From 6dcaf5ffc80e5a92745f77f8d08586591aa2465e Mon Sep 17 00:00:00 2001 From: kevinmenden Date: Fri, 19 Feb 2021 11:26:31 +0100 Subject: [PATCH] add gatk4 bedtointervallist --- .github/filters.yml | 4 ++ software/gatk4/bedtointervallist/functions.nf | 59 ++++++++++++++++++ software/gatk4/bedtointervallist/main.nf | 41 +++++++++++++ software/gatk4/bedtointervallist/meta.yml | 60 +++++++++++++++++++ tests/data/bed/sarscov2.bed | 4 ++ .../GCA_011545545.1_ASM1154554v1_genomic.dict | 2 + .../software/gatk4/bedtointervallist/main.nf | 16 +++++ .../software/gatk4/bedtointervallist/test.yml | 8 +++ 8 files changed, 194 insertions(+) create mode 100644 software/gatk4/bedtointervallist/functions.nf create mode 100644 software/gatk4/bedtointervallist/main.nf create mode 100644 software/gatk4/bedtointervallist/meta.yml create mode 100644 tests/data/bed/sarscov2.bed create mode 100644 tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.dict create mode 100644 tests/software/gatk4/bedtointervallist/main.nf create mode 100644 tests/software/gatk4/bedtointervallist/test.yml diff --git a/.github/filters.yml b/.github/filters.yml index 537d982f..c9f8b99a 100644 --- a/.github/filters.yml +++ b/.github/filters.yml @@ -128,6 +128,10 @@ gatk_createsequencedictionary: - software/gatk/createsequencedictionary/** - tests/software/gatk/createsequencedictionary/** +gatk4_bedtointervallist: + - software/gatk4/bedtointervallist/** + - tests/software/gatk4/bedtointervallist/** + gffread: - software/gffread/** - tests/software/gffread/** diff --git a/software/gatk4/bedtointervallist/functions.nf b/software/gatk4/bedtointervallist/functions.nf new file mode 100644 index 00000000..d25eea86 --- /dev/null +++ b/software/gatk4/bedtointervallist/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)}/$args.filename" + } + } +} diff --git a/software/gatk4/bedtointervallist/main.nf b/software/gatk4/bedtointervallist/main.nf new file mode 100644 index 00000000..85fb8372 --- /dev/null +++ b/software/gatk4/bedtointervallist/main.nf @@ -0,0 +1,41 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +def options = initOptions(params.options) + +process GATK4_BEDTOINTERVALLIST { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) } + + conda (params.enable_conda ? 'bioconda::gatk4:4.1.9.0' : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container 'https://depot.galaxyproject.org/singularity/gatk4:4.1.9.0--py39_0' + } else { + container 'quay.io/biocontainers/gatk4:4.1.9.0--py39_0' + } + + input: + tuple val(meta), path(bed) + path sequence_dict + + output: + tuple val(meta), path('*.interval_list'), emit: interval_list + path '*.version.txt' , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}.${options.suffix}" : "${meta.id}" + """ + gatk BedToIntervalList \\ + -I $bed \\ + -SD $sequence_dict \\ + -O ${prefix}.interval_list \\ + $options.args + + gatk --version | grep Picard | sed "s/Picard Version: //g" > ${software}.version.txt + """ +} diff --git a/software/gatk4/bedtointervallist/meta.yml b/software/gatk4/bedtointervallist/meta.yml new file mode 100644 index 00000000..4ed8629e --- /dev/null +++ b/software/gatk4/bedtointervallist/meta.yml @@ -0,0 +1,60 @@ +name: gatk4_bedtointervallist +description: Creates an interval list from a bed file and a reference dict +keywords: + - bed + - interval list +tools: + - gatk4: + description: | + Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools + with a primary focus on variant discovery and genotyping. Its powerful processing engine + and high-performance computing features make it capable of taking on projects of any size. + homepage: https://gatk.broadinstitute.org/hc/en-us + documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s + doi: 10.1158/1538-7445.AM2017-3590 +params: + - outdir: + type: string + description: | + The pipeline's output directory. By default, the module will + output files into `$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'] + - bed: + type: file + description: Input bed file + pattern: "*.bed" + - dict: + type: file + description: Sequence dictionary + pattern: "*.dict" +output: + - interval_list: + type: file + description: gatk interval list file + pattern: "*.interval_list" + - version: + type: file + description: File containing software version + pattern: "*.version.txt" +authors: + - "@kevinmenden" diff --git a/tests/data/bed/sarscov2.bed b/tests/data/bed/sarscov2.bed new file mode 100644 index 00000000..ba45ab3d --- /dev/null +++ b/tests/data/bed/sarscov2.bed @@ -0,0 +1,4 @@ +MT192765.1 1242 1264 nCoV-2019_5_LEFT 1 + +MT192765.1 1623 1651 nCoV-2019_5_RIGHT 1 - +MT192765.1 1573 1595 nCoV-2019_6_LEFT 2 + +MT192765.1 1942 1964 nCoV-2019_6_RIGHT 2 - diff --git a/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.dict b/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.dict new file mode 100644 index 00000000..bb6a4ae8 --- /dev/null +++ b/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.dict @@ -0,0 +1,2 @@ +@HD VN:1.6 +@SQ SN:MT192765.1 LN:29829 M5:c95f3e5592d0ad9974e41e7f0ea14eb0 UR:file:/Users/kevin/Documents/nfcore/modules/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.fna diff --git a/tests/software/gatk4/bedtointervallist/main.nf b/tests/software/gatk4/bedtointervallist/main.nf new file mode 100644 index 00000000..1775c39b --- /dev/null +++ b/tests/software/gatk4/bedtointervallist/main.nf @@ -0,0 +1,16 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { GATK4_BEDTOINTERVALLIST } from '../../../../software/gatk4/bedtointervallist/main.nf' addParams( options: [:] ) + +workflow test_gatk4_bedtointervallist { + + def input = [] + input = [ [ id:'test' ], // meta map + [ file("${launchDir}/tests/data/bed/sarscov2.bed", checkIfExists: true)] ] + + sd = file("${launchDir}/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.dict", checkIfExists: true) + + GATK4_BEDTOINTERVALLIST ( input, sd ) +} diff --git a/tests/software/gatk4/bedtointervallist/test.yml b/tests/software/gatk4/bedtointervallist/test.yml new file mode 100644 index 00000000..6612cd19 --- /dev/null +++ b/tests/software/gatk4/bedtointervallist/test.yml @@ -0,0 +1,8 @@ +- name: gatk4 bedtointervallist + command: nextflow run ./tests/software/gatk4/bedtointervallist -entry test_gatk4_bedtointervallist -c tests/config/nextflow.config + tags: + - gatk4 + - gatk4_bedtointervallist + files: + - path: output/gatk4/test.interval_list + md5sum: e51101c9357fb2d59fd30e370eefa39c