From a21cc95c690e39874ded387cb4ebd160845614cb Mon Sep 17 00:00:00 2001 From: Johnathan D <28043284+bjohnnyd@users.noreply.github.com> Date: Mon, 26 Jul 2021 19:07:29 +0100 Subject: [PATCH] Add variantbam (#618) * template created for variantbam (#616) * Add bcftools reheader (#585) (#608) * local tests and linting passing (#585) * fix: picard filtersamreads input (#610) * Move readlist into same input channel as bam * Update test reflecting input restructuring * Update tests/modules/picard/filtersamreads/main.nf Co-authored-by: Harshil Patel * fix test Co-authored-by: Harshil Patel * Added module arriba (#611) * Updated the version of STAR in align and genomegenerate modules * Changes in test.yml * Changes in test.yml * Added module arriba * Changes in test configs * Added module Arriba for fusion detection * Fixed review comments * Added an output option for discarded fusions * Resolved some conflits * conflicts * Apply suggestions from code review Co-authored-by: Harshil Patel * added test for new header * enhance module fastp: add `save_merged` (#598) (#614) * enhance module fastp: add `save_merged` (#598) * removed md5sum checks from log and json * Apply suggestions from code review Co-authored-by: James A. Fellows Yates Co-authored-by: Harshil Patel Co-authored-by: praveenraj2018 <43108054+praveenraj2018@users.noreply.github.com> * fixed autogenerated biocontainter links * variantbam module passing all tests/lints (#616) * Added an optional output junction channel in STAR (#621) * Added an optional output channel for chimeric junctions * Fix in test.yml * Apply suggestions from code review Co-authored-by: Harshil Patel * removed qcreport output fixes #616 Co-authored-by: James A. Fellows Yates Co-authored-by: Harshil Patel Co-authored-by: praveenraj2018 <43108054+praveenraj2018@users.noreply.github.com> --- modules/variantbam/functions.nf | 68 +++++++++++++++++++++++++++++++ modules/variantbam/main.nf | 41 +++++++++++++++++++ modules/variantbam/meta.yml | 46 +++++++++++++++++++++ tests/config/pytest_modules.yml | 4 ++ tests/modules/variantbam/main.nf | 13 ++++++ tests/modules/variantbam/test.yml | 7 ++++ 6 files changed, 179 insertions(+) create mode 100644 modules/variantbam/functions.nf create mode 100644 modules/variantbam/main.nf create mode 100644 modules/variantbam/meta.yml create mode 100644 tests/modules/variantbam/main.nf create mode 100644 tests/modules/variantbam/test.yml diff --git a/modules/variantbam/functions.nf b/modules/variantbam/functions.nf new file mode 100644 index 00000000..da9da093 --- /dev/null +++ b/modules/variantbam/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${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)}/$args.filename" + } + } +} diff --git a/modules/variantbam/main.nf b/modules/variantbam/main.nf new file mode 100644 index 00000000..dc29de58 --- /dev/null +++ b/modules/variantbam/main.nf @@ -0,0 +1,41 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +def VERSION = '1.4.4a' + +process VARIANTBAM { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::variantbam=1.4.4a" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/variantbam:1.4.4a--h7d7f7ad_5" + } else { + container "quay.io/biocontainers/variantbam:1.4.4a--h7d7f7ad_5" + } + + input: + tuple val(meta), path(bam) + + output: + tuple val(meta), path("*.bam") , emit: bam + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + variant \\ + $bam \\ + -o ${prefix}.bam \\ + $options.args + + echo $VERSION > ${software}.version.txt + """ +} diff --git a/modules/variantbam/meta.yml b/modules/variantbam/meta.yml new file mode 100644 index 00000000..da0ff5e0 --- /dev/null +++ b/modules/variantbam/meta.yml @@ -0,0 +1,46 @@ +name: variantbam +description: Filtering, downsampling and profiling alignments in BAM/CRAM formats +keywords: + - filter + - bam + - subsample + - downsample + - downsample bam + - subsample bam +tools: + - variantbam: + description: Filtering and profiling of next-generational sequencing data using region-specific rules + homepage: https://github.com/walaj/VariantBam + documentation: https://github.com/walaj/VariantBam#table-of-contents + tool_dev_url: https://github.com/walaj/VariantBam + doi: 10.1093/bioinformatics/btw111 + licence: ['Apache2'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/CRAM file + pattern: "*.{bam,cram}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + - bam: + type: file + description: Filtered or downsampled BAM file + pattern: "*.{bam}" + +authors: + - "@bjohnnyd" diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml index 69e39d91..30de48cb 100644 --- a/tests/config/pytest_modules.yml +++ b/tests/config/pytest_modules.yml @@ -831,6 +831,10 @@ untar: - modules/untar/** - tests/modules/untar/** +variantbam: + - modules/variantbam/** + - tests/modules/variantbam/** + vcftools: - modules/vcftools/** - tests/modules/vcftools/** diff --git a/tests/modules/variantbam/main.nf b/tests/modules/variantbam/main.nf new file mode 100644 index 00000000..3ea09197 --- /dev/null +++ b/tests/modules/variantbam/main.nf @@ -0,0 +1,13 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { VARIANTBAM } from '../../../modules/variantbam/main.nf' addParams( options: [args: '-m 1'] ) + +workflow test_variantbam { + + input = [ [ id:'test', single_end:false ], + file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ] + + VARIANTBAM ( input ) +} diff --git a/tests/modules/variantbam/test.yml b/tests/modules/variantbam/test.yml new file mode 100644 index 00000000..51b824cd --- /dev/null +++ b/tests/modules/variantbam/test.yml @@ -0,0 +1,7 @@ +- name: variantbam test_variantbam + command: nextflow run tests/modules/variantbam -entry test_variantbam -c tests/config/nextflow.config + tags: + - variantbam + files: + - path: output/variantbam/test.bam + md5sum: fc08f065475d60b3b06ee32920564d4b