vsh/rnaseq
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Build branch main with version main (1e1ffb3)

Browse Source 
Build pipeline: vsh-ci-dev-jsbwk

Source commit: 1e1ffb315f

Source message: Merge pull request #17 from viash-hub/add_biobox_modules

- Migrate a number of components to biobox
- Fix tests
- Reduce size of test resources
- Prepare for Viash Hub
This commit is contained in:
CI
2024-09-13 07:41:13 +00:00
commit 1ebb61f1e8
557 changed files with 430700 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

541
target/executable/workflows/genome_alignment_and_quant/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,541 @@
name: "genome_alignment_and_quant"
namespace: "workflows"
version: "main"
argument_groups:
- name: "Input"
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"
alternatives:
- "-i"
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: true
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, or\
\ reverse"
info: null
required: false
choices:
- "forward"
- "reverse"
- "unstranded"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gtf"
description: "GTF file"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--transcript_fasta"
description: "Fasta file of the reference transcriptome."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--star_index"
description: "STAR index directory."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--star_ignore_sjdbgtf"
description: "When using pre-built STAR indices do not re-extract and use splice\
\ junctions from the GTF file"
info: null
default:
- false
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--seq_platform"
description: "Sequencing platform."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--seq_center"
description: "Sequencing center."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--extra_star_align_args"
description: "Extra arguments to pass to STAR alignment command in addition to\
\ defaults defined by the pipeline."
info: null
default:
- ""
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--bam_csi_index"
description: "Create a CSI index for BAM files instead of the traditional BAI\
\ index. This will be required for genomes with larger chromosome sizes."
info: null
default:
- false
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--umi_dedup_stats"
description: "Generate output stats when running \"umi_tools dedup\"."
info: null
default:
- false
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--with_umi"
description: "Enable UMI-based read deduplication."
info: null
default:
- false
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--salmon_quant_libtype"
description: "Override Salmon library type inferred based on strandedness defined\
\ in meta object."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- 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: ";"
- type: "string"
name: "--gtf_group_features"
description: "Define the attribute type used to group features in the GTF file\
\ when running Salmon."
info: null
default:
- "gene_id"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--gtf_extra_attributes"
description: "By default, the pipeline uses the gene_name field to obtain additional\
\ gene identifiers from the input GTF file when running Salmon."
info: null
default:
- "gene_name"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "extra_rsem_calculate_expression_args"
description: "Extra arguments to pass to rsem-calculate-expression command in\
\ addition to defaults defined by the pipeline."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--aligner"
description: "Specifies the alignment algorithm to use - available options are\
\ 'star_salmon', 'star_rsem' and 'hisat2'."
info: null
default:
- "star_salmon"
required: false
choices:
- "star_salmon"
- "star_rsem"
- "hisat2"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--rsem_index"
description: "Path to directory for pre-built RSEM index."
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 for pre-built Salmon index."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--star_multiqc"
info: null
default:
- "$id.star_align.log"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_bam_sorted"
info: null
default:
- "$id.genome.bam"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_bam_index"
info: null
default:
- "$id.genome.bam.bai"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_bam_stats"
info: null
default:
- "$id.genome.stats"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_bam_flagstat"
info: null
default:
- "$id.genome.flagstat"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_bam_idxstats"
info: null
default:
- "$id.genome.idxstats"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--transcriptome_bam"
info: null
default:
- "$id.transcriptome.bam"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--transcriptome_bam_index"
info: null
default:
- "$id.transcriptome.bam.bai"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--transcriptome_bam_stats"
info: null
default:
- "$id.transcriptome.stats"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--transcriptome_bam_flagstat"
info: null
default:
- "$id.transcriptome.flagstat"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--transcriptome_bam_idxstats"
info: null
default:
- "$id.transcriptome.idxstats"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--quant_out_dir"
info: null
default:
- "$id.salmon_quant"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--quant_results_file"
info: null
default:
- "$id.quant.sf"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "nextflow_script"
path: "main.nf"
is_executable: true
entrypoint: "run_wf"
description: "A viash sub-workflow for genome alignment and quantification stage of\
\ nf-core/rnaseq pipeline.\n"
info: null
status: "enabled"
requirements:
commands:
- "ps"
dependencies:
- name: "star/star_align_reads"
repository:
type: "vsh"
repo: "vsh/biobox"
- name: "samtools/samtools_sort"
repository:
type: "vsh"
repo: "vsh/biobox"
- name: "samtools/samtools_index"
repository:
type: "vsh"
repo: "vsh/biobox"
- name: "samtools/samtools_stats"
repository:
type: "vsh"
repo: "vsh/biobox"
- name: "samtools/samtools_flagstat"
repository:
type: "vsh"
repo: "vsh/biobox"
- name: "samtools/samtools_idxstats"
repository:
type: "vsh"
repo: "vsh/biobox"
- name: "umitools/umitools_dedup"
repository:
type: "local"
- name: "umitools_prepareforquant"
repository:
type: "local"
- name: "salmon/salmon_quant"
repository:
type: "vsh"
repo: "vsh/biobox"
- name: "rsem/rsem_calculate_expression"
repository:
type: "local"
repositories:
- type: "vsh"
name: "biobox"
repo: "vsh/biobox"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$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/genome_alignment_and_quant/config.vsh.yaml"
runner: "executable"
engine: "native"
output: "target/executable/workflows/genome_alignment_and_quant"
executable: "target/executable/workflows/genome_alignment_and_quant/genome_alignment_and_quant"
viash_version: "0.9.0"
git_commit: "1e1ffb315fefec05db2ee0c62e1c98ce4b49929c"
git_remote: "https://github.com/viash-hub/rnaseq"
dependencies:
- "target/dependencies/vsh/vsh/biobox/nextflow/star/star_align_reads"
- "target/dependencies/vsh/vsh/biobox/nextflow/samtools/samtools_sort"
- "target/dependencies/vsh/vsh/biobox/nextflow/samtools/samtools_index"
- "target/dependencies/vsh/vsh/biobox/nextflow/samtools/samtools_stats"
- "target/dependencies/vsh/vsh/biobox/nextflow/samtools/samtools_flagstat"
- "target/dependencies/vsh/vsh/biobox/nextflow/samtools/samtools_idxstats"
- "target/nextflow/umitools/umitools_dedup"
- "target/nextflow/umitools_prepareforquant"
- "target/dependencies/vsh/vsh/biobox/nextflow/salmon/salmon_quant"
- "target/nextflow/rsem/rsem_calculate_expression"
package_config:
version: "main"
info:
test_resources:
- path: "gs://viash-hub-test-data/rnaseq/v1"
dest: "testData"
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"

1636
target/executable/workflows/genome_alignment_and_quant/genome_alignment_and_quant Executable file
View File

File diff suppressed because it is too large Load Diff

293
target/executable/workflows/merge_quant_results/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,293 @@
name: "merge_quant_results"
namespace: "workflows"
version: "main"
argument_groups:
- name: "Input"
arguments:
- type: "file"
name: "--salmon_quant_results"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: true
multiple_sep: ","
- type: "file"
name: "--kallisto_quant_results"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: true
multiple_sep: ","
- type: "file"
name: "--gtf"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--gtf_extra_attributes"
info: null
default:
- "gene_name"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--gtf_group_features"
info: null
default:
- "gene_id"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--quant_type"
description: "Quantification method used."
info: null
default:
- "salmon"
required: false
choices:
- "salmon"
- "kallisto"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--versions"
info: null
must_exist: false
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--tpm_gene"
info: null
example:
- "gene_tpm.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_gene"
info: null
example:
- "gene_counts.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_gene_length_scaled"
info: null
example:
- "gene_counts_length_scaled.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_gene_scaled"
info: null
example:
- "gene_counts_scaled.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--tpm_transcript"
info: null
example:
- "transcript_tpm.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--lengths_gene"
info: null
example:
- "gene_length.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_transcript"
info: null
example:
- "transcript_counts.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--lengths_transcript"
info: null
example:
- "transcript_length.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--quant_merged_summarizedexperiment"
info: null
example:
- "quant_merged_summarizedexperiment"
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 sub-workflow to merge the counts obtained from salmon quant across\
\ all samples."
info: null
status: "enabled"
requirements:
commands:
- "ps"
dependencies:
- name: "tx2gene"
repository:
type: "local"
- name: "tximport"
repository:
type: "local"
- name: "summarizedexperiment"
repository:
type: "local"
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/merge_quant_results/config.vsh.yaml"
runner: "executable"
engine: "native"
output: "target/executable/workflows/merge_quant_results"
executable: "target/executable/workflows/merge_quant_results/merge_quant_results"
viash_version: "0.9.0"
git_commit: "1e1ffb315fefec05db2ee0c62e1c98ce4b49929c"
git_remote: "https://github.com/viash-hub/rnaseq"
dependencies:
- "target/nextflow/tx2gene"
- "target/nextflow/tximport"
- "target/nextflow/summarizedexperiment"
package_config:
version: "main"
info:
test_resources:
- path: "gs://viash-hub-test-data/rnaseq/v1"
dest: "testData"
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"

892
target/executable/workflows/merge_quant_results/merge_quant_results Executable file
View File

