name: "pre_processing"
namespace: "workflows"
version: "main"
argument_groups:
- name: "Inputs"
  arguments:
  - type: "string"
    name: "--id"
    description: "ID of the sample."
    info: null
    example:
    - "foo"
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--fastq_1"
    description: "Path to the sample (or read 1 of paired end sample)."
    info: null
    example:
    - "input.fastq.gz"
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--fastq_2"
    description: "Path to read 2 of the sample."
    info: null
    must_exist: false
    create_parent: true
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--strandedness"
    description: "Sample strand-specificity. Must be one of unstranded, forward, reverse\
      \ or auto"
    info: null
    default:
    - "auto"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--bbsplit_index"
    description: "BBsplit index"
    info: null
    must_exist: true
    create_parent: true
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--bbsplit_fasta_list"
    description: "Path to comma-separated file containing a list of reference genomes\
      \ to filter reads against with BBSplit. To use BBSplit, \"--skip_bbsplit\" must\
      \ be explicitly set to \"false\". The file should contain 2 (comma separated)\
      \ columns - short name and full path to reference genome(s)"
    info: null
    must_exist: true
    create_parent: true
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--ribo_database_manifest"
    description: "Text file containing paths to fasta files (one per line) that will\
      \ be used to create the database for SortMeRNA."
    info: null
    must_exist: true
    create_parent: true
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--transcript_fasta"
    description: "Path to FASTA transcriptome file."
    info: null
    must_exist: true
    create_parent: true
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--gtf"
    description: "Path to GTF annotation file."
    info: null
    must_exist: true
    create_parent: true
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--salmon_index"
    description: "Path to directory containing the Salmon index"
    info: null
    must_exist: true
    create_parent: true
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--num_trimmed_reads"
    description: "Number of reads after trimming"
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Extra pipeline options"
  arguments:
  - type: "boolean"
    name: "--skip_qc"
    description: "Skip QC steps of the workflow."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "FastQC options"
  arguments:
  - type: "boolean"
    name: "--skip_fastqc"
    description: "Skip FatQC step."
    info: null
    default:
    - false
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "UMI-tools options"
  arguments:
  - type: "boolean"
    name: "--with_umi"
    description: "Enable UMI-based read deduplication."
    info: null
    default:
    - false
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "boolean"
    name: "--skip_umi_extract"
    description: "Skip umi_tools extract step."
    info: null
    default:
    - false
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--umitools_extract_method"
    description: "UMI pattern to use."
    info: null
    default:
    - "string"
    required: false
    choices:
    - "string"
    - "regex"
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--umitools_bc_pattern"
    description: "The UMI barcode pattern to use e.g. 'NNNNNN' indicates that the\
      \ first 6 nucleotides of the read are from the UMI."
    info: null
    default:
    - ""
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--umitools_bc_pattern2"
    description: "The UMI barcode pattern to use if the UMI is located in read 2."
    info: null
    default:
    - ""
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--umi_discard_read"
    description: "After UMI barcode extraction discard either R1 or R2 by setting\
      \ this parameter to 1 or 2, respectively."
    info: null
    default:
    - 0
    required: false
    choices:
    - 0
    - 1
    - 2
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--umitools_umi_separator"
    description: "The character that separates the UMI in the read name. Most likely\
      \ a colon if you skipped the extraction with UMI-tools and used other software."
    info: null
    default:
    - "_"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--umitools_grouping_method"
    description: "Method to use to determine read groups by subsuming those with similar\
      \ UMIs. All methods start by identifying the reads with the same mapping position,\
      \ but treat similar yet nonidentical UMIs differently."
    info: null
    default:
    - "directional"
    required: false
    choices:
    - "unique"
    - "percentile"
    - "cluster"
    - "adjacency"
    - "directional"
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "boolean"
    name: "--save_umi_intermeds"
    description: "If this option is specified, intermediate FastQ and BAM files produced\
      \ by UMI-tools are also saved in the results directory."
    info: null
    default:
    - false
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Read trimming options"
  arguments:
  - type: "string"
    name: "--trimmer"
    description: "Specify the trimming tool to use."
    info: null
    default:
    - "trimgalore"
    required: false
    choices:
    - "trimgalore"
    - "fastp"
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--extra_trimgalore_args"
    description: "Extra arguments to pass to Trim Galore! command in addition to defaults\
      \ defined by the pipeline."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--min_trimmed_reads"
    description: "Minimum number of trimmed reads below which samples are removed\
      \ from further processing. Some downstream steps in the pipeline will fail if\
      \ this threshold is too low."
    info: null
    default:
    - 10000
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "boolean"
    name: "--skip_trimming"
    description: "Skip the adapter trimming step."
    info: null
    default:
    - false
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "boolean"
    name: "--save_trimmed"
    description: "Save the trimmed FastQ files in the results directory."
    info: null
    default:
    - false
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Alignment options"
  arguments:
  - type: "string"
    name: "--extra_salmon_quant_args"
    description: "Extra arguments to pass to salmon quant command in addition to defaults\
      \ defined by the pipeline."
    info: null
    default:
    - ""
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Read filtering options"
  arguments:
  - type: "boolean_true"
    name: "--skip_bbsplit"
    description: "Skip BBSplit for removal of non-reference genome reads."
    info: null
    direction: "input"
  - type: "boolean_true"
    name: "--remove_ribo_rna"
    description: "Enable the removal of reads derived from ribosomal RNA using SortMeRNA."
