From 3fee38ee2dcce3c6b9ab10d331e194ef492a57e8 Mon Sep 17 00:00:00 2001 From: kevinmenden Date: Mon, 22 Feb 2021 15:21:39 +0100 Subject: [PATCH] added gatk4 revertsam --- .github/filters.yml | 4 ++ software/gatk4/revertsam/functions.nf | 59 +++++++++++++++++++++++++ software/gatk4/revertsam/main.nf | 39 ++++++++++++++++ software/gatk4/revertsam/meta.yml | 17 +++---- tests/software/gatk4/revertsam/main.nf | 12 ++--- tests/software/gatk4/revertsam/test.yml | 10 ++--- 6 files changed, 116 insertions(+), 25 deletions(-) create mode 100644 software/gatk4/revertsam/functions.nf create mode 100644 software/gatk4/revertsam/main.nf diff --git a/.github/filters.yml b/.github/filters.yml index 32ce12a7..d8d63681 100644 --- a/.github/filters.yml +++ b/.github/filters.yml @@ -136,6 +136,10 @@ gatk4_bedtointervallist: - software/gatk4/bedtointervallist/** - tests/software/gatk4/bedtointervallist/** +gatk4_revertsam: + - software/gatk4/revertsam/** + - tests/software/gatk4/revertsam/** + gatk4_samtofastq: - software/gatk4/samtofastq/** - tests/software/gatk4/samtofastq/** diff --git a/software/gatk4/revertsam/functions.nf b/software/gatk4/revertsam/functions.nf new file mode 100644 index 00000000..d25eea86 --- /dev/null +++ b/software/gatk4/revertsam/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)}/$args.filename" + } + } +} diff --git a/software/gatk4/revertsam/main.nf b/software/gatk4/revertsam/main.nf new file mode 100644 index 00000000..b303623b --- /dev/null +++ b/software/gatk4/revertsam/main.nf @@ -0,0 +1,39 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +def options = initOptions(params.options) + +process GATK4_REVERTSAM { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) } + + conda (params.enable_conda ? 'bioconda::gatk4:4.1.9.0' : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container 'https://depot.galaxyproject.org/singularity/gatk4:4.1.9.0--py39_0' + } else { + container 'quay.io/biocontainers/gatk4:4.1.9.0--py39_0' + } + + input: + tuple val(meta), path(bam) + + output: + tuple val(meta), path('*.bam') , emit: bam + path '*.version.txt' , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}.${options.suffix}" : "${meta.id}" + """ + gatk RevertSam \\ + I=$bam \\ + O=${prefix}.reverted.bam \\ + $options.args + + gatk --version | grep Picard | sed "s/Picard Version: //g" > ${software}.version.txt + """ +} diff --git a/software/gatk4/revertsam/meta.yml b/software/gatk4/revertsam/meta.yml index 6d39d330..e7d176c8 100644 --- a/software/gatk4/revertsam/meta.yml +++ b/software/gatk4/revertsam/meta.yml @@ -40,21 +40,14 @@ input: Groovy Map containing sample information e.g. [ id:'test'] - bam: - type: list - description: Two or more VCF files - pattern: "*.{vcf,vcf.gz}" - - ref_dict: type: file - description: Optional Sequence Dictionary as input - pattern: "*.dict" - - use_ref_dict: - type: boolean - description: Specify whether or not to use a given reference dictionary + description: The input bam/sam file + pattern: "*.{bam,sam}" output: - - vcf: + - bam: type: file - description: merged vcf file - pattern: "*.vcf.gz" + description: The reverted bam/sam file + pattern: "*.reverted.bam" - version: type: file description: File containing software version diff --git a/tests/software/gatk4/revertsam/main.nf b/tests/software/gatk4/revertsam/main.nf index 8d37f7ef..077b7d8d 100644 --- a/tests/software/gatk4/revertsam/main.nf +++ b/tests/software/gatk4/revertsam/main.nf @@ -2,17 +2,13 @@ nextflow.enable.dsl = 2 -include { GATK4_MERGEVCFS } from '../../../../software/gatk4/mergevcfs/main.nf' addParams( options: [:] ) +include { GATK4_REVERTSAM } from '../../../../software/gatk4/revertsam/main.nf' addParams( options: [:] ) -workflow test_gatk4_mergevcfs { +workflow test_gatk4_revertsam { def input = [] input = [ [ id:'test' ], // meta map - [ file("${launchDir}/tests/data/vcf/test.vcf", checkIfExists: true), - file("${launchDir}/tests/data/vcf/test2.vcf.gz", checkIfExists: true), - file("${launchDir}/tests/data/vcf/test3.vcf.gz", checkIfExists: true) ] ] + file("${launchDir}/tests/data/bam/sarscov2_aln.bam", checkIfExists: true) ] - ref_dict = file("tests/data/fasta/test.consensus.for_vcf.dict", checkIfExists: true) - - GATK4_MERGEVCFS ( input, ref_dict, false ) + GATK4_REVERTSAM( input ) } diff --git a/tests/software/gatk4/revertsam/test.yml b/tests/software/gatk4/revertsam/test.yml index c649e011..7689af98 100644 --- a/tests/software/gatk4/revertsam/test.yml +++ b/tests/software/gatk4/revertsam/test.yml @@ -1,8 +1,8 @@ -- name: gatk4 mergevcfs - command: nextflow run ./tests/software/gatk4/mergevcfs -entry test_gatk4_mergevcfs -c tests/config/nextflow.config +- name: gatk4 revertsam + command: nextflow run ./tests/software/gatk4/revertsam -entry test_gatk4_revertsam -c tests/config/nextflow.config tags: - gatk4 - - gatk4_mergevcfs + - gatk4_revertsam files: - - path: output/gatk4/test.merged.vcf.gz - md5sum: f25850b7bd4d362b5ea67d4453e9df55 + - path: output/gatk4/test.reverted.bam + md5sum: 6de199f7a0577e2a3fe7b3a9cb4ae25d