@@ -0,0 +1,892 @@
#!/usr/bin/env bash
# merge_quant_results main
#
# 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.
set -e
if [ -z "$VIASH_TEMP" ]; then
VIASH_TEMP=${VIASH_TEMP:-$VIASH_TMPDIR}
VIASH_TEMP=${VIASH_TEMP:-$VIASH_TEMPDIR}
VIASH_TEMP=${VIASH_TEMP:-$VIASH_TMP}
VIASH_TEMP=${VIASH_TEMP:-$TMPDIR}
VIASH_TEMP=${VIASH_TEMP:-$TMP}
VIASH_TEMP=${VIASH_TEMP:-$TEMPDIR}
VIASH_TEMP=${VIASH_TEMP:-$TEMP}
VIASH_TEMP=${VIASH_TEMP:-/tmp}
fi
# define helper functions
# ViashQuote: put quotes around non flag values
# $1 : unquoted string
# return : possibly quoted string
# examples:
# ViashQuote --foo # returns --foo
# ViashQuote bar # returns 'bar'
# Viashquote --foo=bar # returns --foo='bar'
function ViashQuote {
if [[ "$1" =~ ^-+[a-zA-Z0-9_\-]+=.+$ ]]; then
echo "$1" | sed "s#=\(.*\)#='\1'#"
elif [[ "$1" =~ ^-+[a-zA-Z0-9_\-]+$ ]]; then
echo "$1"
else
echo "'$1'"
fi
}
# ViashRemoveFlags: Remove leading flag
# $1 : string with a possible leading flag
# return : string without possible leading flag
# examples:
# ViashRemoveFlags --foo=bar # returns bar
function ViashRemoveFlags {
echo "$1" | sed 's/^--*[a-zA-Z0-9_\-]*=//'
}
# ViashSourceDir: return the path of a bash file, following symlinks
# usage : ViashSourceDir ${BASH_SOURCE[0]}
# $1 : Should always be set to ${BASH_SOURCE[0]}
# returns : The absolute path of the bash file
function ViashSourceDir {
local source="$1"
while [ -h "$source" ]; do
local dir="$( cd -P "$( dirname "$source" )" >/dev/null 2>&1 && pwd )"
source="$(readlink "$source")"
[[ $source != /* ]] && source="$dir/$source"
done
cd -P "$( dirname "$source" )" >/dev/null 2>&1 && pwd
}
# ViashFindTargetDir: return the path of the '.build.yaml' file, following symlinks
# usage : ViashFindTargetDir 'ScriptPath'
# $1 : The location from where to start the upward search
# returns : The absolute path of the '.build.yaml' file
function ViashFindTargetDir {
local source="$1"
while [[ "$source" != "" && ! -e "$source/.build.yaml" ]]; do
source=${source%/*}
done
echo $source
}
# see https://en.wikipedia.org/wiki/Syslog#Severity_level
VIASH_LOGCODE_EMERGENCY=0
VIASH_LOGCODE_ALERT=1
VIASH_LOGCODE_CRITICAL=2
VIASH_LOGCODE_ERROR=3
VIASH_LOGCODE_WARNING=4
VIASH_LOGCODE_NOTICE=5
VIASH_LOGCODE_INFO=6
VIASH_LOGCODE_DEBUG=7
VIASH_VERBOSITY=$VIASH_LOGCODE_NOTICE
# ViashLog: Log events depending on the verbosity level
# usage: ViashLog 1 alert Oh no something went wrong!
# $1: required verbosity level
# $2: display tag
# $3+: messages to display
# stdout: Your input, prepended by '[$2] '.
function ViashLog {
local required_level="$1"
local display_tag="$2"
shift 2
if [ $VIASH_VERBOSITY -ge $required_level ]; then
>&2 echo "[$display_tag]" "$@"
fi
}
# ViashEmergency: log events when the system is unstable
# usage: ViashEmergency Oh no something went wrong.
# stdout: Your input, prepended by '[emergency] '.
function ViashEmergency {
ViashLog $VIASH_LOGCODE_EMERGENCY emergency "$@"
}
# ViashAlert: log events when actions must be taken immediately (e.g. corrupted system database)
# usage: ViashAlert Oh no something went wrong.
# stdout: Your input, prepended by '[alert] '.
function ViashAlert {
ViashLog $VIASH_LOGCODE_ALERT alert "$@"
}
# ViashCritical: log events when a critical condition occurs
# usage: ViashCritical Oh no something went wrong.
# stdout: Your input, prepended by '[critical] '.
function ViashCritical {
ViashLog $VIASH_LOGCODE_CRITICAL critical "$@"
}
# ViashError: log events when an error condition occurs
# usage: ViashError Oh no something went wrong.
# stdout: Your input, prepended by '[error] '.
function ViashError {
ViashLog $VIASH_LOGCODE_ERROR error "$@"
}
# ViashWarning: log potentially abnormal events
# usage: ViashWarning Something may have gone wrong.
# stdout: Your input, prepended by '[warning] '.
function ViashWarning {
ViashLog $VIASH_LOGCODE_WARNING warning "$@"
}
# ViashNotice: log significant but normal events
# usage: ViashNotice This just happened.
# stdout: Your input, prepended by '[notice] '.
function ViashNotice {
ViashLog $VIASH_LOGCODE_NOTICE notice "$@"
}
# ViashInfo: log normal events
# usage: ViashInfo This just happened.
# stdout: Your input, prepended by '[info] '.
function ViashInfo {
ViashLog $VIASH_LOGCODE_INFO info "$@"
}
# ViashDebug: log all events, for debugging purposes
# usage: ViashDebug This just happened.
# stdout: Your input, prepended by '[debug] '.
function ViashDebug {
ViashLog $VIASH_LOGCODE_DEBUG debug "$@"
}
# find source folder of this component
VIASH_META_RESOURCES_DIR=`ViashSourceDir ${BASH_SOURCE[0]}`
# find the root of the built components & dependencies
VIASH_TARGET_DIR=`ViashFindTargetDir $VIASH_META_RESOURCES_DIR`
# define meta fields
VIASH_META_NAME="merge_quant_results"
VIASH_META_FUNCTIONALITY_NAME="merge_quant_results"
VIASH_META_EXECUTABLE="$VIASH_META_RESOURCES_DIR/$VIASH_META_NAME"
VIASH_META_CONFIG="$VIASH_META_RESOURCES_DIR/.config.vsh.yaml"
VIASH_META_TEMP_DIR="$VIASH_TEMP"
# ViashHelp: Display helpful explanation about this executable
function ViashHelp {
echo "merge_quant_results main"
echo ""
echo "A sub-workflow to merge the counts obtained from salmon quant across all"
echo "samples."
echo ""
echo "Input:"
echo " --salmon_quant_results"
echo " type: file, multiple values allowed, file must exist"
echo ""
echo " --kallisto_quant_results"
echo " type: file, multiple values allowed, file must exist"
echo ""
echo " --gtf"
echo " type: file, file must exist"
echo ""
echo " --gtf_extra_attributes"
echo " type: string"
echo " default: gene_name"
echo ""
echo " --gtf_group_features"
echo " type: string"
echo " default: gene_id"
echo ""
echo " --quant_type"
echo " type: string"
echo " default: salmon"
echo " choices: [ salmon, kallisto ]"
echo " Quantification method used."
echo ""
echo " --versions"
echo " type: file"
echo ""
echo "Output:"
echo " --tpm_gene"
echo " type: file, output, file must exist"
echo " example: gene_tpm.tsv"
echo ""
echo " --counts_gene"
echo " type: file, output, file must exist"
echo " example: gene_counts.tsv"
echo ""
echo " --counts_gene_length_scaled"
echo " type: file, output, file must exist"
echo " example: gene_counts_length_scaled.tsv"
echo ""
echo " --counts_gene_scaled"
echo " type: file, output, file must exist"
echo " example: gene_counts_scaled.tsv"
echo ""
echo " --tpm_transcript"
echo " type: file, output, file must exist"
echo " example: transcript_tpm.tsv"
echo ""
echo " --lengths_gene"
echo " type: file, output, file must exist"
echo " example: gene_length.tsv"
echo ""
echo " --counts_transcript"
echo " type: file, output, file must exist"
echo " example: transcript_counts.tsv"
echo ""
echo " --lengths_transcript"
echo " type: file, output, file must exist"
echo " example: transcript_length.tsv"
echo ""
echo " --quant_merged_summarizedexperiment"
echo " type: file, output, file must exist"
echo " example: quant_merged_summarizedexperiment"
}
# initialise variables
VIASH_MODE='run'
VIASH_ENGINE_ID='native'
# initialise array
VIASH_POSITIONAL_ARGS=''
while [[ $# -gt 0 ]]; do
case "$1" in
-h|--help)
ViashHelp
exit
;;
---v|---verbose)
let "VIASH_VERBOSITY=VIASH_VERBOSITY+1"
shift 1
;;
---verbosity)
VIASH_VERBOSITY="$2"
shift 2
;;
---verbosity=*)
VIASH_VERBOSITY="$(ViashRemoveFlags "$1")"
shift 1
;;
--version)
echo "merge_quant_results main"
exit
;;
--salmon_quant_results)
if [ -z "$VIASH_PAR_SALMON_QUANT_RESULTS" ]; then
VIASH_PAR_SALMON_QUANT_RESULTS="$2"
else
VIASH_PAR_SALMON_QUANT_RESULTS="$VIASH_PAR_SALMON_QUANT_RESULTS,""$2"
fi
[ $# -lt 2 ] && ViashError Not enough arguments passed to --salmon_quant_results. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--salmon_quant_results=*)
if [ -z "$VIASH_PAR_SALMON_QUANT_RESULTS" ]; then
VIASH_PAR_SALMON_QUANT_RESULTS=$(ViashRemoveFlags "$1")
else
VIASH_PAR_SALMON_QUANT_RESULTS="$VIASH_PAR_SALMON_QUANT_RESULTS,"$(ViashRemoveFlags "$1")
fi
shift 1
;;
--kallisto_quant_results)
if [ -z "$VIASH_PAR_KALLISTO_QUANT_RESULTS" ]; then
VIASH_PAR_KALLISTO_QUANT_RESULTS="$2"
else
VIASH_PAR_KALLISTO_QUANT_RESULTS="$VIASH_PAR_KALLISTO_QUANT_RESULTS,""$2"
fi
[ $# -lt 2 ] && ViashError Not enough arguments passed to --kallisto_quant_results. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--kallisto_quant_results=*)
if [ -z "$VIASH_PAR_KALLISTO_QUANT_RESULTS" ]; then
VIASH_PAR_KALLISTO_QUANT_RESULTS=$(ViashRemoveFlags "$1")
else
VIASH_PAR_KALLISTO_QUANT_RESULTS="$VIASH_PAR_KALLISTO_QUANT_RESULTS,"$(ViashRemoveFlags "$1")
fi
shift 1
;;
--gtf)
[ -n "$VIASH_PAR_GTF" ] && ViashError Bad arguments for option \'--gtf\': \'$VIASH_PAR_GTF\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_GTF="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --gtf. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--gtf=*)
[ -n "$VIASH_PAR_GTF" ] && ViashError Bad arguments for option \'--gtf=*\': \'$VIASH_PAR_GTF\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_GTF=$(ViashRemoveFlags "$1")
shift 1
;;
--gtf_extra_attributes)
[ -n "$VIASH_PAR_GTF_EXTRA_ATTRIBUTES" ] && ViashError Bad arguments for option \'--gtf_extra_attributes\': \'$VIASH_PAR_GTF_EXTRA_ATTRIBUTES\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_GTF_EXTRA_ATTRIBUTES="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --gtf_extra_attributes. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--gtf_extra_attributes=*)
[ -n "$VIASH_PAR_GTF_EXTRA_ATTRIBUTES" ] && ViashError Bad arguments for option \'--gtf_extra_attributes=*\': \'$VIASH_PAR_GTF_EXTRA_ATTRIBUTES\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_GTF_EXTRA_ATTRIBUTES=$(ViashRemoveFlags "$1")
shift 1
;;
--gtf_group_features)
[ -n "$VIASH_PAR_GTF_GROUP_FEATURES" ] && ViashError Bad arguments for option \'--gtf_group_features\': \'$VIASH_PAR_GTF_GROUP_FEATURES\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_GTF_GROUP_FEATURES="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --gtf_group_features. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--gtf_group_features=*)
[ -n "$VIASH_PAR_GTF_GROUP_FEATURES" ] && ViashError Bad arguments for option \'--gtf_group_features=*\': \'$VIASH_PAR_GTF_GROUP_FEATURES\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_GTF_GROUP_FEATURES=$(ViashRemoveFlags "$1")
shift 1
;;
--quant_type)
[ -n "$VIASH_PAR_QUANT_TYPE" ] && ViashError Bad arguments for option \'--quant_type\': \'$VIASH_PAR_QUANT_TYPE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_QUANT_TYPE="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --quant_type. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--quant_type=*)
[ -n "$VIASH_PAR_QUANT_TYPE" ] && ViashError Bad arguments for option \'--quant_type=*\': \'$VIASH_PAR_QUANT_TYPE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_QUANT_TYPE=$(ViashRemoveFlags "$1")
shift 1
;;
--versions)
[ -n "$VIASH_PAR_VERSIONS" ] && ViashError Bad arguments for option \'--versions\': \'$VIASH_PAR_VERSIONS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_VERSIONS="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --versions. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--versions=*)
[ -n "$VIASH_PAR_VERSIONS" ] && ViashError Bad arguments for option \'--versions=*\': \'$VIASH_PAR_VERSIONS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_VERSIONS=$(ViashRemoveFlags "$1")
shift 1
;;
--tpm_gene)
[ -n "$VIASH_PAR_TPM_GENE" ] && ViashError Bad arguments for option \'--tpm_gene\': \'$VIASH_PAR_TPM_GENE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_TPM_GENE="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --tpm_gene. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--tpm_gene=*)
[ -n "$VIASH_PAR_TPM_GENE" ] && ViashError Bad arguments for option \'--tpm_gene=*\': \'$VIASH_PAR_TPM_GENE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_TPM_GENE=$(ViashRemoveFlags "$1")
shift 1
;;
--counts_gene)
[ -n "$VIASH_PAR_COUNTS_GENE" ] && ViashError Bad arguments for option \'--counts_gene\': \'$VIASH_PAR_COUNTS_GENE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_COUNTS_GENE="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --counts_gene. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--counts_gene=*)
[ -n "$VIASH_PAR_COUNTS_GENE" ] && ViashError Bad arguments for option \'--counts_gene=*\': \'$VIASH_PAR_COUNTS_GENE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_COUNTS_GENE=$(ViashRemoveFlags "$1")
shift 1
;;
--counts_gene_length_scaled)
[ -n "$VIASH_PAR_COUNTS_GENE_LENGTH_SCALED" ] && ViashError Bad arguments for option \'--counts_gene_length_scaled\': \'$VIASH_PAR_COUNTS_GENE_LENGTH_SCALED\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_COUNTS_GENE_LENGTH_SCALED="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --counts_gene_length_scaled. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--counts_gene_length_scaled=*)
[ -n "$VIASH_PAR_COUNTS_GENE_LENGTH_SCALED" ] && ViashError Bad arguments for option \'--counts_gene_length_scaled=*\': \'$VIASH_PAR_COUNTS_GENE_LENGTH_SCALED\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_COUNTS_GENE_LENGTH_SCALED=$(ViashRemoveFlags "$1")
shift 1
;;
--counts_gene_scaled)
[ -n "$VIASH_PAR_COUNTS_GENE_SCALED" ] && ViashError Bad arguments for option \'--counts_gene_scaled\': \'$VIASH_PAR_COUNTS_GENE_SCALED\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_COUNTS_GENE_SCALED="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --counts_gene_scaled. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--counts_gene_scaled=*)
[ -n "$VIASH_PAR_COUNTS_GENE_SCALED" ] && ViashError Bad arguments for option \'--counts_gene_scaled=*\': \'$VIASH_PAR_COUNTS_GENE_SCALED\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_COUNTS_GENE_SCALED=$(ViashRemoveFlags "$1")
shift 1
;;
--tpm_transcript)
[ -n "$VIASH_PAR_TPM_TRANSCRIPT" ] && ViashError Bad arguments for option \'--tpm_transcript\': \'$VIASH_PAR_TPM_TRANSCRIPT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_TPM_TRANSCRIPT="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --tpm_transcript. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--tpm_transcript=*)
[ -n "$VIASH_PAR_TPM_TRANSCRIPT" ] && ViashError Bad arguments for option \'--tpm_transcript=*\': \'$VIASH_PAR_TPM_TRANSCRIPT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_TPM_TRANSCRIPT=$(ViashRemoveFlags "$1")
shift 1
;;
--lengths_gene)
[ -n "$VIASH_PAR_LENGTHS_GENE" ] && ViashError Bad arguments for option \'--lengths_gene\': \'$VIASH_PAR_LENGTHS_GENE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_LENGTHS_GENE="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --lengths_gene. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--lengths_gene=*)
[ -n "$VIASH_PAR_LENGTHS_GENE" ] && ViashError Bad arguments for option \'--lengths_gene=*\': \'$VIASH_PAR_LENGTHS_GENE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_LENGTHS_GENE=$(ViashRemoveFlags "$1")
shift 1
;;
--counts_transcript)
[ -n "$VIASH_PAR_COUNTS_TRANSCRIPT" ] && ViashError Bad arguments for option \'--counts_transcript\': \'$VIASH_PAR_COUNTS_TRANSCRIPT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_COUNTS_TRANSCRIPT="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --counts_transcript. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--counts_transcript=*)
