From 02d10c25a30c1ef86ed8337133c3f7b4a77a40ca Mon Sep 17 00:00:00 2001 From: JoseEspinosa Date: Mon, 8 Feb 2021 23:41:10 +0100 Subject: [PATCH] Add bedtools maskfasta module --- .github/filters.yml | 4 ++ software/bedtools/maskfasta/functions.nf | 59 ++++++++++++++++++++ software/bedtools/maskfasta/main.nf | 41 ++++++++++++++ software/bedtools/maskfasta/meta.yml | 64 ++++++++++++++++++++++ tests/data/bed/C.bed | 2 + tests/software/bedtools/maskfasta/main.nf | 14 +++++ tests/software/bedtools/maskfasta/test.yml | 8 +++ 7 files changed, 192 insertions(+) create mode 100644 software/bedtools/maskfasta/functions.nf create mode 100644 software/bedtools/maskfasta/main.nf create mode 100644 software/bedtools/maskfasta/meta.yml create mode 100644 tests/data/bed/C.bed create mode 100644 tests/software/bedtools/maskfasta/main.nf create mode 100644 tests/software/bedtools/maskfasta/test.yml diff --git a/.github/filters.yml b/.github/filters.yml index 279eaf50..299b5fd6 100644 --- a/.github/filters.yml +++ b/.github/filters.yml @@ -14,6 +14,10 @@ bedtools_intersect: - software/bedtools/intersect/** - tests/software/bedtools/intersect/** +bedtools_maskfasta: + - software/bedtools/maskfasta/** + - tests/software/bedtools/maskfasta/** + bedtools_merge: - software/bedtools/merge/** - tests/software/bedtools/merge/** diff --git a/software/bedtools/maskfasta/functions.nf b/software/bedtools/maskfasta/functions.nf new file mode 100644 index 00000000..d25eea86 --- /dev/null +++ b/software/bedtools/maskfasta/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)}/$args.filename" + } + } +} diff --git a/software/bedtools/maskfasta/main.nf b/software/bedtools/maskfasta/main.nf new file mode 100644 index 00000000..ccd93df7 --- /dev/null +++ b/software/bedtools/maskfasta/main.nf @@ -0,0 +1,41 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +def options = initOptions(params.options) + +process BEDTOOLS_MASKFASTA { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) } + + conda (params.enable_conda ? "bioconda::bedtools=2.30.0" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/bedtools:2.30.0--hc088bd4_0" + } else { + container "quay.io/biocontainers/bedtools:2.30.0--hc088bd4_0" + } + + input: + tuple val(meta), path(bed) + path fasta + + output: + tuple val(meta), path("*.fa"), emit: fasta + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + bedtools \\ + maskfasta \\ + $options.args \\ + -fi $fasta \\ + -bed $bed \\ + -fo ${prefix}.fa + bedtools --version | sed -e "s/bedtools v//g" > ${software}.version.txt + """ +} diff --git a/software/bedtools/maskfasta/meta.yml b/software/bedtools/maskfasta/meta.yml new file mode 100644 index 00000000..ef4e4096 --- /dev/null +++ b/software/bedtools/maskfasta/meta.yml @@ -0,0 +1,64 @@ +name: bedtools_maskfasta +description: masks sequences in a FASTA file based on intervals defined in a feature file. +keywords: + - bed + - fasta + - maskfasta +tools: + - bedtools: + description: | + A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types. + documentation: https://bedtools.readthedocs.io/en/latest/content/tools/intersect.html +params: + - outdir: + type: string + description: | + The pipeline's output directory. By default, the module will + output files into `$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', single_end:false ] + - bed: + type: file + description: Bed feature file + pattern: "*.{bed}" + - fasta: + type: file + description: Input fasta file + pattern: "*.{fa,fasta}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - fasta: + type: file + description: Output masked fasta file + pattern: "*.{fa}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@joseespinosa" + - "@drpatelh" diff --git a/tests/data/bed/C.bed b/tests/data/bed/C.bed new file mode 100644 index 00000000..6a54c85d --- /dev/null +++ b/tests/data/bed/C.bed @@ -0,0 +1,2 @@ +gi|170079663|ref|NC_010473.1| 1 100 + diff --git a/tests/software/bedtools/maskfasta/main.nf b/tests/software/bedtools/maskfasta/main.nf new file mode 100644 index 00000000..11901636 --- /dev/null +++ b/tests/software/bedtools/maskfasta/main.nf @@ -0,0 +1,14 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { BEDTOOLS_MASKFASTA } from '../../../../software/bedtools/maskfasta/main.nf' addParams( options: [:] ) + +workflow test_bedtools_maskfasta { + def input,fasta = [] + bed = [ [ id:'test'], + file("${launchDir}/tests/data/bed/C.bed", checkIfExists: true) ] + fasta = [ file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa", checkIfExists: true) ] + + BEDTOOLS_MASKFASTA( bed, fasta ) +} diff --git a/tests/software/bedtools/maskfasta/test.yml b/tests/software/bedtools/maskfasta/test.yml new file mode 100644 index 00000000..e068c593 --- /dev/null +++ b/tests/software/bedtools/maskfasta/test.yml @@ -0,0 +1,8 @@ +- name: bedtools merge + command: nextflow run ./tests/software/bedtools/maskfasta -entry test_bedtools_maskfasta -c tests/config/nextflow.config + tags: + - bedtools + - bedtools_maskfasta + files: + - path: output/bedtools/test.fa + md5sum: 6ff45e409858b259090e1c04309adc3f