From 17dbff52f4ef27617abb3e03b503bc5423259fb4 Mon Sep 17 00:00:00 2001 From: Kevin Menden Date: Wed, 17 Mar 2021 09:42:35 +0100 Subject: [PATCH] added gatk4 variantfiltration (#265) * added gatk4 variantfiltration * replace merge with filter * Update software/gatk4/variantfiltration/main.nf Co-authored-by: Harshil Patel * updated input Co-authored-by: Harshil Patel --- software/gatk4/variantfiltration/functions.nf | 59 ++++++++++++++++ software/gatk4/variantfiltration/main.nf | 42 ++++++++++++ software/gatk4/variantfiltration/meta.yml | 68 +++++++++++++++++++ tests/config/pytest_software.yml | 4 ++ .../software/gatk4/variantfiltration/main.nf | 18 +++++ .../software/gatk4/variantfiltration/test.yml | 8 +++ 6 files changed, 199 insertions(+) create mode 100644 software/gatk4/variantfiltration/functions.nf create mode 100644 software/gatk4/variantfiltration/main.nf create mode 100644 software/gatk4/variantfiltration/meta.yml create mode 100644 tests/software/gatk4/variantfiltration/main.nf create mode 100644 tests/software/gatk4/variantfiltration/test.yml diff --git a/software/gatk4/variantfiltration/functions.nf b/software/gatk4/variantfiltration/functions.nf new file mode 100644 index 00000000..d25eea86 --- /dev/null +++ b/software/gatk4/variantfiltration/functions.nf @@ -0,0 +1,59 @@ +/* + * ----------------------------------------------------- + * Utility functions used in nf-core DSL2 module files + * ----------------------------------------------------- + */ + +/* + * Extract name of software tool from process name using $task.process + */ +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +/* + * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules + */ +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.publish_by_id = args.publish_by_id ?: false + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +/* + * Tidy up and join elements of a list to return a path string + */ +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +/* + * Function to save/publish module results + */ +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_id) { + path_list.add(args.publish_id) + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/software/gatk4/variantfiltration/main.nf b/software/gatk4/variantfiltration/main.nf new file mode 100644 index 00000000..e11e6038 --- /dev/null +++ b/software/gatk4/variantfiltration/main.nf @@ -0,0 +1,42 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +def options = initOptions(params.options) + +process GATK4_VARIANTFILTRATION { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) } + + conda (params.enable_conda ? "bioconda::gatk4=4.2.0.0" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/gatk4:4.2.0.0--0" + } else { + container "quay.io/biocontainers/gatk4:4.2.0.0--0" + } + + input: + tuple val(meta), path(vcf) + tuple path(fasta), path(fai), path(dict) + + output: + tuple val(meta), path("*filtered.vcf"), emit: vcf + path "*.version.txt" , emit: version + + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + gatk VariantFiltration \\ + -R $fasta \\ + -V $vcf \\ + -O ${prefix}.filtered.vcf \\ + $options.args + + gatk --version | grep Picard | sed "s/Picard Version: //g" > ${software}.version.txt + """ +} diff --git a/software/gatk4/variantfiltration/meta.yml b/software/gatk4/variantfiltration/meta.yml new file mode 100644 index 00000000..c7065efc --- /dev/null +++ b/software/gatk4/variantfiltration/meta.yml @@ -0,0 +1,68 @@ +name: gatk4_variantfiltration +description: Filter variants +keywords: + - vcf + - filter +tools: + - gatk4: + description: | + Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools + with a primary focus on variant discovery and genotyping. Its powerful processing engine + and high-performance computing features make it capable of taking on projects of any size. + homepage: https://gatk.broadinstitute.org/hc/en-us + documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s + doi: 10.1158/1538-7445.AM2017-3590 +params: + - outdir: + type: string + description: | + The pipeline's output directory. By default, the module will + output files into `$params.outdir/` + - publish_dir_mode: + type: string + description: | + Value for the Nextflow `publishDir` mode parameter. + Available: symlink, rellink, link, copy, copyNoFollow, move. + - enable_conda: + type: boolean + description: | + Run the module with Conda using the software specified + via the `conda` directive + - singularity_pull_docker_container: + type: boolean + description: | + Instead of directly downloading Singularity images for use with Singularity, + force the workflow to pull and convert Docker containers instead. +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test'] + - vcf: + type: list + description: Input VCF file + pattern: "*.{vcf}" + - fasta: + type: file + description: Fasta file of reference genome + pattern: "*.fasta" + - fai: + type: file + description: Index of fasta file + pattern: "*.fasta.fai" + - dict: + type: file + description: Sequence dictionary of fastea file + pattern: "*.dict" +output: + - vcf: + type: file + description: filtered VCF file + pattern: "*.filtered.{vcf}" + - version: + type: file + description: File containing software version + pattern: "*.version.txt" +authors: + - "@kevinmenden" diff --git a/tests/config/pytest_software.yml b/tests/config/pytest_software.yml index 3e06b77a..eece533c 100644 --- a/tests/config/pytest_software.yml +++ b/tests/config/pytest_software.yml @@ -320,3 +320,7 @@ untar: ucsc_bedgraphtobigwig: - software/ucsc/bedgraphtobigwig/** - tests/software/ucsc/bedgraphtobigwig/** + +gatk4_variantfiltration: + - software/gatk4/variantfiltration/** + - tests/software/gatk4/variantfiltration/** diff --git a/tests/software/gatk4/variantfiltration/main.nf b/tests/software/gatk4/variantfiltration/main.nf new file mode 100644 index 00000000..8501eef6 --- /dev/null +++ b/tests/software/gatk4/variantfiltration/main.nf @@ -0,0 +1,18 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +test_options = ['args': '--filter-name "test_filter" --filter-expression "MQ0 > 0"'] +include { GATK4_VARIANTFILTRATION } from '../../../../software/gatk4/variantfiltration/main.nf' addParams( options: test_options ) + +workflow test_gatk4_variantfiltration { + def input = [] + input = [ [ id:'test' ], // meta map + [ file("${launchDir}/tests/data/genomics/sarscov2/vcf/test.vcf", checkIfExists: true)] ] + + fasta = [ file("tests/data/genomics/sarscov2/fasta/test_genome.fasta", checkIfExists: true), + file("tests/data/genomics/sarscov2/fasta/test_genome.fasta.fai", checkIfExists: true), + file("tests/data/genomics/sarscov2/fasta/test_genome.dict", checkIfExists: true)] + + GATK4_VARIANTFILTRATION ( input, fasta ) +} diff --git a/tests/software/gatk4/variantfiltration/test.yml b/tests/software/gatk4/variantfiltration/test.yml new file mode 100644 index 00000000..01031519 --- /dev/null +++ b/tests/software/gatk4/variantfiltration/test.yml @@ -0,0 +1,8 @@ +- name: Run tests for gatk4/variantfiltration - test_gatk4_variantfiltration + command: nextflow run tests/software/gatk4/variantfiltration -entry test_gatk4_variantfiltration + -c tests/config/nextflow.config + tags: + - gatk4 + - gatk4_variantfiltration + files: + - path: output/gatk4/test.filtered.vcf