[ -n "$VIASH_PAR_COUNTS_TRANSCRIPT" ] && ViashError Bad arguments for option \'--counts_transcript=*\': \'$VIASH_PAR_COUNTS_TRANSCRIPT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_COUNTS_TRANSCRIPT=$(ViashRemoveFlags "$1")
shift 1
;;
--lengths_transcript)
[ -n "$VIASH_PAR_LENGTHS_TRANSCRIPT" ] && ViashError Bad arguments for option \'--lengths_transcript\': \'$VIASH_PAR_LENGTHS_TRANSCRIPT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_LENGTHS_TRANSCRIPT="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --lengths_transcript. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--lengths_transcript=*)
[ -n "$VIASH_PAR_LENGTHS_TRANSCRIPT" ] && ViashError Bad arguments for option \'--lengths_transcript=*\': \'$VIASH_PAR_LENGTHS_TRANSCRIPT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_LENGTHS_TRANSCRIPT=$(ViashRemoveFlags "$1")
shift 1
;;
--quant_merged_summarizedexperiment)
[ -n "$VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT" ] && ViashError Bad arguments for option \'--quant_merged_summarizedexperiment\': \'$VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --quant_merged_summarizedexperiment. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--quant_merged_summarizedexperiment=*)
[ -n "$VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT" ] && ViashError Bad arguments for option \'--quant_merged_summarizedexperiment=*\': \'$VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT=$(ViashRemoveFlags "$1")
shift 1
;;
---engine)
VIASH_ENGINE_ID="$2"
shift 2
;;
---engine=*)
VIASH_ENGINE_ID="$(ViashRemoveFlags "$1")"
shift 1
;;
---cpus)
[ -n "$VIASH_META_CPUS" ] && ViashError Bad arguments for option \'---cpus\': \'$VIASH_META_CPUS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_META_CPUS="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to ---cpus. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
---cpus=*)
[ -n "$VIASH_META_CPUS" ] && ViashError Bad arguments for option \'---cpus=*\': \'$VIASH_META_CPUS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_META_CPUS=$(ViashRemoveFlags "$1")
shift 1
;;
---memory)
[ -n "$VIASH_META_MEMORY" ] && ViashError Bad arguments for option \'---memory\': \'$VIASH_META_MEMORY\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_META_MEMORY="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to ---memory. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
---memory=*)
[ -n "$VIASH_META_MEMORY" ] && ViashError Bad arguments for option \'---memory=*\': \'$VIASH_META_MEMORY\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_META_MEMORY=$(ViashRemoveFlags "$1")
shift 1
;;
*) # positional arg or unknown option
# since the positional args will be eval'd, can we always quote, instead of using ViashQuote
VIASH_POSITIONAL_ARGS="$VIASH_POSITIONAL_ARGS '$1'"
[[ $1 == -* ]] && ViashWarning $1 looks like a parameter but is not a defined parameter and will instead be treated as a positional argument. Use "--help" to get more information on the parameters.
shift # past argument
;;
esac
done
# parse positional parameters
eval set -- $VIASH_POSITIONAL_ARGS
if [ "$VIASH_ENGINE_ID" == "native" ] ; then
VIASH_ENGINE_TYPE='native'
else
ViashError "Engine '$VIASH_ENGINE_ID' is not recognized. Options are: native."
exit 1
fi
# setting computational defaults
# helper function for parsing memory strings
function ViashMemoryAsBytes {
local memory=`echo "$1" | tr '[:upper:]' '[:lower:]' | tr -d '[:space:]'`
local memory_regex='^([0-9]+)([kmgtp]i?b?|b)$'
if [[ $memory =~ $memory_regex ]]; then
local number=${memory/[^0-9]*/}
local symbol=${memory/*[0-9]/}
case $symbol in
b) memory_b=$number ;;
kb|k) memory_b=$(( $number * 1000 )) ;;
mb|m) memory_b=$(( $number * 1000 * 1000 )) ;;
gb|g) memory_b=$(( $number * 1000 * 1000 * 1000 )) ;;
tb|t) memory_b=$(( $number * 1000 * 1000 * 1000 * 1000 )) ;;
pb|p) memory_b=$(( $number * 1000 * 1000 * 1000 * 1000 * 1000 )) ;;
kib|ki) memory_b=$(( $number * 1024 )) ;;
mib|mi) memory_b=$(( $number * 1024 * 1024 )) ;;
gib|gi) memory_b=$(( $number * 1024 * 1024 * 1024 )) ;;
tib|ti) memory_b=$(( $number * 1024 * 1024 * 1024 * 1024 )) ;;
pib|pi) memory_b=$(( $number * 1024 * 1024 * 1024 * 1024 * 1024 )) ;;
esac
echo "$memory_b"
fi
}
# compute memory in different units
if [ ! -z ${VIASH_META_MEMORY+x} ]; then
VIASH_META_MEMORY_B=`ViashMemoryAsBytes $VIASH_META_MEMORY`
# do not define other variables if memory_b is an empty string
if [ ! -z "$VIASH_META_MEMORY_B" ]; then
VIASH_META_MEMORY_KB=$(( ($VIASH_META_MEMORY_B+999) / 1000 ))
VIASH_META_MEMORY_MB=$(( ($VIASH_META_MEMORY_KB+999) / 1000 ))
VIASH_META_MEMORY_GB=$(( ($VIASH_META_MEMORY_MB+999) / 1000 ))
VIASH_META_MEMORY_TB=$(( ($VIASH_META_MEMORY_GB+999) / 1000 ))
VIASH_META_MEMORY_PB=$(( ($VIASH_META_MEMORY_TB+999) / 1000 ))
VIASH_META_MEMORY_KIB=$(( ($VIASH_META_MEMORY_B+1023) / 1024 ))
VIASH_META_MEMORY_MIB=$(( ($VIASH_META_MEMORY_KIB+1023) / 1024 ))
VIASH_META_MEMORY_GIB=$(( ($VIASH_META_MEMORY_MIB+1023) / 1024 ))
VIASH_META_MEMORY_TIB=$(( ($VIASH_META_MEMORY_GIB+1023) / 1024 ))
VIASH_META_MEMORY_PIB=$(( ($VIASH_META_MEMORY_TIB+1023) / 1024 ))
else
# unset memory if string is empty
unset $VIASH_META_MEMORY_B
fi
fi
# unset nproc if string is empty
if [ -z "$VIASH_META_CPUS" ]; then
unset $VIASH_META_CPUS
fi
# check whether required parameters exist
if [ -z ${VIASH_META_NAME+x} ]; then
ViashError 'name' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_META_FUNCTIONALITY_NAME+x} ]; then
ViashError 'functionality_name' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_META_RESOURCES_DIR+x} ]; then
ViashError 'resources_dir' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_META_EXECUTABLE+x} ]; then
ViashError 'executable' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_META_CONFIG+x} ]; then
ViashError 'config' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_META_TEMP_DIR+x} ]; then
ViashError 'temp_dir' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
# filling in defaults
if [ -z ${VIASH_PAR_GTF_EXTRA_ATTRIBUTES+x} ]; then
VIASH_PAR_GTF_EXTRA_ATTRIBUTES="gene_name"
fi
if [ -z ${VIASH_PAR_GTF_GROUP_FEATURES+x} ]; then
VIASH_PAR_GTF_GROUP_FEATURES="gene_id"
fi
if [ -z ${VIASH_PAR_QUANT_TYPE+x} ]; then
VIASH_PAR_QUANT_TYPE="salmon"
fi
# check whether required files exist
if [ ! -z "$VIASH_PAR_SALMON_QUANT_RESULTS" ]; then
IFS=','
set -f
for file in $VIASH_PAR_SALMON_QUANT_RESULTS; do
unset IFS
if [ ! -e "$file" ]; then
ViashError "Input file '$file' does not exist."
exit 1
fi
done
set +f
fi
if [ ! -z "$VIASH_PAR_KALLISTO_QUANT_RESULTS" ]; then
IFS=','
set -f
for file in $VIASH_PAR_KALLISTO_QUANT_RESULTS; do
unset IFS
if [ ! -e "$file" ]; then
ViashError "Input file '$file' does not exist."
exit 1
fi
done
set +f
fi
if [ ! -z "$VIASH_PAR_GTF" ] && [ ! -e "$VIASH_PAR_GTF" ]; then
ViashError "Input file '$VIASH_PAR_GTF' does not exist."
exit 1
fi
# check whether parameters values are of the right type
if [[ -n "$VIASH_META_CPUS" ]]; then
if ! [[ "$VIASH_META_CPUS" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'cpus' has to be an integer. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_B" ]]; then
if ! [[ "$VIASH_META_MEMORY_B" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_b' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_KB" ]]; then
if ! [[ "$VIASH_META_MEMORY_KB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_kb' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_MB" ]]; then
if ! [[ "$VIASH_META_MEMORY_MB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_mb' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_GB" ]]; then
if ! [[ "$VIASH_META_MEMORY_GB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_gb' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_TB" ]]; then
if ! [[ "$VIASH_META_MEMORY_TB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_tb' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_PB" ]]; then
if ! [[ "$VIASH_META_MEMORY_PB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_pb' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_KIB" ]]; then
if ! [[ "$VIASH_META_MEMORY_KIB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_kib' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_MIB" ]]; then
if ! [[ "$VIASH_META_MEMORY_MIB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_mib' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_GIB" ]]; then
if ! [[ "$VIASH_META_MEMORY_GIB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_gib' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_TIB" ]]; then
if ! [[ "$VIASH_META_MEMORY_TIB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_tib' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_PIB" ]]; then
if ! [[ "$VIASH_META_MEMORY_PIB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_pib' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
# check whether value is belongs to a set of choices
if [ ! -z "$VIASH_PAR_QUANT_TYPE" ]; then
VIASH_PAR_QUANT_TYPE_CHOICES=("salmon;kallisto")
IFS=';'
set -f
if ! [[ ";${VIASH_PAR_QUANT_TYPE_CHOICES[*]};" =~ ";$VIASH_PAR_QUANT_TYPE;" ]]; then
ViashError '--quant_type' specified value of \'$VIASH_PAR_QUANT_TYPE\' is not in the list of allowed values. Use "--help" to get more information on the parameters.
exit 1
fi
set +f
unset IFS
fi
# create parent directories of output files, if so desired
if [ ! -z "$VIASH_PAR_TPM_GENE" ] && [ ! -d "$(dirname "$VIASH_PAR_TPM_GENE")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_TPM_GENE")"
fi
if [ ! -z "$VIASH_PAR_COUNTS_GENE" ] && [ ! -d "$(dirname "$VIASH_PAR_COUNTS_GENE")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_COUNTS_GENE")"
fi
if [ ! -z "$VIASH_PAR_COUNTS_GENE_LENGTH_SCALED" ] && [ ! -d "$(dirname "$VIASH_PAR_COUNTS_GENE_LENGTH_SCALED")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_COUNTS_GENE_LENGTH_SCALED")"
fi
if [ ! -z "$VIASH_PAR_COUNTS_GENE_SCALED" ] && [ ! -d "$(dirname "$VIASH_PAR_COUNTS_GENE_SCALED")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_COUNTS_GENE_SCALED")"
fi
if [ ! -z "$VIASH_PAR_TPM_TRANSCRIPT" ] && [ ! -d "$(dirname "$VIASH_PAR_TPM_TRANSCRIPT")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_TPM_TRANSCRIPT")"
fi
if [ ! -z "$VIASH_PAR_LENGTHS_GENE" ] && [ ! -d "$(dirname "$VIASH_PAR_LENGTHS_GENE")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_LENGTHS_GENE")"
fi
if [ ! -z "$VIASH_PAR_COUNTS_TRANSCRIPT" ] && [ ! -d "$(dirname "$VIASH_PAR_COUNTS_TRANSCRIPT")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_COUNTS_TRANSCRIPT")"
fi
if [ ! -z "$VIASH_PAR_LENGTHS_TRANSCRIPT" ] && [ ! -d "$(dirname "$VIASH_PAR_LENGTHS_TRANSCRIPT")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_LENGTHS_TRANSCRIPT")"
fi
if [ ! -z "$VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT" ] && [ ! -d "$(dirname "$VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT")"
fi
if [ "$VIASH_ENGINE_ID" == "native" ] ; then
if [ "$VIASH_MODE" == "run" ]; then
VIASH_CMD="bash"
else
ViashError "Engine '$VIASH_ENGINE_ID' does not support mode '$VIASH_MODE'."
exit 1
fi
fi
# set dependency paths
VIASH_DEP_TX2GENE="$VIASH_META_RESOURCES_DIR/../../../nextflow/tx2gene/main.nf"
VIASH_DEP_TXIMPORT="$VIASH_META_RESOURCES_DIR/../../../nextflow/tximport/main.nf"
VIASH_DEP_SUMMARIZEDEXPERIMENT="$VIASH_META_RESOURCES_DIR/../../../nextflow/summarizedexperiment/main.nf"
ViashDebug "Running command: $(echo $VIASH_CMD)"
cat << VIASHEOF | eval $VIASH_CMD
set -e
tempscript=\$(mktemp "$VIASH_META_TEMP_DIR/viash-run-merge_quant_results-XXXXXX").nf
function clean_up {
rm "\$tempscript"
}
function interrupt {
echo -e "\nCTRL-C Pressed..."
exit 1
}
trap clean_up EXIT
trap interrupt INT SIGINT
cat > "\$tempscript" << 'VIASHMAIN'
//// VIASH START
// The following code has been auto-generated by Viash.
//// VIASH END
workflow run_wf {
take:
input_ch
main:
output_ch = input_ch
| map { id, state ->
def quant_results = state.quant_type == 'kallisto' ? state.kallisto_quant_results : state.salmon_quant_results
[id, state + [quant_results: quant_results]]
}
| tx2gene.run (
fromState: [
"quant_results": "quant_results",
"gtf_extra_attributes": "gtf_extra_attributes",
"gtf": "gtf",
"gtf_group_features": "gtf_group_features",
"quant_type": "quant_type"
],
toState: [ "tx2gene_tsv": "tsv" ]
)
| tximport.run (
fromState: [
"quant_results": "quant_results",
"tx2gene_tsv": "tx2gene_tsv",
"quant_type": "quant_type"
],
toState: [
"tpm_gene": "tpm_gene",
"counts_gene": "counts_gene",
"counts_gene_length_scaled": "counts_gene_length_scaled",
"counts_gene_scaled": "counts_gene_scaled",
"tpm_transcript": "tpm_transcript",
"counts_transcript": "counts_transcript",
"length_gene": "length_gene",
"length_transcript": "length_transcript"
]
)
| summarizedexperiment.run (
fromState: [
"tpm_gene": "tpm_gene",
"counts_gene": "counts_gene",
"counts_gene_length_scaled": "counts_gene_length_scaled",
"counts_gene_scaled": "counts_gene_scaled",
"tpm_transcript": "tpm_transcript",
"counts_transcript": "counts_transcript",
"tx2gene_tsv": "tx2gene_tsv"
],
toState: [ "quant_merged_summarizedexperiment": "output" ]
)
| setState (
[ "tpm_gene": "tpm_gene",
"counts_gene": "counts_gene",
"counts_gene_length_scaled": "counts_gene_length_scaled",
"counts_gene_scaled": "counts_gene_scaled",
"tpm_transcript": "tpm_transcript",
"counts_transcript": "counts_transcript",
"quant_merged_summarizedexperiment": "quant_merged_summarizedexperiment" ]
)
emit:
output_ch
}
VIASHMAIN
nextflow run . -main-script "\$tempscript" &
wait "\$!"
VIASHEOF
# check whether required files exist
if [ ! -z "$VIASH_PAR_TPM_GENE" ] && [ ! -e "$VIASH_PAR_TPM_GENE" ]; then
ViashError "Output file '$VIASH_PAR_TPM_GENE' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_COUNTS_GENE" ] && [ ! -e "$VIASH_PAR_COUNTS_GENE" ]; then
ViashError "Output file '$VIASH_PAR_COUNTS_GENE' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_COUNTS_GENE_LENGTH_SCALED" ] && [ ! -e "$VIASH_PAR_COUNTS_GENE_LENGTH_SCALED" ]; then
ViashError "Output file '$VIASH_PAR_COUNTS_GENE_LENGTH_SCALED' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_COUNTS_GENE_SCALED" ] && [ ! -e "$VIASH_PAR_COUNTS_GENE_SCALED" ]; then
ViashError "Output file '$VIASH_PAR_COUNTS_GENE_SCALED' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_TPM_TRANSCRIPT" ] && [ ! -e "$VIASH_PAR_TPM_TRANSCRIPT" ]; then
ViashError "Output file '$VIASH_PAR_TPM_TRANSCRIPT' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_LENGTHS_GENE" ] && [ ! -e "$VIASH_PAR_LENGTHS_GENE" ]; then
ViashError "Output file '$VIASH_PAR_LENGTHS_GENE' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_COUNTS_TRANSCRIPT" ] && [ ! -e "$VIASH_PAR_COUNTS_TRANSCRIPT" ]; then
ViashError "Output file '$VIASH_PAR_COUNTS_TRANSCRIPT' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_LENGTHS_TRANSCRIPT" ] && [ ! -e "$VIASH_PAR_LENGTHS_TRANSCRIPT" ]; then
ViashError "Output file '$VIASH_PAR_LENGTHS_TRANSCRIPT' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT" ] && [ ! -e "$VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT" ]; then
ViashError "Output file '$VIASH_PAR_QUANT_MERGED_SUMMARIZEDEXPERIMENT' does not exist."
exit 1
fi
exit 0

