From b5b259a2d9204de519e1adf2bb0a7a093ca2d5b5 Mon Sep 17 00:00:00 2001 From: phue Date: Wed, 17 Feb 2021 17:34:51 +0100 Subject: [PATCH 1/2] add qualimap/bamqc + test --- .github/filters.yml | 4 ++ software/qualimap/bamqc/functions.nf | 59 ++++++++++++++++++++++ software/qualimap/bamqc/main.nf | 63 +++++++++++++++++++++++ software/qualimap/bamqc/meta.yml | 70 ++++++++++++++++++++++++++ tests/software/qualimap/bamqc/main.nf | 16 ++++++ tests/software/qualimap/bamqc/test.yml | 26 ++++++++++ 6 files changed, 238 insertions(+) create mode 100644 software/qualimap/bamqc/functions.nf create mode 100644 software/qualimap/bamqc/main.nf create mode 100644 software/qualimap/bamqc/meta.yml create mode 100644 tests/software/qualimap/bamqc/main.nf create mode 100644 tests/software/qualimap/bamqc/test.yml diff --git a/.github/filters.yml b/.github/filters.yml index 695ac1b9..631c88e0 100644 --- a/.github/filters.yml +++ b/.github/filters.yml @@ -181,6 +181,10 @@ preseq_lcextrap: - software/preseq/lcextrap/** - tests/software/preseq/lcextrap/** +qualimap_bamqc: + - software/qualimap/bamqc/** + - tests/software/qualimap/bamqc/** + quast: - software/quast/** - tests/software/quast/** diff --git a/software/qualimap/bamqc/functions.nf b/software/qualimap/bamqc/functions.nf new file mode 100644 index 00000000..d25eea86 --- /dev/null +++ b/software/qualimap/bamqc/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)}/$args.filename" + } + } +} diff --git a/software/qualimap/bamqc/main.nf b/software/qualimap/bamqc/main.nf new file mode 100644 index 00000000..d54dc704 --- /dev/null +++ b/software/qualimap/bamqc/main.nf @@ -0,0 +1,63 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +def options = initOptions(params.options) + +process QUALIMAP_BAMQC { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) } + + conda (params.enable_conda ? "bioconda::qualimap=2.2.2d" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/qualimap:2.2.2d--1" + } else { + container "quay.io/biocontainers/qualimap:2.2.2d--1" + } + + input: + tuple val(meta), path(bam) + path gff + val use_gff + + output: + tuple val(meta), path("${prefix}"), emit: results + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + + def threads = task.cpus + def collect_pairs = meta.single_end ? '' : '--collect-overlap-pairs' + def memory = task.memory.toGiga() + "G" + + def regions = use_gff ? "--gff $gff" : '' + + def strandedness = 'non-strand-specific' + if (meta.strandedness == 'forward') { + strandedness = 'strand-specific-forward' + } else if (meta.strandedness == 'reverse') { + strandedness = 'strand-specific-reverse' + } + """ + unset DISPLAY + mkdir tmp + export _JAVA_OPTIONS=-Djava.io.tmpdir=./tmp + qualimap \\ + --java-mem-size=$memory \\ + bamqc \\ + $options.args \\ + -bam $bam \\ + $regions \\ + -p $strandedness \\ + $collect_pairs \\ + -outdir $prefix \\ + -nt $threads + + echo \$(qualimap 2>&1) | sed 's/^.*QualiMap v.//; s/Built.*\$//' > ${software}.version.txt + """ +} diff --git a/software/qualimap/bamqc/meta.yml b/software/qualimap/bamqc/meta.yml new file mode 100644 index 00000000..61f4bc8b --- /dev/null +++ b/software/qualimap/bamqc/meta.yml @@ -0,0 +1,70 @@ +name: qualimap_bamqc +description: Evaluate alignment data +keywords: + - quality control + - qc + - bam +tools: + - qualimap: + description: | + Qualimap 2 is a platform-independent application written in + Java and R that provides both a Graphical User Interface and + a command-line interface to facilitate the quality control of + alignment sequencing data and its derivatives like feature counts. + homepage: http://qualimap.bioinfo.cipf.es/ + documentation: http://qualimap.conesalab.org/doc_html/index.html + doi: 10.1093/bioinformatics/bts503 +params: + - outdir: + type: string + description: | + The pipeline's output directory. By default, the module will + output files into `$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 ] + - bam: + type: file + description: BAM file + pattern: "*.