From b012b349c1ef324f1e72fd474b941e2e249b8a65 Mon Sep 17 00:00:00 2001 From: Benjamin Wingfield Date: Mon, 15 Nov 2021 13:55:18 +0000 Subject: [PATCH] New module: `plink2/vcf` (#1006) * implement plink2 VCF import * fix yaml indentation Co-authored-by: Chris Cheshire --- modules/plink2/vcf/functions.nf | 78 +++++++++++++++++++++++++++++++ modules/plink2/vcf/main.nf | 43 +++++++++++++++++ modules/plink2/vcf/meta.yml | 52 +++++++++++++++++++++ tests/modules/plink2/vcf/main.nf | 13 ++++++ tests/modules/plink2/vcf/test.yml | 12 +++++ 5 files changed, 198 insertions(+) create mode 100644 modules/plink2/vcf/functions.nf create mode 100644 modules/plink2/vcf/main.nf create mode 100644 modules/plink2/vcf/meta.yml create mode 100644 tests/modules/plink2/vcf/main.nf create mode 100644 tests/modules/plink2/vcf/test.yml diff --git a/modules/plink2/vcf/functions.nf b/modules/plink2/vcf/functions.nf new file mode 100644 index 00000000..85628ee0 --- /dev/null +++ b/modules/plink2/vcf/functions.nf @@ -0,0 +1,78 @@ +// +// 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() +} + +// +// Extract name of module from process name using $task.process +// +def getProcessName(task_process) { + return task_process.tokenize(':')[-1] +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + + // Do not publish versions.yml unless running from pytest workflow + if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) { + return null + } + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${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)}/$args.filename" + } +} diff --git a/modules/plink2/vcf/main.nf b/modules/plink2/vcf/main.nf new file mode 100644 index 00000000..869a5587 --- /dev/null +++ b/modules/plink2/vcf/main.nf @@ -0,0 +1,43 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process PLINK2_VCF { + tag "$meta.id" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::plink2=2.00a2.3" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/plink2:2.00a2.3--h712d239_1" + } else { + container "quay.io/biocontainers/plink2:2.00a2.3--h712d239_1" + } + + input: + tuple val(meta), path(vcf) + + output: + tuple val(meta), path("*.pgen"), emit: pgen + tuple val(meta), path("*.psam"), emit: psam + tuple val(meta), path("*.pvar"), emit: pvar + path "versions.yml" , emit: versions + + script: + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + plink2 \\ + $options.args \\ + --vcf $vcf \\ + --out ${prefix} + + cat <<-END_VERSIONS > versions.yml + ${getProcessName(task.process)}: + ${getSoftwareName(task.process)}: \$(plink2 --version 2>&1 | sed 's/^PLINK v//; s/ 64.*\$//' ) + END_VERSIONS + """ +} diff --git a/modules/plink2/vcf/meta.yml b/modules/plink2/vcf/meta.yml new file mode 100644 index 00000000..1b2f3a9b --- /dev/null +++ b/modules/plink2/vcf/meta.yml @@ -0,0 +1,52 @@ +name: plink2_vcf +description: Import variant genetic data using plink2 +keywords: + - plink2 + - import +tools: + - plink2: + description: | + Whole genome association analysis toolset, designed to perform a range + of basic, large-scale analyses in a computationally efficient manner + homepage: http://www.cog-genomics.org/plink/2.0/ + documentation: http://www.cog-genomics.org/plink/2.0/general_usage + tool_dev_url: None + doi: "" + licence: ['GPL v3'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - vcf: + type: file + description: Variant calling file (vcf) + pattern: "*.{vcf}, *.{vcf.gz}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" + - pgen: + type: file + description: PLINK 2 binary genotype table + pattern: "*.{pgen}" + - psam: + type: file + description: PLINK 2 sample information file + pattern: "*.{psam}" + - pvar: + type: file + description: PLINK 2 variant information file + pattern: "*.{psam}" + +authors: + - "@nebfield" diff --git a/tests/modules/plink2/vcf/main.nf b/tests/modules/plink2/vcf/main.nf new file mode 100644 index 00000000..409e7995 --- /dev/null +++ b/tests/modules/plink2/vcf/main.nf @@ -0,0 +1,13 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { PLINK2_VCF } from '../../../../modules/plink2/vcf/main.nf' addParams( options: [args:'--allow-extra-chr'] ) + +workflow test_plink2_vcf { + + input = [ [ id:'test', single_end:false ], // meta map + file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true) ] + + PLINK2_VCF ( input ) +} diff --git a/tests/modules/plink2/vcf/test.yml b/tests/modules/plink2/vcf/test.yml new file mode 100644 index 00000000..3f0cddc6 --- /dev/null +++ b/tests/modules/plink2/vcf/test.yml @@ -0,0 +1,12 @@ +- name: plink2 vcf test_plink2_vcf + command: nextflow run tests/modules/plink2/vcf -entry test_plink2_vcf -c tests/config/nextflow.config + tags: + - plink2/vcf + - plink2 + files: + - path: output/plink2/test.pgen + md5sum: d66d3cd4a6c9cca1a4073d7f4b277041 + - path: output/plink2/test.psam + md5sum: dc3b77d7753a7bed41734323e3549b10 + - path: output/plink2/test.pvar + md5sum: d61e53f847a6335138b584216b4e45d0