From 1426d89440cf5a8e752e4d051aa8199c2d14c9c4 Mon Sep 17 00:00:00 2001 From: Sruthi Suresh Date: Wed, 11 Nov 2020 12:46:31 -0600 Subject: [PATCH] Completed sloprefseq and removegenes modules (main.nf, meta.yml and functiosn.nf file). Also added the test directory with input/output/main.nf files. --- software/bedtools/slop/functions.nf | 59 +++++++++++++++++++ software/bedtools/slop/main.nf | 39 ++++++++++++ software/bedtools/slop/meta.yml | 53 +++++++++++++++++ software/bedtools/test/input/A.bed | 5 ++ .../bedtools/test/input/B.metatranscripts | 1 + software/bedtools/test/input/genome.sizes | 1 + software/bedtools/test/main.nf | 29 +++++++++ software/bedtools/test/nextflow.config | 20 +++++++ .../output/test_bed_file/test.nogenes.bed | 0 .../test/output/test_bed_file/test.slop.bed | 3 + 10 files changed, 210 insertions(+) create mode 100644 software/bedtools/slop/functions.nf create mode 100644 software/bedtools/slop/main.nf create mode 100644 software/bedtools/slop/meta.yml create mode 100644 software/bedtools/test/input/A.bed create mode 100644 software/bedtools/test/input/B.metatranscripts create mode 100644 software/bedtools/test/input/genome.sizes create mode 100644 software/bedtools/test/main.nf create mode 100644 software/bedtools/test/nextflow.config create mode 100644 software/bedtools/test/output/test_bed_file/test.nogenes.bed create mode 100644 software/bedtools/test/output/test_bed_file/test.slop.bed diff --git a/software/bedtools/slop/functions.nf b/software/bedtools/slop/functions.nf new file mode 100644 index 00000000..54dc8fe8 --- /dev/null +++ b/software/bedtools/slop/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)}/$args.filename" + } + } +} \ No newline at end of file diff --git a/software/bedtools/slop/main.nf b/software/bedtools/slop/main.nf new file mode 100644 index 00000000..67b3a1ae --- /dev/null +++ b/software/bedtools/slop/main.nf @@ -0,0 +1,39 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [upstream: 1, + downstream: 10 ] + +def options = initOptions(params.options) + +process BEDTOOLS_SLOP { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) } + + conda (params.enable_conda ? "bioconda::bedtools =2.29.2" : null) + if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/bedtools:2.29.2--hc088bd4_0 " + } else { + container "quay.io/biocontainers/bedtools:2.29.2--hc088bd4_0" + } + + input: + tuple val(meta), path(beds) + path sizes + + output: + tuple val(meta), path("*.slop.bed"), emit: slopbed + path "*.version.txt", emit: version + + script: + def software = getSoftwareName(task.process) + def beds_files = beds.sort() + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + slopBed -i ${beds[0]} -g $sizes -l ${params.upstream} -r ${params.downstream} > ${prefix}.slop.bed + bedtools --version | sed -e "s/Bedtools v//g" > ${software}.version.txt + """ +} diff --git a/software/bedtools/slop/meta.yml b/software/bedtools/slop/meta.yml new file mode 100644 index 00000000..fab1e802 --- /dev/null +++ b/software/bedtools/slop/meta.yml @@ -0,0 +1,53 @@ +name: bedtools_slop +description: Adds 1 KB to the front of the genes and 10 KB to the end of the sequence. +keywords: + - bed + - slopBed + - downstream + - upstream +tools: + - bedtools: + description: | + A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types. + documentation: https://bedtools.readthedocs.io/en/latest/ + +params: + - outdir: + type: string + description: | + The pipeline's output directory. By default, the module will + output files into `$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 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bed: + type: file + description: List of bed files + pattern: "*.{bed}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bed: + type: file + description: Edited bed file + pattern: "*.{bed}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" \ No newline at end of file diff --git a/software/bedtools/test/input/A.bed b/software/bedtools/test/input/A.bed new file mode 100644 index 00000000..dc9a4f0c --- /dev/null +++ b/software/bedtools/test/input/A.bed @@ -0,0 +1,5 @@ +chr1 951 1061 +chr1 1300 1420 +chr1 1400 1500 + + diff --git a/software/bedtools/test/input/B.metatranscripts b/software/bedtools/test/input/B.metatranscripts new file mode 100644 index 00000000..74e0ef4e --- /dev/null +++ b/software/bedtools/test/input/B.metatranscripts @@ -0,0 +1 @@ +chr1 999 1010 diff --git a/software/bedtools/test/input/genome.sizes b/software/bedtools/test/input/genome.sizes new file mode 100644 index 00000000..8cc54558 --- /dev/null +++ b/software/bedtools/test/input/genome.sizes @@ -0,0 +1 @@ +chr1 1780869 diff --git a/software/bedtools/test/main.nf b/software/bedtools/test/main.nf new file mode 100644 index 00000000..404b477f --- /dev/null +++ b/software/bedtools/test/main.nf @@ -0,0 +1,29 @@ +#!/usr/bin/env nextflow + +nextflow.preview.dsl = 2 + +include { BEDTOOLS_SLOP } from '../slop/main.nf' addParams( options: [publish_dir:'test_bed_file']) +include { BEDTOOLS_REMOVEGENES } from '../removegenes/main.nf' addParams( options: [publish_dir:'test_bed_file']) + +// Define input channels + +// Run the workflow +workflow test_bed_file { + def input = [] + input = [ [ id:'test', single_end:true ], + [ file("${baseDir}/input/A.bed", checkIfExists: true),] ] + + BEDTOOLS_SLOP( + input, + file("${baseDir}/input/genome.sizes", checkIfExists: true) + ) + BEDTOOLS_REMOVEGENES( + BEDTOOLS_SLOP.out.slopbed, + file("${baseDir}/input/B.metatranscripts", checkIfExists: true) + ) + +} + +workflow { + test_bed_file() +} diff --git a/software/bedtools/test/nextflow.config b/software/bedtools/test/nextflow.config new file mode 100644 index 00000000..4ee101de --- /dev/null +++ b/software/bedtools/test/nextflow.config @@ -0,0 +1,20 @@ + +params { + outdir = "output/" + publish_dir_mode = "copy" + enable_conda = false +} + +profiles { + conda { + params.enable_conda = true + } + docker { + docker.enabled = true + docker.runOptions = '-u \$(id -u):\$(id -g)' + } + singularity { + singularity.enabled = true + singularity.autoMounts = true + } +} diff --git a/software/bedtools/test/output/test_bed_file/test.nogenes.bed b/software/bedtools/test/output/test_bed_file/test.nogenes.bed new file mode 100644 index 00000000..e69de29b diff --git a/software/bedtools/test/output/test_bed_file/test.slop.bed b/software/bedtools/test/output/test_bed_file/test.slop.bed new file mode 100644 index 00000000..147ddaa0 --- /dev/null +++ b/software/bedtools/test/output/test_bed_file/test.slop.bed @@ -0,0 +1,3 @@ +chr1 951 1061 +chr1 1300 1420 +chr1 1400 1500