513
target/executable/workflows/post_processing/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,513 @@
name: "post_processing"
namespace: "workflows"
version: "main"
argument_groups:
- name: "Input"
arguments:
- type: "string"
name: "--id"
description: "ID of the sample."
info: null
example:
- "foo"
required: true
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: "boolean"
name: "--paired"
description: "Paired fastq files or not?"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fasta"
description: "Path to FASTA genome file."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fai"
description: "Path to FASTA index"
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gtf"
description: "GTF file"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_bam"
description: "Genome BAM file"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--chrom_sizes"
description: "File containing chromosome lengths"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--star_multiqc"
description: "STAR align log file."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--extra_picard_args"
description: "Extra arguments to pass to picard MarkDuplicates command in addition\
\ to defaults defined by the pipeline."
info: null
default:
- ""
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--extra_stringtie_args"
description: "Extra arguments to pass to stringtie command in addition to defaults\
\ defined by the pipeline."
info: null
default:
- ""
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--stringtie_ignore_gtf"
description: "Perform reference-guided de novo assembly of transcripts using StringTie,\
\ i.e. don't restrict to those in GTF file."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--extra_bedtools_args"
description: "Extra arguments to pass to bedtools genomecov command in addition\
\ to defaults defined by the pipeline."
info: null
default:
- ""
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--bam_csi_index"
description: "Create a CSI index for BAM files instead of the traditional BAI\
\ index. This will be required for genomes with larger chromosome sizes."
info: null
default:
- false
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_mapped_reads"
description: "Minimum percentage of uniquely mapped reads below which samples\
\ are removed from further processing."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- 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_qc"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--skip_markduplicates"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--skip_stringtie"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--skip_bigwig"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--processed_genome_bam"
info: null
default:
- "$id.markdup.sorted.bam"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_bam_index"
info: null
default:
- "$id.markdup.sorted.bam"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_bam_stats"
info: null
default:
- "$id.markdup.sorted.bam.stats"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_bam_flagstat"
info: null
default:
- "$id.markdup.sorted.bam.flagstat"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_bam_idxstats"
info: null
default:
- "$id.markdup.sorted.bam.idxstats"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--markduplicates_metrics"
info: null
default:
- "$id.markdup.sorted.MarkDuplicates.metrics.txt"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--stringtie_transcript_gtf"
info: null
default:
- "$id.stringtie.transcripts.gtf"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--stringtie_coverage_gtf"
info: null
default:
- "$id.stringtie.coverage.gtf"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--stringtie_abundance"
info: null
default:
- "$id.stringtie.gene_abundance.txt"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--stringtie_ballgown"
info: null
default:
- "$id.stringtie.ballgown"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bedgraph_forward"
info: null
default:
- "$id.forward.bedgraph"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bedgraph_reverse"
info: null
default:
- "$id.reverse.bedgraph"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bigwig_forward"
info: null
default:
- "$id.forward.bigwig"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bigwig_reverse"
info: null
default:
- "$id.reverse.bigwig"
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 viash sub-workflow for the post-processing stage of nf-core/rnaseq\
\ pipeline.\n"
info: null
status: "enabled"
requirements:
commands:
- "ps"
dependencies:
- name: "picard_markduplicates"
repository:
type: "local"
- name: "samtools/samtools_sort"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.1"
- name: "samtools/samtools_index"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.1"
- name: "samtools/samtools_stats"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.1"
- name: "samtools/samtools_flagstat"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.1"
- name: "samtools/samtools_idxstats"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.1"
- name: "stringtie"
repository:
type: "local"
- name: "bedtools_genomecov"
repository:
type: "local"
- name: "ucsc/bedclip"
repository:
type: "local"
- name: "ucsc/bedgraphtobigwig"
repository:
type: "local"
repositories:
- type: "vsh"
name: "biobox"
repo: "vsh/biobox"
tag: "v0.1"
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/post_processing/config.vsh.yaml"
runner: "executable"
engine: "native"
output: "target/executable/workflows/post_processing"
executable: "target/executable/workflows/post_processing/post_processing"
viash_version: "0.9.0"
git_commit: "1e1ffb315fefec05db2ee0c62e1c98ce4b49929c"
git_remote: "https://github.com/viash-hub/rnaseq"
dependencies:
- "target/nextflow/picard_markduplicates"
- "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_sort"
- "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_index"
- "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_stats"
- "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_flagstat"
- "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/samtools/samtools_idxstats"
- "target/nextflow/stringtie"
- "target/nextflow/bedtools_genomecov"
- "target/nextflow/ucsc/bedclip"
- "target/nextflow/ucsc/bedgraphtobigwig"
package_config:
version: "main"
info:
test_resources:
- path: "gs://viash-hub-test-data/rnaseq/v1"
dest: "testData"
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"

