$ref": "#/definitions/inputs" - }, - - { - "$ref": "#/definitions/outputs" - }, - - { - "$ref": "#/definitions/arguments" - }, - - { - "$ref": "#/definitions/nextflow input-output arguments" - } -] -} diff --git a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/nextflow_schema.json b/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/nextflow_schema.json deleted file mode 100644 index 6c1dc14..0000000 --- a/target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/nextflow_schema.json +++ /dev/null @@ -1,171 +0,0 @@ -{ -"$schema": "http://json-schema.org/draft-07/schema", -"title": "star_align_reads", -"description": "Aligns reads to a reference genome using STAR.\n", -"type": "object", -"definitions": { - - - - "inputs" : { - "title": "Inputs", - "type": "object", - "description": "No description", - "properties": { - - - "input": { - "type": - "string", - "description": "Type: List of `file`, required, example: `mysample_S1_L001_R1_001.fastq.gz`, multiple_sep: `\":\"`. The single-end or paired-end R1 FastQ files to be processed", - "help_text": "Type: List of `file`, required, example: `mysample_S1_L001_R1_001.fastq.gz`, multiple_sep: `\":\"`. The single-end or paired-end R1 FastQ files to be processed." - - } - - - , - "input_r2": { - "type": - "string", - "description": "Type: List of `file`, example: `mysample_S1_L001_R2_001.fastq.gz`, multiple_sep: `\":\"`. The paired-end R2 FastQ files to be processed", - "help_text": "Type: List of `file`, example: `mysample_S1_L001_R2_001.fastq.gz`, multiple_sep: `\":\"`. The paired-end R2 FastQ files to be processed. Only required if --input is a paired-end R1 file." - - } - - -} -}, - - - "outputs" : { - "title": "Outputs", - "type": "object", - "description": "No description", - "properties": { - - - "aligned_reads": { - "type": - "string", - "description": "Type: `file`, required, default: `$id.$key.aligned_reads.bam`, example: `aligned_reads.bam`. The output file containing the aligned reads", - "help_text": "Type: `file`, required, default: `$id.$key.aligned_reads.bam`, example: `aligned_reads.bam`. The output file containing the aligned reads." - , - "default": "$id.$key.aligned_reads.bam" - } - - - , - "reads_per_gene": { - "type": - "string", - "description": "Type: `file`, default: `$id.$key.reads_per_gene.tsv`, example: `reads_per_gene.tsv`. The output file containing the number of reads per gene", - "help_text": "Type: `file`, default: `$id.$key.reads_per_gene.tsv`, example: `reads_per_gene.tsv`. The output file containing the number of reads per gene." - , - "default": "$id.$key.reads_per_gene.tsv" - } - - - , - "unmapped": { - "type": - "string", - "description": "Type: `file`, default: `$id.$key.unmapped.fastq`, example: `unmapped.fastq`. The output file containing the unmapped reads", - "help_text": "Type: `file`, default: `$id.$key.unmapped.fastq`, example: `unmapped.fastq`. The output file containing the unmapped reads." - , - "default": "$id.$key.unmapped.fastq" - } - - - , - "unmapped_r2": { - "type": - "string", - "description": "Type: `file`, default: `$id.$key.unmapped_r2.fastq`, example: `unmapped_r2.fastq`. The output file containing the unmapped R2 reads", - "help_text": "Type: `file`, default: `$id.$key.unmapped_r2.fastq`, example: `unmapped_r2.fastq`. The output file containing the unmapped R2 reads." - , - "default": "$id.$key.unmapped_r2.fastq" - } - - - , - "chimeric_junctions": { - "type": - "string", - "description": "Type: `file`, default: `$id.$key.chimeric_junctions.tsv`, example: `chimeric_junctions.tsv`. The output file containing the chimeric junctions", - "help_text": "Type: `file`, default: `$id.$key.chimeric_junctions.tsv`, example: `chimeric_junctions.tsv`. The output file containing the chimeric junctions." - , - "default": "$id.$key.chimeric_junctions.tsv" - } - - - , - "log": { - "type": - "string", - "description": "Type: `file`, default: `$id.$key.log.txt`, example: `log.txt`. The output file containing the log of the alignment process", - "help_text": "Type: `file`, default: `$id.