From 10524e351518e0278ae1c2058de3a18046b3e887 Mon Sep 17 00:00:00 2001 From: MaxUlysse Date: Tue, 16 Feb 2021 14:47:53 +0100 Subject: [PATCH] chores: add modules for htslib/tabix --- .github/filters.yml | 4 ++ software/htslib/tabix/functions.nf | 59 ++++++++++++++++++++++++++++ software/htslib/tabix/main.nf | 35 +++++++++++++++++ software/htslib/tabix/meta.yml | 49 +++++++++++++++++++++++ tests/software/htslib/tabix/main.nf | 9 +++++ tests/software/htslib/tabix/test.yml | 8 ++++ 6 files changed, 164 insertions(+) create mode 100644 software/htslib/tabix/functions.nf create mode 100644 software/htslib/tabix/main.nf create mode 100644 software/htslib/tabix/meta.yml create mode 100644 tests/software/htslib/tabix/main.nf create mode 100644 tests/software/htslib/tabix/test.yml diff --git a/.github/filters.yml b/.github/filters.yml index 9fe5cdb9..2007f181 100644 --- a/.github/filters.yml +++ b/.github/filters.yml @@ -136,6 +136,10 @@ gunzip: - software/gunzip/** - tests/software/gunzip/** +htslib_tabix: + - software/htslib/tabix/** + - tests/software/htslib/tabix/** + ivar_consensus: - software/ivar/consensus/** - tests/software/ivar/consensus/** diff --git a/software/htslib/tabix/functions.nf b/software/htslib/tabix/functions.nf new file mode 100644 index 00000000..d25eea86 --- /dev/null +++ b/software/htslib/tabix/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)}/$args.filename" + } + } +} diff --git a/software/htslib/tabix/main.nf b/software/htslib/tabix/main.nf new file mode 100644 index 00000000..dcffba4f --- /dev/null +++ b/software/htslib/tabix/main.nf @@ -0,0 +1,35 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +def options = initOptions(params.options) + +process HTSLIB_TABIX { + tag "$vcf" + 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:'') } + + conda (params.enable_conda ? "bioconda::tabix=0.2.6" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/tabix:0.2.6--ha92aebf_0" + } else { + container "quay.io/biocontainers/tabix:0.2.6--ha92aebf_0" + } + + input: + path vcf + + output: + path("*.tbi") , emit: tbi + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + """ + tabix -p vcf $vcf + + echo \$(tabix -h 2>&1) | sed 's/^.*Version: //; s/(.*\$//' > ${software}.version.txt + """ +} diff --git a/software/htslib/tabix/meta.yml b/software/htslib/tabix/meta.yml new file mode 100644 index 00000000..dd13ebdc --- /dev/null +++ b/software/htslib/tabix/meta.yml @@ -0,0 +1,49 @@ +name: htslib_tabix +description: create tabix index from a sorted bgzip vcf file +keywords: + - index + - tabix + - vcf +tools: + - tabix: + description: Generic indexer for TAB-delimited genome position files. + homepage: https://www.htslib.org/ + documentation: https://www.htslib.org/doc/tabix.1.html + doi: 10.1093/bioinformatics/btq671 +params: + - outdir: + type: string + description: | + The pipeline's output directory. By default, the module will + output files into `$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: + - vcf: + type: file + description: vcf.gz file + pattern: "*.{vcf.gz}" +output: + - tbi: + type: file + description: tabix index file + pattern: "*.{tbi}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@maxulysse" diff --git a/tests/software/htslib/tabix/main.nf b/tests/software/htslib/tabix/main.nf new file mode 100644 index 00000000..5e2f857a --- /dev/null +++ b/tests/software/htslib/tabix/main.nf @@ -0,0 +1,9 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { HTSLIB_TABIX } from '../../../../software/htslib/tabix/main.nf' addParams( options: [:] ) + +workflow test_htslib_tabix { + HTSLIB_TABIX ( file("${launchDir}/tests/data/vcf/test.vcf.gz", checkIfExists: true) ) +} \ No newline at end of file diff --git a/tests/software/htslib/tabix/test.yml b/tests/software/htslib/tabix/test.yml new file mode 100644 index 00000000..677c6530 --- /dev/null +++ b/tests/software/htslib/tabix/test.yml @@ -0,0 +1,8 @@ +- name: htslib tabix + command: nextflow run ./tests/software/htslib/tabix -entry test_htslib_tabix -c tests/config/nextflow.config + tags: + - htslib + - htslib_tabix + files: + - path: output/htslib/test.vcf.gz.tbi + md5sum: a03f56d3e968f32256ffb9f6b7d01812