1397
target/executable/workflows/post_processing/post_processing Executable file
View File

File diff suppressed because it is too large Load Diff

669
target/executable/workflows/pre_processing/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,669 @@
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"
name: "--skip_bbsplit"
description: "Skip BBSplit for removal of non-reference genome reads."
info: null
default:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--remove_ribo_rna"
description: "Enable the removal of reads derived from ribosomal RNA using SortMeRNA."
info: null
default:
- false
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- 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:
- "$id.$key.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:
- "$id.$key.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: ";"
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: "trimgalore"
repository:
type: "local"
- name: "bbmap_bbsplit"
repository:
type: "local"
- name: "sortmerna"
repository:
type: "local"
- name: "fastp"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.1"
- name: "fq_subsample"
repository:
type: "local"
- name: "salmon/salmon_quant"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.1"
repositories:
- type: "vsh"
name: "biobox"
repo: "vsh/biobox"
tag: "v0.1"
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: "1e1ffb315fefec05db2ee0c62e1c98ce4b49929c"
git_remote: "https://github.com/viash-hub/rnaseq"
dependencies:
- "target/nextflow/fastqc"
- "target/nextflow/umitools/umitools_extract"
- "target/nextflow/trimgalore"
- "target/nextflow/bbmap_bbsplit"
- "target/nextflow/sortmerna"
- "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/fastp"
- "target/nextflow/fq_subsample"
- "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/salmon/salmon_quant"
package_config:
version: "main"
info:
test_resources:
- path: "gs://viash-hub-test-data/rnaseq/v1"
dest: "testData"
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"

1740
target/executable/workflows/pre_processing/pre_processing Executable file
View File

File diff suppressed because it is too large Load Diff

530
target/executable/workflows/prepare_genome/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,530 @@
name: "prepare_genome"
namespace: "workflows"
version: "main"
argument_groups:
- name: "Input"
arguments:
- type: "file"
name: "--fasta"
description: "Path to FASTA genome file."
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gtf"
description: "Path to GTF annotation file. This parameter is *mandatory* if --genome\
\ is not specified."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gff"
description: "Path to GFF3 annotation file. Required if \"--gtf\" is not specified."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--additional_fasta"
description: "FASTA file to concatenate to genome FASTA file e.g. containing spike-in\
\ sequences."
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: "--gene_bed"
description: "Path to BED file containing gene intervals. This will be created\
\ from the GTF file if not specified."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--splicesites"
description: "Splice sites file required for HISAT2."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--skip_bbsplit"
description: "Skip BBSplit for removal of non-reference genome reads."
info: null
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: "--star_index"
description: "Path to directory or tar.gz archive for pre-built STAR index."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--rsem_index"
description: "Path to directory or tar.gz archive for pre-built RSEM index."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "extra_rsem_prepare_reference_args"
description: "Extra arguments to pass to rsem-prepare-reference command in addition\
\ to defaults defined by the pipeline."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--salmon_index"
description: "Path to directory or tar.gz archive for pre-built Salmon index."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--kallisto_index"
description: "Path to directory or tar.gz archive for pre-built Kallisto index."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bbsplit_index"
description: "Path to directory or tar.gz archive for pre-built BBSplit index."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--pseudo_aligner_kmer_size"
description: "Kmer length passed to indexing step of pseudoaligners."
info: null
default:
- 31
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--gencode"
description: "Specify if the GTF annotation is in GENCODE format."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--biotype"
description: "Biotype value to use while appending entries to GTF file when additional\
\ fasta file is provided."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--filter_gtf"
description: "Whether to filter the GTF or not?"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--aligner"
description: "Specifies the alignment algorithm to use - available options are\
\ 'star_salmon', 'star_rsem' and 'hisat2'."
info: null
default:
- "star_salmon"
required: false
choices:
- "star_salmon"
- "star_rsem"
- "hisat2"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--pseudo_aligner"
description: "Specifies the pseudo aligner to use - available options are 'salmon'.\
\ Runs in addition to '--aligner'."
info: null
default:
- "salmon"
required: false
choices:
- "salmon"
- "kallisto"
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--fasta_uncompressed"
info: null
default:
- "reference_genome.fasta"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gtf_uncompressed"
info: null
default:
- "gene_annotation.gtf"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--transcript_fasta_uncompressed"
info: null
default:
- "transcriptome.fasta"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gene_bed_uncompressed"
info: null
default:
- "gene_annotation.bed"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--star_index_uncompressed"
description: "Path to STAR index."
info: null
default:
- "STAR_index"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--rsem_index_uncompressed"
description: "Path to directory or tar.gz archive for pre-built RSEM index."
info: null
default:
- "RSEM_index"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--salmon_index_uncompressed"
description: "Path to Salmon index."
info: null
default:
- "Salmon_index"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--kallisto_index_uncompressed"
description: "Path to Kallisto index."
info: null
default:
- "Kallisto_index"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--bbsplit_index_uncompressed"
description: "Path to BBSplit index."
info: null
default:
- "BBSplit_index"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--chrom_sizes"
description: "File containing chromosome lengths"
info: null
default:
- "reference_genome.fasta.sizes"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--fai"
description: "FASTA index file"
info: null
default:
- "reference_genome.fasta.fai"
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 preparing all the required genome references\n"
info: null
status: "enabled"
requirements:
commands:
- "ps"
dependencies:
- name: "gunzip"
repository:
type: "local"
- name: "gffread"
repository:
type: "vsh"
repo: "biobox"
tag: "main"
- name: "cat_additional_fasta"
repository:
type: "local"
- name: "gtf2bed"
repository:
type: "local"
- name: "preprocess_transcripts_fasta"
repository:
type: "local"
- name: "gtf_filter"
repository:
type: "local"
- name: "rsem/rsem_prepare_reference"
repository:
type: "vsh"
repo: "biobox"
tag: "main"
- name: "getchromsizes"
repository:
type: "local"
- name: "untar"
repository:
type: "vsh"
repo: "craftbox"
tag: "main"
- name: "star/star_genome_generate"
repository:
type: "vsh"
repo: "biobox"
tag: "main"
- name: "bbmap_bbsplit"
repository:
type: "local"
- name: "salmon/salmon_index"
repository:
type: "vsh"
repo: "biobox"
tag: "main"
- name: "kallisto/kallisto_index"
repository:
type: "local"
repositories:
- type: "vsh"
name: "biobox"
repo: "biobox"
tag: "main"
- type: "vsh"
name: "craftbox"
repo: "craftbox"
tag: "main"
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/prepare_genome/config.vsh.yaml"
runner: "executable"
engine: "native"
output: "target/executable/workflows/prepare_genome"
executable: "target/executable/workflows/prepare_genome/prepare_genome"
viash_version: "0.9.0"
git_commit: "1e1ffb315fefec05db2ee0c62e1c98ce4b49929c"
git_remote: "https://github.com/viash-hub/rnaseq"
dependencies:
- "target/nextflow/gunzip"
- "target/dependencies/vsh/vsh/biobox/main/nextflow/gffread"
- "target/nextflow/cat_additional_fasta"
- "target/nextflow/gtf2bed"
- "target/nextflow/preprocess_transcripts_fasta"
- "target/nextflow/gtf_filter"
- "target/dependencies/vsh/vsh/biobox/main/nextflow/rsem/rsem_prepare_reference"
- "target/nextflow/getchromsizes"
- "target/dependencies/vsh/vsh/craftbox/main/nextflow/untar"
- "target/dependencies/vsh/vsh/biobox/main/nextflow/star/star_genome_generate"
- "target/nextflow/bbmap_bbsplit"
- "target/dependencies/vsh/vsh/biobox/main/nextflow/salmon/salmon_index"
- "target/nextflow/kallisto/kallisto_index"
package_config:
version: "main"
info:
test_resources:
- path: "gs://viash-hub-test-data/rnaseq/v1"
dest: "testData"
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"

1465
target/executable/workflows/prepare_genome/prepare_genome Executable file
View File

File diff suppressed because it is too large Load Diff

304
target/executable/workflows/pseudo_alignment_and_quant/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,304 @@
name: "pseudo_alignment_and_quant"
namespace: "workflows"
version: "main"
argument_groups:
- name: "Input"
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"
alternatives:
- "-i"
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: true
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, or\
\ reverse"
info: null
required: false
choices:
- "forward"
- "reverse"
- "unstranded"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--gtf"
description: "GTF file"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--transcript_fasta"
description: "Fasta file of the reference transcriptome."
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--pseudo_aligner"
description: "Specifies the pseudo aligner to use - available options are 'salmon'.\
\ Runs in addition to '--aligner'."
info: null
default:
- "false"
required: false
choices:
- "salmon"
- "kallisto"
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--salmon_index"
description: "Salmon index"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--kallisto_index"
description: "Kallisto index"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--lib_type"
description: "Override library type inferred based on strandedness defined in\
\ meta object"
info: null
default:
- ""
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--kallisto_quant_fragment_length"
description: "For single-end mode only, the estimated average fragment length\
\ to use for quantification with Kallisto."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--kallisto_quant_fragment_length_sd"
description: "For single-end mode only, the estimated standard deviation of the\
\ fragment length for quantification with Kallisto."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--pseudo_multiqc"
info: null
default:
- "$id.quant.log"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--quant_out_dir"
info: null
default:
- "$id.salmon_quant"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--salmon_quant_results_file"
info: null
default:
- "$id.quant.sf"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--kallisto_quant_results_file"
info: null
default:
- "$id.abundance.tsv"
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 viash sub-workflow for pseudo alignment and quantification stage of\
\ nf-core/rnaseq pipeline.\n"
info: null
status: "enabled"
requirements:
commands:
- "ps"
dependencies:
- name: "salmon/salmon_quant"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "v0.1"
- name: "kallisto/kallisto_quant"
repository:
type: "local"
repositories:
- type: "vsh"
name: "biobox"
repo: "vsh/biobox"
tag: "v0.1"
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/pseudo_alignment_and_quant/config.vsh.yaml"
runner: "executable"
engine: "native"
output: "target/executable/workflows/pseudo_alignment_and_quant"
executable: "target/executable/workflows/pseudo_alignment_and_quant/pseudo_alignment_and_quant"
viash_version: "0.9.0"
git_commit: "1e1ffb315fefec05db2ee0c62e1c98ce4b49929c"
git_remote: "https://github.com/viash-hub/rnaseq"
dependencies:
- "target/dependencies/vsh/vsh/biobox/v0.1/nextflow/salmon/salmon_quant"
- "target/nextflow/kallisto/kallisto_quant"
package_config:
version: "main"
info:
test_resources:
- path: "gs://viash-hub-test-data/rnaseq/v1"
dest: "testData"
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"