{bam}" + - gff: + type: file + description: Feature file with regions of interest + pattern: "*.{gff,gtf,bed}" + - use_gff: + type: boolean + description: Specifies if feature file should be used or not +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - results: + type: dir + description: Qualimap results dir + pattern: "*/*" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@phue" diff --git a/tests/software/qualimap/bamqc/main.nf b/tests/software/qualimap/bamqc/main.nf new file mode 100644 index 00000000..1873e81b --- /dev/null +++ b/tests/software/qualimap/bamqc/main.nf @@ -0,0 +1,16 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { QUALIMAP_BAMQC } from '../../../../software/qualimap/bamqc/main.nf' addParams( options: [:] ) + +workflow test_qualimap_bamqc { + + def input = [] + input = [ [ id:'test', single_end:false ], // meta map + file("${launchDir}/tests/data/bam/test.paired_end.sorted.bam", checkIfExists: true) ] + def gff = file("dummy_file.txt") + def use_gff = false + + QUALIMAP_BAMQC ( input, gff, use_gff ) +} diff --git a/tests/software/qualimap/bamqc/test.yml b/tests/software/qualimap/bamqc/test.yml new file mode 100644 index 00000000..e33ab0b5 --- /dev/null +++ b/tests/software/qualimap/bamqc/test.yml @@ -0,0 +1,26 @@ +- name: Run qualimap bamqc test workflow + command: nextflow run ./tests/software/qualimap/bamqc -entry test_qualimap_bamqc -c tests/config/nextflow.config + tags: + - qualimap + - qualimap_bamqc + files: + - path: output/qualimap/test/raw_data_qualimapReport/coverage_across_reference.txt + md5sum: 0e2ae3deae8adbe6c66db4dadb260c76 + - path: output/qualimap/test/raw_data_qualimapReport/coverage_histogram.txt + md5sum: 0e9f37aabb761969526f445ed8d3173b + - path: output/qualimap/test/raw_data_qualimapReport/duplication_rate_histogram.txt + md5sum: 2299c92a3049270b9d7b1f521cafbb86 + - path: output/qualimap/test/raw_data_qualimapReport/genome_fraction_coverage.txt + md5sum: 89c8c882c9423fafe03b4fc98e2bfb5a + - path: output/qualimap/test/raw_data_qualimapReport/insert_size_across_reference.txt + md5sum: 966230f2bbe796788beac30678597e79 + - path: output/qualimap/test/raw_data_qualimapReport/insert_size_histogram.txt + md5sum: b3049afc6c3c57c3b278abd66a66a690 + - path: output/qualimap/test/raw_data_qualimapReport/mapped_reads_gc-content_distribution.txt + md5sum: e9e0189463430b5565ea6da1d5976e40 + - path: output/qualimap/test/raw_data_qualimapReport/mapped_reads_nucleotide_content.txt + md5sum: fa1566299e1bcd2d65c95b32ae2ca3d1 + - path: output/qualimap/test/raw_data_qualimapReport/mapping_quality_across_reference.txt + md5sum: 40b6951739a602da545e38a00b698fde + - path: output/qualimap/test/raw_data_qualimapReport/mapping_quality_histogram.txt + md5sum: c66579f0114a9aedc70820fa609fb1ec From 0606c06a2504a1e5de40119f44b4a7709b9feb1e Mon Sep 17 00:00:00 2001 From: phue Date: Thu, 18 Feb 2021 10:00:49 +0100 Subject: [PATCH 2/2] qualimap/bamqc: remove unneeded variable definition can just use task.cpus directly --- software/qualimap/bamqc/main.nf | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/software/qualimap/bamqc/main.nf b/software/qualimap/bamqc/main.nf index d54dc704..a1426d93 100644 --- a/software/qualimap/bamqc/main.nf +++ b/software/qualimap/bamqc/main.nf @@ -31,10 +31,8 @@ process QUALIMAP_BAMQC { def software = getSoftwareName(task.process) prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - def threads = task.cpus def collect_pairs = meta.single_end ? '' : '--collect-overlap-pairs' def memory = task.memory.toGiga() + "G" - def regions = use_gff ? "--gff $gff" : '' def strandedness = 'non-strand-specific' @@ -56,7 +54,7 @@ process QUALIMAP_BAMQC { -p $strandedness \\ $collect_pairs \\ -outdir $prefix \\ - -nt $threads + -nt $task.cpus echo \$(qualimap 2>&1) | sed 's/^.*QualiMap v.//; s/Built.*\$//' > ${software}.version.txt """