$key.log.txt`, example: `log.txt`. The output file containing the log of the alignment process." - , - "default": "$id.$key.log.txt" - } - - - , - "splice_junctions": { - "type": - "string", - "description": "Type: `file`, default: `$id.$key.splice_junctions.tsv`, example: `splice_junctions.tsv`. The output file containing the splice junctions", - "help_text": "Type: `file`, default: `$id.$key.splice_junctions.tsv`, example: `splice_junctions.tsv`. The output file containing the splice junctions." - , - "default": "$id.$key.splice_junctions.tsv" - } - - -} -}, - - - "nextflow input-output arguments" : { - "title": "Nextflow input-output arguments", - "type": "object", - "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", - "properties": { - - - "publish_dir": { - "type": - "string", - "description": "Type: `string`, required, example: `output/`. Path to an output directory", - "help_text": "Type: `string`, required, example: `output/`. Path to an output directory." - - } - - - , - "param_list": { - "type": - "string", - "description": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel", - "help_text": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel. A `param_list` can either be a list of maps, a csv file, a json file, a yaml file, or simply a yaml blob.\n\n* A list of maps (as-is) where the keys of each map corresponds to the arguments of the pipeline. Example: in a `nextflow.config` file: `param_list: [ [\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027], [\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027] ]`.\n* A csv file should have column names which correspond to the different arguments of this pipeline. Example: `--param_list data.csv` with columns `id,input`.\n* A json or a yaml file should be a list of maps, each of which has keys corresponding to the arguments of the pipeline. Example: `--param_list data.json` with contents `[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]`.\n* A yaml blob can also be passed directly as a string. Example: `--param_list \"[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]\"`.\n\nWhen passing a csv, json or yaml file, relative path names are relativized to the location of the parameter file. No relativation is performed when `param_list` is a list of maps (as-is) or a yaml blob.", - "hidden": true - - } - - -} -} -}, -"allOf": [ - - { - "$ref": "#/definitions/inputs" - }, - - { - "$ref": "#/definitions/outputs" - }, - - { - "$ref": "#/definitions/nextflow input-output arguments" - } -] -} diff --git a/target/nextflow/mapping_and_qc/.config.vsh.yaml b/target/nextflow/mapping_and_qc/.config.vsh.yaml index 9be9983..4c715c1 100644 --- a/target/nextflow/mapping_and_qc/.config.vsh.yaml +++ b/target/nextflow/mapping_and_qc/.config.vsh.yaml @@ -59,37 +59,32 @@ dependencies: repository: type: "vsh" repo: "vsh/biobox" - tag: "v0.1" -- name: "pear" - repository: - type: "vsh" - repo: "vsh/biobox" - tag: "v0.1" + tag: "main" - name: "falco" repository: type: "vsh" repo: "vsh/biobox" - tag: "v0.1" + tag: "main" - name: "multiqc" repository: type: "vsh" repo: "vsh/biobox" - tag: "v0.1" + tag: "main" - name: "star/star_align_reads" repository: type: "vsh" repo: "vsh/biobox" - tag: "v0.1" + tag: "main" - name: "samtools/samtools_stats" repository: type: "vsh" repo: "vsh/biobox" - tag: "v0.1" + tag: "main" repositories: - type: "vsh" name: "bb" repo: "vsh/biobox" - tag: "v0.1" + tag: "main" license: "MIT" links: repository: "https://github.com/viash-hub/playground" @@ -167,15 +162,14 @@ build_info: output: "target/nextflow/mapping_and_qc" executable: "target/nextflow/mapping_and_qc/main.nf" viash_version: "0.9.0-RC6" - git_commit: "ec3c23e349a796e57e6634e140325afde4515bbf" + git_commit: "861319f5ddc22d51899493bcd30e7066c42193cb" git_remote: "https://github.com/viash-hub/playground" dependencies: - - "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt" - - "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear" - - "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco" - - "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc" - - "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads" - - "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats" + - "target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt" + - "target/dependencies/vsh/vsh/biobox/main/nextflow/falco" + - "target/dependencies/vsh/vsh/biobox/main/nextflow/multiqc" + - "target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads" + - "target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats" package_config: name: "playground" version: "main" diff --git a/target/nextflow/mapping_and_qc/main.nf b/target/nextflow/mapping_and_qc/main.nf index 6072477..614b891 100644 --- a/target/nextflow/mapping_and_qc/main.nf +++ b/target/nextflow/mapping_and_qc/main.nf @@ -2856,15 +2856,7 @@ meta = [ "repository" : { "type" : "vsh", "repo" : "vsh/biobox", - "tag" : "v0.1" - } - }, - { - "name" : "pear", - "repository" : { - "type" : "vsh", - "repo" : "vsh/biobox", - "tag" : "v0.1" + "tag" : "main" } }, { @@ -2872,7 +2864,7 @@ meta = [ "repository" : { "type" : "vsh", "repo" : "vsh/biobox", - "tag" : "v0.1" + "tag" : "main" } }, { @@ -2880,7 +2872,7 @@ meta = [ "repository" : { "type" : "vsh", "repo" : "vsh/biobox", - "tag" : "v0.1" + "tag" : "main" } }, { @@ -2888,7 +2880,7 @@ meta = [ "repository" : { "type" : "vsh", "repo" : "vsh/biobox", - "tag" : "v0.1" + "tag" : "main" } }, { @@ -2896,7 +2888,7 @@ meta = [ "repository" : { "type" : "vsh", "repo" : "vsh/biobox", - "tag" : "v0.1" + "tag" : "main" } } ], @@ -2905,7 +2897,7 @@ meta = [ "type" : "vsh", "name" : "bb", "repo" : "vsh/biobox", - "tag" : "v0.1" + "tag" : "main" } ], "license" : "MIT", @@ -2997,7 +2989,7 @@ meta = [ "engine" : "native|native", "output" : "target/nextflow/mapping_and_qc", "viash_version" : "0.9.0-RC6", - "git_commit" : "ec3c23e349a796e57e6634e140325afde4515bbf", + "git_commit" : "861319f5ddc22d51899493bcd30e7066c42193cb", "git_remote" : "https://github.com/viash-hub/playground" }, "package_config" : { @@ -3033,12 +3025,11 @@ meta = [ // resolve dependencies dependencies (if any) meta["root_dir"] = getRootDir() -include { cutadapt } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/v0.1/nextflow/cutadapt/main.nf" -include { pear } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/v0.1/nextflow/pear/main.nf" -include { falco } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/v0.1/nextflow/falco/main.nf" -include { multiqc } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/v0.1/nextflow/multiqc/main.nf" -include { star_align_reads } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/v0.1/nextflow/star/star_align_reads/main.nf" -include { samtools_stats } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats/main.nf" +include { cutadapt } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/main.nf" +include { falco } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/main/nextflow/falco/main.nf" +include { multiqc } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/main/nextflow/multiqc/main.nf" +include { star_align_reads } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/main/nextflow/star/star_align_reads/main.nf" +include { samtools_stats } from "${meta.root_dir}/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats/main.nf" // inner workflow // user-provided Nextflow code @@ -3061,14 +3052,18 @@ workflow run_wf { }, toState: [ "output_falco": "outdir", - ] + ], + directives: [label: ["lowmem", "lowcpu"]] ) + | niceView() | cutadapt.run( fromState: {id, state -> [ "input": state.input_r1, "input_r2": state.input_r2, - "quality_cutoff": "20", // Could make this a parameter + "quality_cutoff": "30", // Could make this a parameter + "quality_cutoff_r2": "30", // Could make this a parameter + "minimum_length": "60:60", // Could make this a parameter "adapter": "CTGTCTCTTATACACATCT", // Could make this a parameter "adapter_r2": "CTGTCTCTTATACACATCT", // Could make this a parameter "output": "*.fastq", @@ -3078,29 +3073,23 @@ workflow run_wf { def newKeys = [ "trimmed_r1": output_state["output"][0], "trimmed_r2": output_state["output"][1], - "output_cutadapt": output_state["output"] ] def new_state = state + newKeys return new_state - } - ) - | pear.run( - fromState: [ - "forward_fastq": "trimmed_r1", - "reverse_fastq": "trimmed_r2", - ], - toState: [ - "output_pear": "assembled", - ] + }, + directives: [label: ["midmem", "midmem"]] ) | star_align_reads.run( fromState: [ - "input": "output_pear", - "genomeDir": "reference", + "input": "trimmed_r1", + "input_r2": "trimmed_r2", + "genome_dir": "reference", ], toState: [ "output_star": "aligned_reads", - ] + ], + directives: [label: ["highmem", "midcpu"]] + ) | samtools_stats.run( fromState: [ @@ -3108,7 +3097,9 @@ workflow run_wf { ], toState: [ "output_samtools_stats": "output", - ] + ], + directives: [label: ["midmem", "lowcpu"]] + ) | toSortedList() | map { events -> @@ -3125,7 +3116,9 @@ workflow run_wf { ], toState: [ "multiqc_output": "output_report", - ] + ], + directives: [label: ["midmem", "lowcpu"]] + ) | setState(["multiqc_output", "_meta"]) diff --git a/target/nextflow/mapping_and_qc/nextflow_schema.json b/target/nextflow/mapping_and_qc/nextflow_schema.json index cb9a4bd..fb1f783 100644 --- a/target/nextflow/mapping_and_qc/nextflow_schema.json +++ b/target/nextflow/mapping_and_qc/nextflow_schema.json @@ -60,7 +60,7 @@ "description": "Type: `file`, required, default: `$id.$key.multiqc_output.html`, example: `multiqc.html`. ", "help_text": "Type: `file`, required, default: `$id.$key.multiqc_output.html`, example: `multiqc.html`. " , - "default": "$id.$key.multiqc_output.html" + "default":"$id.$key.multiqc_output.html" } diff --git a/test_data.sh b/test_data.sh index 581c3fe..c96feca 100755 --- a/test_data.sh +++ b/test_data.sh @@ -15,6 +15,11 @@ if [ ! -f "$TEST_DATA_DIR/SRR1570800_1.fastq" ] || [ ! -f "$TEST_DATA_DIR/SRR157 docker run -t --rm -v $PWD:/output:rw -w /output/test_data ncbi/sra-tools fasterq-dump -e 2 -p SRR1570800 fi +head -n 10000 "$TEST_DATA_DIR/SRR1569895_1.fastq" > "$TEST_DATA_DIR/SRR1569895_1_subsample.fastq" +head -n 10000 "$TEST_DATA_DIR/SRR1569895_2.fastq" > "$TEST_DATA_DIR/SRR1569895_2_subsample.fastq" +head -n 10000 "$TEST_DATA_DIR/SRR1570800_1.fastq" > "$TEST_DATA_DIR/SRR1570800_1_subsample.fastq" +head -n 10000 "$TEST_DATA_DIR/SRR1570800_2.fastq" > "$TEST_DATA_DIR/SRR1570800_2_subsample.fastq" + export NXF_SCM_FILE="$TEST_DATA_DIR/scm.config" cat > $NXF_SCM_FILE << EOF @@ -39,8 +44,8 @@ if [ ! -d "$TEST_DATA_DIR/S288C_reference_genome_Current_Release" ]; then --publish_dir "$TEST_DATA_DIR" fi -zcat "$TEST_DATA_DIR/S288C_reference_genome_Current_Release/S288C_reference_sequence_R64-5-1_20240529.fsa.gz" > "$TEST_DATA_DIR/S288C_reference_genome_Current_Release/S288C_reference_sequence_R64-5-1_20240529.fsa" -zcat "$TEST_DATA_DIR/S288C_reference_genome_Current_Release/saccharomyces_cerevisiae_R64-5-1_20240529.gff.gz" > "$TEST_DATA_DIR/S288C_reference_genome_Current_Release/saccharomyces_cerevisiae_R64-5-1_20240529.gff" +gunzip -c "$TEST_DATA_DIR/S288C_reference_genome_Current_Release/S288C_reference_sequence_R64-5-1_20240529.fsa.gz" > "$TEST_DATA_DIR/S288C_reference_genome_Current_Release/S288C_reference_sequence_R64-5-1_20240529.fsa" +gunzip -c "$TEST_DATA_DIR/S288C_reference_genome_Current_Release/saccharomyces_cerevisiae_R64-5-1_20240529.gff.gz" > "$TEST_DATA_DIR/S288C_reference_genome_Current_Release/saccharomyces_cerevisiae_R64-5-1_20240529.gff" sed -i -e 's/^.*chromosome=\(.*\)\]$/>chr\1/' "$TEST_DATA_DIR/S288C_reference_genome_Current_Release/S288C_reference_sequence_R64-5-1_20240529.fsa" if [ ! -d "$TEST_DATA_DIR/S288C_reference_genome_Current_Release_STAR" ]; then @@ -59,11 +64,11 @@ PARAMS_FILE=params_file.yaml cat > $PARAMS_FILE << EOF param_list: - id: SRR1569895 - input_r1: $TEST_DATA_DIR/SRR1569895_1.fastq - input_r2: $TEST_DATA_DIR/SRR1569895_2.fastq + input_r1: $TEST_DATA_DIR/SRR1569895_1_subsample.fastq + input_r2: $TEST_DATA_DIR/SRR1569895_2_subsample.fastq - id: SRR1570800 - input_r1: $TEST_DATA_DIR/SRR1570800_1.fastq - input_r2: $TEST_DATA_DIR/SRR1570800_2.fastq + input_r1: $TEST_DATA_DIR/SRR1570800_1_subsample.fastq + input_r2: $TEST_DATA_DIR/SRR1570800_2_subsample.fastq publish_dir: foo reference: $TEST_DATA_DIR/S288C_reference_genome_Current_Release_STAR EOF