918
target/executable/workflows/pseudo_alignment_and_quant/pseudo_alignment_and_quant Executable file
View File

@@ -0,0 +1,918 @@
#!/usr/bin/env bash
# pseudo_alignment_and_quant main
#
# 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.
set -e
if [ -z "$VIASH_TEMP" ]; then
VIASH_TEMP=${VIASH_TEMP:-$VIASH_TMPDIR}
VIASH_TEMP=${VIASH_TEMP:-$VIASH_TEMPDIR}
VIASH_TEMP=${VIASH_TEMP:-$VIASH_TMP}
VIASH_TEMP=${VIASH_TEMP:-$TMPDIR}
VIASH_TEMP=${VIASH_TEMP:-$TMP}
VIASH_TEMP=${VIASH_TEMP:-$TEMPDIR}
VIASH_TEMP=${VIASH_TEMP:-$TEMP}
VIASH_TEMP=${VIASH_TEMP:-/tmp}
fi
# define helper functions
# ViashQuote: put quotes around non flag values
# $1 : unquoted string
# return : possibly quoted string
# examples:
# ViashQuote --foo # returns --foo
# ViashQuote bar # returns 'bar'
# Viashquote --foo=bar # returns --foo='bar'
function ViashQuote {
if [[ "$1" =~ ^-+[a-zA-Z0-9_\-]+=.+$ ]]; then
echo "$1" | sed "s#=\(.*\)#='\1'#"
elif [[ "$1" =~ ^-+[a-zA-Z0-9_\-]+$ ]]; then
echo "$1"
else
echo "'$1'"
fi
}
# ViashRemoveFlags: Remove leading flag
# $1 : string with a possible leading flag
# return : string without possible leading flag
# examples:
# ViashRemoveFlags --foo=bar # returns bar
function ViashRemoveFlags {
echo "$1" | sed 's/^--*[a-zA-Z0-9_\-]*=//'
}
# ViashSourceDir: return the path of a bash file, following symlinks
# usage : ViashSourceDir ${BASH_SOURCE[0]}
# $1 : Should always be set to ${BASH_SOURCE[0]}
# returns : The absolute path of the bash file
function ViashSourceDir {
local source="$1"
while [ -h "$source" ]; do
local dir="$( cd -P "$( dirname "$source" )" >/dev/null 2>&1 && pwd )"
source="$(readlink "$source")"
[[ $source != /* ]] && source="$dir/$source"
done
cd -P "$( dirname "$source" )" >/dev/null 2>&1 && pwd
}
# ViashFindTargetDir: return the path of the '.build.yaml' file, following symlinks
# usage : ViashFindTargetDir 'ScriptPath'
# $1 : The location from where to start the upward search
# returns : The absolute path of the '.build.yaml' file
function ViashFindTargetDir {
local source="$1"
while [[ "$source" != "" && ! -e "$source/.build.yaml" ]]; do
source=${source%/*}
done
echo $source
}
# see https://en.wikipedia.org/wiki/Syslog#Severity_level
VIASH_LOGCODE_EMERGENCY=0
VIASH_LOGCODE_ALERT=1
VIASH_LOGCODE_CRITICAL=2
VIASH_LOGCODE_ERROR=3
VIASH_LOGCODE_WARNING=4
VIASH_LOGCODE_NOTICE=5
VIASH_LOGCODE_INFO=6
VIASH_LOGCODE_DEBUG=7
VIASH_VERBOSITY=$VIASH_LOGCODE_NOTICE
# ViashLog: Log events depending on the verbosity level
# usage: ViashLog 1 alert Oh no something went wrong!
# $1: required verbosity level
# $2: display tag
# $3+: messages to display
# stdout: Your input, prepended by '[$2] '.
function ViashLog {
local required_level="$1"
local display_tag="$2"
shift 2
if [ $VIASH_VERBOSITY -ge $required_level ]; then
>&2 echo "[$display_tag]" "$@"
fi
}
# ViashEmergency: log events when the system is unstable
# usage: ViashEmergency Oh no something went wrong.
# stdout: Your input, prepended by '[emergency] '.
function ViashEmergency {
ViashLog $VIASH_LOGCODE_EMERGENCY emergency "$@"
}
# ViashAlert: log events when actions must be taken immediately (e.g. corrupted system database)
# usage: ViashAlert Oh no something went wrong.
# stdout: Your input, prepended by '[alert] '.
function ViashAlert {
ViashLog $VIASH_LOGCODE_ALERT alert "$@"
}
# ViashCritical: log events when a critical condition occurs
# usage: ViashCritical Oh no something went wrong.
# stdout: Your input, prepended by '[critical] '.
function ViashCritical {
ViashLog $VIASH_LOGCODE_CRITICAL critical "$@"
}
# ViashError: log events when an error condition occurs
# usage: ViashError Oh no something went wrong.
# stdout: Your input, prepended by '[error] '.
function ViashError {
ViashLog $VIASH_LOGCODE_ERROR error "$@"
}
# ViashWarning: log potentially abnormal events
# usage: ViashWarning Something may have gone wrong.
# stdout: Your input, prepended by '[warning] '.
function ViashWarning {
ViashLog $VIASH_LOGCODE_WARNING warning "$@"
}
# ViashNotice: log significant but normal events
# usage: ViashNotice This just happened.
# stdout: Your input, prepended by '[notice] '.
function ViashNotice {
ViashLog $VIASH_LOGCODE_NOTICE notice "$@"
}
# ViashInfo: log normal events
# usage: ViashInfo This just happened.
# stdout: Your input, prepended by '[info] '.
function ViashInfo {
ViashLog $VIASH_LOGCODE_INFO info "$@"
}
# ViashDebug: log all events, for debugging purposes
# usage: ViashDebug This just happened.
# stdout: Your input, prepended by '[debug] '.
function ViashDebug {
ViashLog $VIASH_LOGCODE_DEBUG debug "$@"
}
# find source folder of this component
VIASH_META_RESOURCES_DIR=`ViashSourceDir ${BASH_SOURCE[0]}`
# find the root of the built components & dependencies
VIASH_TARGET_DIR=`ViashFindTargetDir $VIASH_META_RESOURCES_DIR`
# define meta fields
VIASH_META_NAME="pseudo_alignment_and_quant"
VIASH_META_FUNCTIONALITY_NAME="pseudo_alignment_and_quant"
VIASH_META_EXECUTABLE="$VIASH_META_RESOURCES_DIR/$VIASH_META_NAME"
VIASH_META_CONFIG="$VIASH_META_RESOURCES_DIR/.config.vsh.yaml"
VIASH_META_TEMP_DIR="$VIASH_TEMP"
# ViashHelp: Display helpful explanation about this executable
function ViashHelp {
echo "pseudo_alignment_and_quant main"
echo ""
echo "A viash sub-workflow for pseudo alignment and quantification stage of"
echo "nf-core/rnaseq pipeline."
echo ""
echo "Input:"
echo " --id"
echo " type: string, required parameter"
echo " example: foo"
echo " ID of the sample."
echo ""
echo " -i, --fastq_1"
echo " type: file, required parameter, file must exist"
echo " example: input.fastq.gz"
echo " Path to the sample (or read 1 of paired end sample)."
echo ""
echo " --fastq_2"
echo " type: file, file must exist"
echo " Path to read 2 of the sample."
echo ""
echo " --strandedness"
echo " type: string"
echo " choices: [ forward, reverse, unstranded ]"
echo " Sample strand-specificity. Must be one of unstranded, forward, or"
echo " reverse"
echo ""
echo " --gtf"
echo " type: file, file must exist"
echo " GTF file"
echo ""
echo " --transcript_fasta"
echo " type: file, file must exist"
echo " Fasta file of the reference transcriptome."
echo ""
echo " --pseudo_aligner"
echo " type: string"
echo " default: false"
echo " choices: [ salmon, kallisto ]"
echo " Specifies the pseudo aligner to use - available options are 'salmon'."
echo " Runs in addition to '--aligner'."
echo ""
echo " --salmon_index"
echo " type: file, file must exist"
echo " Salmon index"
echo ""
echo " --kallisto_index"
echo " type: file, file must exist"
echo " Kallisto index"
echo ""
echo " --lib_type"
echo " type: string"
echo " default:"
echo " Override library type inferred based on strandedness defined in meta"
echo " object"
echo ""
echo " --kallisto_quant_fragment_length"
echo " type: integer"
echo " For single-end mode only, the estimated average fragment length to use"
echo " for quantification with Kallisto."
echo ""
echo " --kallisto_quant_fragment_length_sd"
echo " type: integer"
echo " For single-end mode only, the estimated standard deviation of the"
echo " fragment length for quantification with Kallisto."
echo ""
echo "Output:"
echo " --pseudo_multiqc"
echo " type: file, output, file must exist"
echo " default: \$id.quant.log"
echo ""
echo " --quant_out_dir"
echo " type: file, output, file must exist"
echo " default: \$id.salmon_quant"
echo ""
echo " --salmon_quant_results_file"
echo " type: file, output, file must exist"
echo " default: \$id.quant.sf"
echo ""
echo " --kallisto_quant_results_file"
echo " type: file, output, file must exist"
echo " default: \$id.abundance.tsv"
}
# initialise variables
VIASH_MODE='run'
VIASH_ENGINE_ID='native'
# initialise array
VIASH_POSITIONAL_ARGS=''
while [[ $# -gt 0 ]]; do
case "$1" in
-h|--help)
ViashHelp
exit
;;
---v|---verbose)
let "VIASH_VERBOSITY=VIASH_VERBOSITY+1"
shift 1
;;
---verbosity)
VIASH_VERBOSITY="$2"
shift 2
;;
---verbosity=*)
VIASH_VERBOSITY="$(ViashRemoveFlags "$1")"
shift 1
;;
--version)
echo "pseudo_alignment_and_quant main"
exit
;;
--id)
[ -n "$VIASH_PAR_ID" ] && ViashError Bad arguments for option \'--id\': \'$VIASH_PAR_ID\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_ID="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --id. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--id=*)
[ -n "$VIASH_PAR_ID" ] && ViashError Bad arguments for option \'--id=*\': \'$VIASH_PAR_ID\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_ID=$(ViashRemoveFlags "$1")
shift 1
;;
--fastq_1)
[ -n "$VIASH_PAR_FASTQ_1" ] && ViashError Bad arguments for option \'--fastq_1\': \'$VIASH_PAR_FASTQ_1\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_FASTQ_1="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --fastq_1. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--fastq_1=*)
[ -n "$VIASH_PAR_FASTQ_1" ] && ViashError Bad arguments for option \'--fastq_1=*\': \'$VIASH_PAR_FASTQ_1\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_FASTQ_1=$(ViashRemoveFlags "$1")
shift 1
;;
-i)
[ -n "$VIASH_PAR_FASTQ_1" ] && ViashError Bad arguments for option \'-i\': \'$VIASH_PAR_FASTQ_1\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_FASTQ_1="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to -i. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--fastq_2)
[ -n "$VIASH_PAR_FASTQ_2" ] && ViashError Bad arguments for option \'--fastq_2\': \'$VIASH_PAR_FASTQ_2\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_FASTQ_2="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --fastq_2. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--fastq_2=*)
[ -n "$VIASH_PAR_FASTQ_2" ] && ViashError Bad arguments for option \'--fastq_2=*\': \'$VIASH_PAR_FASTQ_2\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_FASTQ_2=$(ViashRemoveFlags "$1")
shift 1
;;
--strandedness)
[ -n "$VIASH_PAR_STRANDEDNESS" ] && ViashError Bad arguments for option \'--strandedness\': \'$VIASH_PAR_STRANDEDNESS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_STRANDEDNESS="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --strandedness. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--strandedness=*)
[ -n "$VIASH_PAR_STRANDEDNESS" ] && ViashError Bad arguments for option \'--strandedness=*\': \'$VIASH_PAR_STRANDEDNESS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_STRANDEDNESS=$(ViashRemoveFlags "$1")
shift 1
;;
--gtf)
[ -n "$VIASH_PAR_GTF" ] && ViashError Bad arguments for option \'--gtf\': \'$VIASH_PAR_GTF\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_GTF="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --gtf. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--gtf=*)
[ -n "$VIASH_PAR_GTF" ] && ViashError Bad arguments for option \'--gtf=*\': \'$VIASH_PAR_GTF\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_GTF=$(ViashRemoveFlags "$1")
