Add subworkflows for ensemblvep and snpeff (#1124)

* greatly simplify syntax

* feat: add subworkflows to annotate (+ bgzip/tabix index) with ensemblvep and snpeff

* feat: get versions from all tools

* add commented infor for new annotation modules
This commit is contained in:
Maxime U. Garcia 2021-12-07 17:12:35 +01:00 committed by GitHub
parent 7389963d5c
commit 31d4099f38
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
11 changed files with 196 additions and 11 deletions

View file

@ -0,0 +1,26 @@
//
// Run VEP to annotate VCF files
//
include { ENSEMBLVEP } from '../../../modules/ensemblvep/main'
include { TABIX_BGZIPTABIX as ANNOTATION_BGZIPTABIX } from '../../../modules/tabix/bgziptabix/main'
workflow ANNOTATION_ENSEMBLVEP {
take:
vcf // channel: [ val(meta), vcf ]
vep_genome // value: which genome
vep_species // value: which species
vep_cache_version // value: which cache version
vep_cache // path: path_to_vep_cache (optionnal)
main:
ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache)
ANNOTATION_BGZIPTABIX(ENSEMBLVEP.out.vcf)
ch_versions = ENSEMBLVEP.out.versions.first().mix(ANNOTATION_BGZIPTABIX.out.versions.first())
emit:
vcf_tbi = ANNOTATION_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
reports = ENSEMBLVEP.out.report // path: *.html
versions = ch_versions // path: versions.yml
}

View file

@ -0,0 +1,29 @@
name: annotation_ensemblvep
description: |
Perform annotation with ensemblvep and bgzip + tabix index the resulting VCF file
keywords:
- ensemblvep
modules:
- ensemblvep
- tabix/bgziptabix
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test' ]
- input:
type: vcf
description: list containing one vcf file
pattern: "[ *.{vcf,vcf.gz} ]"
output:
- versions:
type: file
description: File containing software versions
pattern: 'versions.yml'
- vcf_tbi:
type: file
description: Compressed vcf file + tabix index
pattern: "[ *{.vcf.gz,vcf.gz.tbi} ]"
authors:
- '@maxulysse'

View file

@ -0,0 +1,23 @@
//
// Run SNPEFF to annotate VCF files
//
include { SNPEFF } from '../../../modules/snpeff/main'
include { TABIX_BGZIPTABIX as ANNOTATION_BGZIPTABIX } from '../../../modules/tabix/bgziptabix/main'
workflow ANNOTATION_SNPEFF {
take:
vcf // channel: [ val(meta), vcf ]
snpeff_db // value: version of db to use
snpeff_cache // path: path_to_snpeff_cache (optionnal)
main:
SNPEFF(vcf, snpeff_db, snpeff_cache)
ANNOTATION_BGZIPTABIX(SNPEFF.out.vcf)
ch_versions = SNPEFF.out.versions.first().mix(ANNOTATION_BGZIPTABIX.out.versions.first())
emit:
vcf_tbi = ANNOTATION_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
reports = SNPEFF.out.report // path: *.html
versions = ch_versions // path: versions.yml
}

View file

@ -0,0 +1,29 @@
name: annotation_snpeff
description: |
Perform annotation with snpeff and bgzip + tabix index the resulting VCF file
keywords:
- snpeff
modules:
- snpeff
- tabix/bgziptabix
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test' ]
- input:
type: vcf
description: list containing one vcf file
pattern: "[ *.{vcf,vcf.gz} ]"
output:
- versions:
type: file
description: File containing software versions
pattern: 'versions.yml'
- vcf_tbi:
type: file
description: Compressed vcf file + tabix index
pattern: "[ *{.vcf.gz,vcf.gz.tbi} ]"
authors:
- '@maxulysse'

