diff --git a/modules/bcftools/view/functions.nf b/modules/bcftools/view/functions.nf new file mode 100644 index 00000000..da9da093 --- /dev/null +++ b/modules/bcftools/view/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/bcftools/view/main.nf b/modules/bcftools/view/main.nf new file mode 100644 index 00000000..92f7036b --- /dev/null +++ b/modules/bcftools/view/main.nf @@ -0,0 +1,51 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process BCFTOOLS_VIEW { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::bcftools=1.13" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/bcftools:1.13--h3a49de5_0" + } else { + container "quay.io/biocontainers/bcftools:1.13--h3a49de5_0" + } + + input: + tuple val(meta), path(vcf), path(index) + path(regions) + path(targets) + path(samples) + + output: + tuple val(meta), path("*.gz") , emit: vcf + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + def regions_file = regions ? "--regions-file ${regions}" : "" + def targets_file = targets ? "--targets-file ${targets}" : "" + def samples_file = samples ? "--samples-file ${samples}" : "" + + + """ + bcftools view \\ + --output ${prefix}.vcf.gz \\ + ${regions_file} \\ + ${targets_file} \\ + ${samples_file} \\ + $options.args \\ + --threads $task.cpus \\ + ${vcf} + + echo \$(bcftools --version 2>&1) | sed 's/^.*bcftools //; s/ .*\$//' > ${software}.version.txt + """ +} diff --git a/modules/bcftools/view/meta.yml b/modules/bcftools/view/meta.yml new file mode 100644 index 00000000..947e2562 --- /dev/null +++ b/modules/bcftools/view/meta.yml @@ -0,0 +1,62 @@ +name: bcftools_view +description: View, subset and filter VCF or BCF files by position and filtering expression. Convert between VCF and BCF +keywords: + - variant calling + - view + - bcftools + - VCF + +tools: + - view: + description: | + View, subset and filter VCF or BCF files by position and filtering expression. Convert between VCF and BCF + homepage: http://samtools.github.io/bcftools/bcftools.html + documentation: http://www.htslib.org/doc/bcftools.html + doi: 10.1093/bioinformatics/btp352 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - vcf: + type: file + description: | + The vcf file to be inspected. + e.g. 'file.vcf' + - index: + type: file + description: | + The tab index for the VCF file to be inspected. + e.g. 'file.tbi' + - regions: + type: file + description: | + Optionally, restrict the operation to regions listed in this file. + e.g. 'file.vcf' + - targets: + type: file + description: | + Optionally, restrict the operation to regions listed in this file (doesn't rely upon index files) + e.g. 'file.vcf' + - samples: + type: file + description: | + Optional, file of sample names to be included or excluded. + e.g. 'file.tsv' +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - vcf: + type: file + description: VCF normalized output file + pattern: "*.{vcf.gz}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@abhi18av" diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml index fb033966..042040f7 100644 --- a/tests/config/pytest_modules.yml +++ b/tests/config/pytest_modules.yml @@ -70,6 +70,10 @@ bcftools/stats: - modules/bcftools/stats/** - tests/modules/bcftools/stats/** +bcftools/view: + - modules/bcftools/view/** + - tests/modules/bcftools/view/** + bedtools/bamtobed: - modules/bedtools/bamtobed/** - tests/modules/bedtools/bamtobed/** diff --git a/tests/config/test_data.config b/tests/config/test_data.config index 73232088..e03bb2a8 100644 --- a/tests/config/test_data.config +++ b/tests/config/test_data.config @@ -67,6 +67,7 @@ params { test2_vcf = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test2.vcf" test2_vcf_gz = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test2.vcf.gz" test2_vcf_gz_tbi = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test2.vcf.gz.tbi" + test2_vcf_targets_tsv_gz = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test2.targets.tsv.gz" test3_vcf = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test3.vcf" test3_vcf_gz = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test3.vcf.gz" test3_vcf_gz_tbi = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test3.vcf.gz.tbi" diff --git a/tests/modules/bcftools/view/main.nf b/tests/modules/bcftools/view/main.nf new file mode 100644 index 00000000..a8ac3b31 --- /dev/null +++ b/tests/modules/bcftools/view/main.nf @@ -0,0 +1,31 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { BCFTOOLS_VIEW } from '../../../../modules/bcftools/view/main.nf' addParams( options: ['args': '--no-version'] ) + +workflow test_bcftools_view { + + regions = [] + targets = [] + samples = [] + + input = [[ id:'out', single_end:false ], // meta map + file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true), + file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)] + + BCFTOOLS_VIEW ( input, regions, targets, samples ) +} + +workflow test_bcftools_view_with_optional_files { + + regions = file(params.test_data['sarscov2']['illumina']['test3_vcf_gz'], checkIfExists: true) + targets = file(params.test_data['sarscov2']['illumina']['test2_vcf_targets_tsv_gz'], checkIfExists: true) + samples = [] + + input = [[ id:'out', single_end:false ], // meta map + file(params.test_data['sarscov2']['illumina']['test2_vcf_gz'], checkIfExists: true), + file(params.test_data['sarscov2']['illumina']['test2_vcf_gz_tbi'], checkIfExists: true)] + + BCFTOOLS_VIEW ( input, regions, targets, samples ) +} diff --git a/tests/modules/bcftools/view/test.yml b/tests/modules/bcftools/view/test.yml new file mode 100644 index 00000000..179e9a1c --- /dev/null +++ b/tests/modules/bcftools/view/test.yml @@ -0,0 +1,17 @@ +- name: bcftools view + command: nextflow run ./tests/modules/bcftools/view -entry test_bcftools_view -c tests/config/nextflow.config + tags: + - bcftools + - bcftools/view + files: + - path: output/bcftools/out.vcf.gz + md5sum: fc178eb342a91dc0d1d568601ad8f8e2 + +- name: bcftools view with optional files + command: nextflow run ./tests/modules/bcftools/view -entry test_bcftools_view_with_optional_files -c tests/config/nextflow.config + tags: + - bcftools + - bcftools/view + files: + - path: output/bcftools/out.vcf.gz + md5sum: 1d450e1c65b081ead0edbf5e4fa539ee