shift 1
;;
--transcript_fasta)
[ -n "$VIASH_PAR_TRANSCRIPT_FASTA" ] && ViashError Bad arguments for option \'--transcript_fasta\': \'$VIASH_PAR_TRANSCRIPT_FASTA\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_TRANSCRIPT_FASTA="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --transcript_fasta. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--transcript_fasta=*)
[ -n "$VIASH_PAR_TRANSCRIPT_FASTA" ] && ViashError Bad arguments for option \'--transcript_fasta=*\': \'$VIASH_PAR_TRANSCRIPT_FASTA\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_TRANSCRIPT_FASTA=$(ViashRemoveFlags "$1")
shift 1
;;
--pseudo_aligner)
[ -n "$VIASH_PAR_PSEUDO_ALIGNER" ] && ViashError Bad arguments for option \'--pseudo_aligner\': \'$VIASH_PAR_PSEUDO_ALIGNER\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_PSEUDO_ALIGNER="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --pseudo_aligner. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--pseudo_aligner=*)
[ -n "$VIASH_PAR_PSEUDO_ALIGNER" ] && ViashError Bad arguments for option \'--pseudo_aligner=*\': \'$VIASH_PAR_PSEUDO_ALIGNER\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_PSEUDO_ALIGNER=$(ViashRemoveFlags "$1")
shift 1
;;
--salmon_index)
[ -n "$VIASH_PAR_SALMON_INDEX" ] && ViashError Bad arguments for option \'--salmon_index\': \'$VIASH_PAR_SALMON_INDEX\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_SALMON_INDEX="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --salmon_index. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--salmon_index=*)
[ -n "$VIASH_PAR_SALMON_INDEX" ] && ViashError Bad arguments for option \'--salmon_index=*\': \'$VIASH_PAR_SALMON_INDEX\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_SALMON_INDEX=$(ViashRemoveFlags "$1")
shift 1
;;
--kallisto_index)
[ -n "$VIASH_PAR_KALLISTO_INDEX" ] && ViashError Bad arguments for option \'--kallisto_index\': \'$VIASH_PAR_KALLISTO_INDEX\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_KALLISTO_INDEX="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --kallisto_index. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--kallisto_index=*)
[ -n "$VIASH_PAR_KALLISTO_INDEX" ] && ViashError Bad arguments for option \'--kallisto_index=*\': \'$VIASH_PAR_KALLISTO_INDEX\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_KALLISTO_INDEX=$(ViashRemoveFlags "$1")
shift 1
;;
--lib_type)
[ -n "$VIASH_PAR_LIB_TYPE" ] && ViashError Bad arguments for option \'--lib_type\': \'$VIASH_PAR_LIB_TYPE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_LIB_TYPE="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --lib_type. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--lib_type=*)
[ -n "$VIASH_PAR_LIB_TYPE" ] && ViashError Bad arguments for option \'--lib_type=*\': \'$VIASH_PAR_LIB_TYPE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_LIB_TYPE=$(ViashRemoveFlags "$1")
shift 1
;;
--kallisto_quant_fragment_length)
[ -n "$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH" ] && ViashError Bad arguments for option \'--kallisto_quant_fragment_length\': \'$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --kallisto_quant_fragment_length. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--kallisto_quant_fragment_length=*)
[ -n "$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH" ] && ViashError Bad arguments for option \'--kallisto_quant_fragment_length=*\': \'$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH=$(ViashRemoveFlags "$1")
shift 1
;;
--kallisto_quant_fragment_length_sd)
[ -n "$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH_SD" ] && ViashError Bad arguments for option \'--kallisto_quant_fragment_length_sd\': \'$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH_SD\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH_SD="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --kallisto_quant_fragment_length_sd. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--kallisto_quant_fragment_length_sd=*)
[ -n "$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH_SD" ] && ViashError Bad arguments for option \'--kallisto_quant_fragment_length_sd=*\': \'$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH_SD\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH_SD=$(ViashRemoveFlags "$1")
shift 1
;;
--pseudo_multiqc)
[ -n "$VIASH_PAR_PSEUDO_MULTIQC" ] && ViashError Bad arguments for option \'--pseudo_multiqc\': \'$VIASH_PAR_PSEUDO_MULTIQC\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_PSEUDO_MULTIQC="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --pseudo_multiqc. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--pseudo_multiqc=*)
[ -n "$VIASH_PAR_PSEUDO_MULTIQC" ] && ViashError Bad arguments for option \'--pseudo_multiqc=*\': \'$VIASH_PAR_PSEUDO_MULTIQC\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_PSEUDO_MULTIQC=$(ViashRemoveFlags "$1")
shift 1
;;
--quant_out_dir)
[ -n "$VIASH_PAR_QUANT_OUT_DIR" ] && ViashError Bad arguments for option \'--quant_out_dir\': \'$VIASH_PAR_QUANT_OUT_DIR\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_QUANT_OUT_DIR="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --quant_out_dir. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--quant_out_dir=*)
[ -n "$VIASH_PAR_QUANT_OUT_DIR" ] && ViashError Bad arguments for option \'--quant_out_dir=*\': \'$VIASH_PAR_QUANT_OUT_DIR\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_QUANT_OUT_DIR=$(ViashRemoveFlags "$1")
shift 1
;;
--salmon_quant_results_file)
[ -n "$VIASH_PAR_SALMON_QUANT_RESULTS_FILE" ] && ViashError Bad arguments for option \'--salmon_quant_results_file\': \'$VIASH_PAR_SALMON_QUANT_RESULTS_FILE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_SALMON_QUANT_RESULTS_FILE="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --salmon_quant_results_file. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--salmon_quant_results_file=*)
[ -n "$VIASH_PAR_SALMON_QUANT_RESULTS_FILE" ] && ViashError Bad arguments for option \'--salmon_quant_results_file=*\': \'$VIASH_PAR_SALMON_QUANT_RESULTS_FILE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_SALMON_QUANT_RESULTS_FILE=$(ViashRemoveFlags "$1")
shift 1
;;
--kallisto_quant_results_file)
[ -n "$VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE" ] && ViashError Bad arguments for option \'--kallisto_quant_results_file\': \'$VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to --kallisto_quant_results_file. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
--kallisto_quant_results_file=*)
[ -n "$VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE" ] && ViashError Bad arguments for option \'--kallisto_quant_results_file=*\': \'$VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE=$(ViashRemoveFlags "$1")
shift 1
;;
---engine)
VIASH_ENGINE_ID="$2"
shift 2
;;
---engine=*)
VIASH_ENGINE_ID="$(ViashRemoveFlags "$1")"
shift 1
;;
---cpus)
[ -n "$VIASH_META_CPUS" ] && ViashError Bad arguments for option \'---cpus\': \'$VIASH_META_CPUS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_META_CPUS="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to ---cpus. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
---cpus=*)
[ -n "$VIASH_META_CPUS" ] && ViashError Bad arguments for option \'---cpus=*\': \'$VIASH_META_CPUS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_META_CPUS=$(ViashRemoveFlags "$1")
shift 1
;;
---memory)
[ -n "$VIASH_META_MEMORY" ] && ViashError Bad arguments for option \'---memory\': \'$VIASH_META_MEMORY\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_META_MEMORY="$2"
[ $# -lt 2 ] && ViashError Not enough arguments passed to ---memory. Use "--help" to get more information on the parameters. && exit 1
shift 2
;;
---memory=*)
[ -n "$VIASH_META_MEMORY" ] && ViashError Bad arguments for option \'---memory=*\': \'$VIASH_META_MEMORY\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
VIASH_META_MEMORY=$(ViashRemoveFlags "$1")
shift 1
;;
*) # positional arg or unknown option
# since the positional args will be eval'd, can we always quote, instead of using ViashQuote
VIASH_POSITIONAL_ARGS="$VIASH_POSITIONAL_ARGS '$1'"
[[ $1 == -* ]] && ViashWarning $1 looks like a parameter but is not a defined parameter and will instead be treated as a positional argument. Use "--help" to get more information on the parameters.
shift # past argument
;;
esac
done
# parse positional parameters
eval set -- $VIASH_POSITIONAL_ARGS
if [ "$VIASH_ENGINE_ID" == "native" ] ; then
VIASH_ENGINE_TYPE='native'
else
ViashError "Engine '$VIASH_ENGINE_ID' is not recognized. Options are: native."
exit 1
fi
# setting computational defaults
# helper function for parsing memory strings
function ViashMemoryAsBytes {
local memory=`echo "$1" | tr '[:upper:]' '[:lower:]' | tr -d '[:space:]'`
local memory_regex='^([0-9]+)([kmgtp]i?b?|b)$'
if [[ $memory =~ $memory_regex ]]; then
local number=${memory/[^0-9]*/}
local symbol=${memory/*[0-9]/}
case $symbol in
b) memory_b=$number ;;
kb|k) memory_b=$(( $number * 1000 )) ;;
mb|m) memory_b=$(( $number * 1000 * 1000 )) ;;
gb|g) memory_b=$(( $number * 1000 * 1000 * 1000 )) ;;
tb|t) memory_b=$(( $number * 1000 * 1000 * 1000 * 1000 )) ;;
pb|p) memory_b=$(( $number * 1000 * 1000 * 1000 * 1000 * 1000 )) ;;
kib|ki) memory_b=$(( $number * 1024 )) ;;
mib|mi) memory_b=$(( $number * 1024 * 1024 )) ;;
gib|gi) memory_b=$(( $number * 1024 * 1024 * 1024 )) ;;
tib|ti) memory_b=$(( $number * 1024 * 1024 * 1024 * 1024 )) ;;
pib|pi) memory_b=$(( $number * 1024 * 1024 * 1024 * 1024 * 1024 )) ;;
esac
echo "$memory_b"
fi
}
# compute memory in different units
if [ ! -z ${VIASH_META_MEMORY+x} ]; then
VIASH_META_MEMORY_B=`ViashMemoryAsBytes $VIASH_META_MEMORY`
# do not define other variables if memory_b is an empty string
if [ ! -z "$VIASH_META_MEMORY_B" ]; then
VIASH_META_MEMORY_KB=$(( ($VIASH_META_MEMORY_B+999) / 1000 ))
VIASH_META_MEMORY_MB=$(( ($VIASH_META_MEMORY_KB+999) / 1000 ))
VIASH_META_MEMORY_GB=$(( ($VIASH_META_MEMORY_MB+999) / 1000 ))
VIASH_META_MEMORY_TB=$(( ($VIASH_META_MEMORY_GB+999) / 1000 ))
VIASH_META_MEMORY_PB=$(( ($VIASH_META_MEMORY_TB+999) / 1000 ))
VIASH_META_MEMORY_KIB=$(( ($VIASH_META_MEMORY_B+1023) / 1024 ))
VIASH_META_MEMORY_MIB=$(( ($VIASH_META_MEMORY_KIB+1023) / 1024 ))
VIASH_META_MEMORY_GIB=$(( ($VIASH_META_MEMORY_MIB+1023) / 1024 ))
VIASH_META_MEMORY_TIB=$(( ($VIASH_META_MEMORY_GIB+1023) / 1024 ))
VIASH_META_MEMORY_PIB=$(( ($VIASH_META_MEMORY_TIB+1023) / 1024 ))
else
# unset memory if string is empty
unset $VIASH_META_MEMORY_B
fi
fi
# unset nproc if string is empty
if [ -z "$VIASH_META_CPUS" ]; then
unset $VIASH_META_CPUS
fi
# check whether required parameters exist
if [ -z ${VIASH_PAR_ID+x} ]; then
ViashError '--id' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_PAR_FASTQ_1+x} ]; then