View file

@ -1451,6 +1451,19 @@ yara/mapper:
- modules/yara/mapper/** - modules/yara/mapper/**
- tests/modules/yara/mapper/** - tests/modules/yara/mapper/**
# subworkflows/align_bowtie2:
# - subworkflows/nf-core/align_bowtie2/**
# - tests/subworkflows/nf-core/align_bowtie2/**
# - *subworkflows_bam_sort_samtools
# subworkflows/annotation_ensemblvep: &subworkflows_annotation_ensemblvep
# - subworkflows/nf-core/annotation_ensemblvep/**
# - tests/subworkflows/nf-core/annotation_ensemblvep/**
# subworkflows/annotation_snpeff: &subworkflows_annotation_snpeff
# - subworkflows/nf-core/annotation_snpeff/**
# - tests/subworkflows/nf-core/annotation_snpeff/**
# subworkflows/bam_stats_samtools: &subworkflows_bam_stats_samtools # subworkflows/bam_stats_samtools: &subworkflows_bam_stats_samtools
# - subworkflows/nf-core/bam_stats_samtools/** # - subworkflows/nf-core/bam_stats_samtools/**
# - tests/subworkflows/nf-core/bam_stats_samtools/** # - tests/subworkflows/nf-core/bam_stats_samtools/**
@ -1462,17 +1475,6 @@ yara/mapper:
# - *samtools_index # - *samtools_index
# - *subworkflows_bam_stats_samtools # - *subworkflows_bam_stats_samtools
# subworkflows/align_bowtie2:
# - subworkflows/nf-core/align_bowtie2/**
# - tests/subworkflows/nf-core/align_bowtie2/**
# - *subworkflows_bam_sort_samtools
# subworkflows/sra_fastq:
# - subworkflows/nf-core/sra_fastq/**
# - tests/subworkflows/nf-core/sra_fastq/**
# - *sratools_fasterqdump
# - *sratools_prefetch
# subworkflows/gatk_create_som_pon: # subworkflows/gatk_create_som_pon:
# - subworkflows/nf-core/gatk_create_som_pon/** # - subworkflows/nf-core/gatk_create_som_pon/**
# - tests/subworkflows/nf-core/gatk_create_som_pon/** # - tests/subworkflows/nf-core/gatk_create_som_pon/**
@ -1495,3 +1497,9 @@ yara/mapper:
# - *gatk4_getpileupsummaries # - *gatk4_getpileupsummaries
# - *gatk4_calculatecontamination # - *gatk4_calculatecontamination
# - *gatk4_filtermutectcalls # - *gatk4_filtermutectcalls
# subworkflows/sra_fastq:
# - subworkflows/nf-core/sra_fastq/**
# - tests/subworkflows/nf-core/sra_fastq/**
# - *sratools_fasterqdump
# - *sratools_prefetch

View file

@ -0,0 +1,14 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { ANNOTATION_ENSEMBLVEP } from '../../../../subworkflows/nf-core/annotation_ensemblvep/main'
workflow annotation_ensemblvep {
input = [
[ id:'test' ], // meta map
file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
]
ANNOTATION_ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [] )
}

View file

@ -0,0 +1,14 @@
process {
publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
withName: ENSEMBLVEP {
container = 'nfcore/vep:104.3.WBcel235'
publishDir = [ enabled: false ]
}
withName: ANNOTATION_BGZIPTABIX {
ext.prefix = { "${meta.id}_VEP.ann.vcf" }
}
}

View file

@ -0,0 +1,7 @@
- name: ensemblvep annotation_ensemblvep
command: nextflow run ./tests/subworkflows/nf-core/annotation_ensemblvep -entry annotation_ensemblvep -c ./tests/config/nextflow.config -c ./tests/subworkflows/nf-core/annotation_ensemblvep/nextflow.config
tags:
- annotation_ensemblvep
files:
- path: output/annotation/test_VEP.ann.vcf.gz
- path: output/annotation/test_VEP.ann.vcf.gz.tbi

View file

@ -0,0 +1,14 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { ANNOTATION_SNPEFF } from '../../../../subworkflows/nf-core/annotation_snpeff/main'
workflow annotation_snpeff {
input = [
[ id:'test' ], // meta map
file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
]
ANNOTATION_SNPEFF ( input, "WBcel235.99", [] )
}

View file

@ -0,0 +1,14 @@
process {
publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
withName: SNPEFF {
container = 'nfcore/snpeff:5.0.WBcel235'
publishDir = [ enabled: false ]
}
withName: ANNOTATION_BGZIPTABIX {
ext.prefix = { "${meta.id}_snpEff.ann.vcf" }
}
}

View file

@ -0,0 +1,7 @@
- name: snpeff annotation_snpeff
command: nextflow run ./tests/subworkflows/nf-core/annotation_snpeff -entry annotation_snpeff -c ./tests/config/nextflow.config -c ./tests/subworkflows/nf-core/annotation_snpeff/nextflow.config
tags:
- annotation_snpeff
files:
- path: output/annotation/test_snpEff.ann.vcf.gz
- path: output/annotation/test_snpEff.ann.vcf.gz.tbi