Files
rnaseq/target/executable/workflows/post_processing/.config.vsh.yaml
CI 2d86d22f22 Build branch main with version main (a04f9ba)
Build pipeline: viash-hub.rnaseq.main-xf2ql

Source commit: a04f9bab8a

Source message: avoid generating STAR index if alignment is skipped
2024-11-13 12:53:08 +00:00

528 lines
13 KiB
YAML

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:
- "$id.genome.bam"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--genome_bam_index"
info: null
default:
- "$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:
- "$id.genome.idxstats"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--markduplicates_metrics"
info: null
default:
- "$id.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: "main"
- name: "samtools/samtools_index"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "main"
- name: "samtools/samtools_stats"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "main"
- name: "samtools/samtools_flagstat"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "main"
- name: "samtools/samtools_idxstats"
repository:
type: "vsh"
repo: "vsh/biobox"
tag: "main"
- 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: "main"
- type: "vsh"
name: "craftbox"
repo: "craftbox"
tag: "v0.1.0"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "native"
id: "native"
build_info:
config: "src/workflows/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: "a04f9bab8aec1c4f5e8ade4d5b68c2d4c92a7814"
git_remote: "https://x-access-token:ghs_U4pAQwhSWAqkeDDEK1YyMxMtkXglzF3wJkYc@github.com/viash-hub/rnaseq"
dependencies:
- "target/nextflow/picard_markduplicates"
- "target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_sort"
- "target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_index"
- "target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_stats"
- "target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_flagstat"
- "target/dependencies/vsh/vsh/biobox/main/nextflow/samtools/samtools_idxstats"
- "target/nextflow/stringtie"
- "target/nextflow/bedtools_genomecov"
- "target/nextflow/ucsc/bedclip"
- "target/nextflow/ucsc/bedgraphtobigwig"
package_config:
name: "rnaseq"
version: "main"
info:
test_resources:
- path: "gs://viash-hub-test-data/rnaseq/v1"
dest: "testData"
repositories:
- type: "vsh"
name: "biobox"
repo: "vsh/biobox"
tag: "main"
- type: "vsh"
name: "craftbox"
repo: "craftbox"
tag: "v0.1.0"
viash_version: "0.9.0"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].directives.tag\
\ := '$id'\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'main'"
organization: "vsh"