    info: null
    direction: "input"
- name: "Other options"
  arguments:
  - type: "string"
    name: "--extra_fq_subsample_args"
    description: "Extra arguments to pass to fq subsample command in addition to defaults\
      \ defined by the pipeline."
    info: null
    default:
    - "--record-count 1000000 --seed 1"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Output"
  arguments:
  - type: "file"
    name: "--qc_output1"
    description: "Path to output directory"
    info: null
    default:
    - "$id.read_1.fastq"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--qc_output2"
    description: "Path to output directory"
    info: null
    default:
    - "$id.read_2.fastq"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--fastqc_html_1"
    description: "FastQC HTML report for read 1."
    info: null
    default:
    - "$id.read_1.fastqc.html"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--fastqc_html_2"
    description: "FastQC HTML report for read 2."
    info: null
    default:
    - "$id.read_2.fastqc.html"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--fastqc_zip_1"
    description: "FastQC report archive for read 1."
    info: null
    default:
    - "$id.read_1.fastqc.zip"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--fastqc_zip_2"
    description: "FastQC report archive for read 2."
    info: null
    default:
    - "$id.read_2.fastqc.zip"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--trim_log_1"
    info: null
    default:
    - "$id.read_1.trimming_report.txt"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--trim_log_2"
    info: null
    default:
    - "$id.read_2.trimming_report.txt"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--trim_html_1"
    info: null
    default:
    - "$id.read_1.trimmed_fastqc.html"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--trim_html_2"
    info: null
    default:
    - "$id.read_2.trimmed_fastqc.html"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--trim_zip_1"
    info: null
    default:
    - "$id.read_1.trimmed_fastqc.zip"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--trim_zip_2"
    info: null
    default:
    - "$id.read_2.trimmed_fastqc.zip"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--sortmerna_log"
    description: "Sortmerna log file."
    info: null
    default:
    - "$id.sortmerna.log"
    must_exist: false
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--salmon_quant_output"
    description: "Results from Salmon quant"
    info: null
    default:
    - "$id.salmon_quant_output"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--trim_json"
    description: "The fastp json format report file name"
    info: null
    default:
    - "$id.fastp_out.json"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--trim_html"
    description: "The fastp html format report file name"
    info: null
    default:
    - "$id.fastp_out.html"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--merged_out"
    description: "File name to store merged fastp output."
    info: null
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
resources:
- type: "nextflow_script"
  path: "main.nf"
  is_executable: true
  entrypoint: "run_wf"
description: "A subworkflow for the pre-processing stage of the nf-core/rnaseq pipeline.\n"
info: null
status: "enabled"
requirements:
  commands:
  - "ps"
dependencies:
- name: "fastqc"
  repository:
    type: "local"
- name: "umitools/umitools_extract"
  repository:
    type: "local"
- name: "umi_tools/umi_tools_extract"
  repository:
    type: "vsh"
    repo: "vsh/biobox"
    tag: "main"
- name: "trimgalore"
  repository:
    type: "local"
- name: "bbmap_bbsplit"
  repository:
    type: "local"
- name: "sortmerna"
  repository:
    type: "local"
- name: "fastp"
  repository:
    type: "vsh"
    repo: "vsh/biobox"
    tag: "main"
- name: "fq_subsample"
  repository:
    type: "local"
- name: "salmon/salmon_quant"
  repository:
    type: "vsh"
    repo: "vsh/biobox"
    tag: "main"
repositories:
- type: "vsh"
  name: "biobox"
  repo: "vsh/biobox"
  tag: "main"
- type: "vsh"
  name: "craftbox"
  repo: "craftbox"
  tag: "v0.1.0"
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: "native"
  id: "native"
build_info:
  config: "src/workflows/pre_processing/config.vsh.yaml"
  runner: "executable"
  engine: "native"
  output: "target/executable/workflows/pre_processing"
  executable: "target/executable/workflows/pre_processing/pre_processing"
  viash_version: "0.9.0"
  git_commit: "a4f2c7d5a1d0c27cc538c9b06ec4dec5c62f8d74"
  git_remote: "https://x-access-token:ghs_hUComHHyuHIIVQYt2HdqulL85sCkXr3K9lOo@github.com/viash-hub/rnaseq"
  dependencies:
  - "target/nextflow/fastqc"
  - "target/nextflow/umitools/umitools_extract"
  - "target/dependencies/vsh/vsh/biobox/main/nextflow/umi_tools/umi_tools_extract"
  - "target/nextflow/trimgalore"
  - "target/nextflow/bbmap_bbsplit"
  - "target/nextflow/sortmerna"
  - "target/dependencies/vsh/vsh/biobox/main/nextflow/fastp"
  - "target/nextflow/fq_subsample"
  - "target/dependencies/vsh/vsh/biobox/main/nextflow/salmon/salmon_quant"
package_config:
  name: "rnaseq"
  version: "main"
  info:
    test_resources:
    - path: "gs://viash-hub-test-data/rnaseq/v1"
      dest: "testData"
  repositories:
  - type: "vsh"
    name: "biobox"
    repo: "vsh/biobox"
    tag: "main"
  - type: "vsh"
    name: "craftbox"
    repo: "craftbox"
    tag: "v0.1.0"
  viash_version: "0.9.0"
  source: "src"
  target: "target"
  config_mods:
  - ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].directives.tag\
    \ := '$id'\n"
  - ".engines += { type: \"native\" }"
  - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
  - ".engines[.type == 'docker'].target_tag := 'main'"
  organization: "vsh"