ViashError '--fastq_1' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_META_NAME+x} ]; then
ViashError 'name' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_META_FUNCTIONALITY_NAME+x} ]; then
ViashError 'functionality_name' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_META_RESOURCES_DIR+x} ]; then
ViashError 'resources_dir' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_META_EXECUTABLE+x} ]; then
ViashError 'executable' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_META_CONFIG+x} ]; then
ViashError 'config' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
if [ -z ${VIASH_META_TEMP_DIR+x} ]; then
ViashError 'temp_dir' is a required argument. Use "--help" to get more information on the parameters.
exit 1
fi
# filling in defaults
if [ -z ${VIASH_PAR_PSEUDO_ALIGNER+x} ]; then
VIASH_PAR_PSEUDO_ALIGNER="false"
fi
if [ -z ${VIASH_PAR_LIB_TYPE+x} ]; then
VIASH_PAR_LIB_TYPE=""
fi
if [ -z ${VIASH_PAR_PSEUDO_MULTIQC+x} ]; then
VIASH_PAR_PSEUDO_MULTIQC="\$id.quant.log"
fi
if [ -z ${VIASH_PAR_QUANT_OUT_DIR+x} ]; then
VIASH_PAR_QUANT_OUT_DIR="\$id.salmon_quant"
fi
if [ -z ${VIASH_PAR_SALMON_QUANT_RESULTS_FILE+x} ]; then
VIASH_PAR_SALMON_QUANT_RESULTS_FILE="\$id.quant.sf"
fi
if [ -z ${VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE+x} ]; then
VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE="\$id.abundance.tsv"
fi
# check whether required files exist
if [ ! -z "$VIASH_PAR_FASTQ_1" ] && [ ! -e "$VIASH_PAR_FASTQ_1" ]; then
ViashError "Input file '$VIASH_PAR_FASTQ_1' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_FASTQ_2" ] && [ ! -e "$VIASH_PAR_FASTQ_2" ]; then
ViashError "Input file '$VIASH_PAR_FASTQ_2' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_GTF" ] && [ ! -e "$VIASH_PAR_GTF" ]; then
ViashError "Input file '$VIASH_PAR_GTF' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_TRANSCRIPT_FASTA" ] && [ ! -e "$VIASH_PAR_TRANSCRIPT_FASTA" ]; then
ViashError "Input file '$VIASH_PAR_TRANSCRIPT_FASTA' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_SALMON_INDEX" ] && [ ! -e "$VIASH_PAR_SALMON_INDEX" ]; then
ViashError "Input file '$VIASH_PAR_SALMON_INDEX' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_KALLISTO_INDEX" ] && [ ! -e "$VIASH_PAR_KALLISTO_INDEX" ]; then
ViashError "Input file '$VIASH_PAR_KALLISTO_INDEX' does not exist."
exit 1
fi
# check whether parameters values are of the right type
if [[ -n "$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH" ]]; then
if ! [[ "$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH" =~ ^[-+]?[0-9]+$ ]]; then
ViashError '--kallisto_quant_fragment_length' has to be an integer. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH_SD" ]]; then
if ! [[ "$VIASH_PAR_KALLISTO_QUANT_FRAGMENT_LENGTH_SD" =~ ^[-+]?[0-9]+$ ]]; then
ViashError '--kallisto_quant_fragment_length_sd' has to be an integer. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_CPUS" ]]; then
if ! [[ "$VIASH_META_CPUS" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'cpus' has to be an integer. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_B" ]]; then
if ! [[ "$VIASH_META_MEMORY_B" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_b' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_KB" ]]; then
if ! [[ "$VIASH_META_MEMORY_KB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_kb' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_MB" ]]; then
if ! [[ "$VIASH_META_MEMORY_MB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_mb' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_GB" ]]; then
if ! [[ "$VIASH_META_MEMORY_GB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_gb' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_TB" ]]; then
if ! [[ "$VIASH_META_MEMORY_TB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_tb' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_PB" ]]; then
if ! [[ "$VIASH_META_MEMORY_PB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_pb' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_KIB" ]]; then
if ! [[ "$VIASH_META_MEMORY_KIB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_kib' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_MIB" ]]; then
if ! [[ "$VIASH_META_MEMORY_MIB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_mib' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_GIB" ]]; then
if ! [[ "$VIASH_META_MEMORY_GIB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_gib' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_TIB" ]]; then
if ! [[ "$VIASH_META_MEMORY_TIB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_tib' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
if [[ -n "$VIASH_META_MEMORY_PIB" ]]; then
if ! [[ "$VIASH_META_MEMORY_PIB" =~ ^[-+]?[0-9]+$ ]]; then
ViashError 'memory_pib' has to be a long. Use "--help" to get more information on the parameters.
exit 1
fi
fi
# check whether value is belongs to a set of choices
if [ ! -z "$VIASH_PAR_STRANDEDNESS" ]; then
VIASH_PAR_STRANDEDNESS_CHOICES=("forward;reverse;unstranded")
IFS=';'
set -f
if ! [[ ";${VIASH_PAR_STRANDEDNESS_CHOICES[*]};" =~ ";$VIASH_PAR_STRANDEDNESS;" ]]; then
ViashError '--strandedness' specified value of \'$VIASH_PAR_STRANDEDNESS\' is not in the list of allowed values. Use "--help" to get more information on the parameters.
exit 1
fi
set +f
unset IFS
fi
if [ ! -z "$VIASH_PAR_PSEUDO_ALIGNER" ]; then
VIASH_PAR_PSEUDO_ALIGNER_CHOICES=("salmon;kallisto")
IFS=';'
set -f
if ! [[ ";${VIASH_PAR_PSEUDO_ALIGNER_CHOICES[*]};" =~ ";$VIASH_PAR_PSEUDO_ALIGNER;" ]]; then
ViashError '--pseudo_aligner' specified value of \'$VIASH_PAR_PSEUDO_ALIGNER\' is not in the list of allowed values. Use "--help" to get more information on the parameters.
exit 1
fi
set +f
unset IFS
fi
# create parent directories of output files, if so desired
if [ ! -z "$VIASH_PAR_PSEUDO_MULTIQC" ] && [ ! -d "$(dirname "$VIASH_PAR_PSEUDO_MULTIQC")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_PSEUDO_MULTIQC")"
fi
if [ ! -z "$VIASH_PAR_QUANT_OUT_DIR" ] && [ ! -d "$(dirname "$VIASH_PAR_QUANT_OUT_DIR")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_QUANT_OUT_DIR")"
fi
if [ ! -z "$VIASH_PAR_SALMON_QUANT_RESULTS_FILE" ] && [ ! -d "$(dirname "$VIASH_PAR_SALMON_QUANT_RESULTS_FILE")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_SALMON_QUANT_RESULTS_FILE")"
fi
if [ ! -z "$VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE" ] && [ ! -d "$(dirname "$VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE")" ]; then
mkdir -p "$(dirname "$VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE")"
fi
if [ "$VIASH_ENGINE_ID" == "native" ] ; then
if [ "$VIASH_MODE" == "run" ]; then
VIASH_CMD="bash"
else
ViashError "Engine '$VIASH_ENGINE_ID' does not support mode '$VIASH_MODE'."
exit 1
fi
fi
# set dependency paths
VIASH_DEP_KALLISTO_KALLISTO_QUANT="$VIASH_META_RESOURCES_DIR/../../../nextflow/kallisto/kallisto_quant/main.nf"
VIASH_DEP_SALMON_SALMON_QUANT="$VIASH_TARGET_DIR/dependencies/vsh/vsh/biobox/v0.1/nextflow/salmon/salmon_quant/main.nf"
ViashDebug "Running command: $(echo $VIASH_CMD)"
cat << VIASHEOF | eval $VIASH_CMD
set -e
tempscript=\$(mktemp "$VIASH_META_TEMP_DIR/viash-run-pseudo_alignment_and_quant-XXXXXX").nf
function clean_up {
rm "\$tempscript"
}
function interrupt {
echo -e "\nCTRL-C Pressed..."
exit 1
}
trap clean_up EXIT
trap interrupt INT SIGINT
cat > "\$tempscript" << 'VIASHMAIN'
//// VIASH START
// The following code has been auto-generated by Viash.
//// VIASH END
workflow run_wf {
take:
input_ch
main:
output_ch = input_ch
| map { id, state ->
def input = state.fastq_2 ? [ state.fastq_1, state.fastq_2 ] : [ state.fastq_1 ]
def paired = input.size() == 2
[ id, state + [ paired: paired, input: input ] ]
}
// Infer lib-type for salmon quant
| map { id, state ->
def lib_type = (state.paired) ?
(
(state.strandedness == "forward") ?
"ISF" :
(
(state.strandedness == "reverse") ? "ISR" : "IU"
)
)
: (
(state.strandedness == "forward") ?
"SF" :
(
(state.strandedness == "reverse") ? "SR" : "U"
)
)
[ id, state + [lib_type: lib_type] ]
}
// Count reads from BAM alignments using Salmon
| salmon_quant.run (
runIf: { id, state -> state.pseudo_aligner == 'salmon' },
fromState: { id, state ->
def unmated_reads = !state.paired ? state.fastq_1 : null
def mates1 = state.paired ? state.fastq_1 : null
def mates2 = state.paired ? state.fastq_2 : null
[ unmated_reads: unmated_reads,
mates1: mates1,
mates2: mates2,
gene_map: state.gtf,
index: state.salmon_index,
lib_type: state.lib_type ]
},
toState: [
"quant_results_dir": "output",
"salmon_quant_results_file": "quant_results"
]
)
| kallisto_quant.run (
runIf: { id, state -> state.pseudo_aligner == 'kallisto'},
fromState: [
"input": "input",
"paired": "paired",
"gtf": "gtf",
"index": "kallisto_index",
"fragment_length": "kallisto_quant_fragment_length",
"fragment_length_sd": "kallisto_quant_fragment_length_sd"
],
toState: [
"quant_out_dir": "output",
"kallisto_quant_results_file": "quant_results_file",
"pseudo_multiqc": "log"
]
)
| map { id, state ->
def mod_state = state.findAll { key, value -> value instanceof java.nio.file.Path && value.exists() }
[ id, mod_state ]
}
| setState (
[ "pseudo_multiqc": "quant_results",
"quant_out_dir": "quant_out_dir",
"salmon_quant_results_file": "salmon_quant_results_file",
"kallisto_quant_results_file": "kallisto_quant_results_file" ]
)
emit:
output_ch
}
VIASHMAIN
nextflow run . -main-script "\$tempscript" &
wait "\$!"
VIASHEOF
# check whether required files exist
if [ ! -z "$VIASH_PAR_PSEUDO_MULTIQC" ] && [ ! -e "$VIASH_PAR_PSEUDO_MULTIQC" ]; then
ViashError "Output file '$VIASH_PAR_PSEUDO_MULTIQC' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_QUANT_OUT_DIR" ] && [ ! -e "$VIASH_PAR_QUANT_OUT_DIR" ]; then
ViashError "Output file '$VIASH_PAR_QUANT_OUT_DIR' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_SALMON_QUANT_RESULTS_FILE" ] && [ ! -e "$VIASH_PAR_SALMON_QUANT_RESULTS_FILE" ]; then
ViashError "Output file '$VIASH_PAR_SALMON_QUANT_RESULTS_FILE' does not exist."
exit 1
fi
if [ ! -z "$VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE" ] && [ ! -e "$VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE" ]; then
ViashError "Output file '$VIASH_PAR_KALLISTO_QUANT_RESULTS_FILE' does not exist."
exit 1
fi
exit 0

1626
target/executable/workflows/quality_control/.config.vsh.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

4315
target/executable/workflows/quality_control/quality_control Executable file
View File

File diff suppressed because it is too large Load Diff

1984
target/executable/workflows/rnaseq/.config.vsh.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

5080
target/executable/workflows/rnaseq/rnaseq Executable file
View File

File diff suppressed because it is too large Load Diff