From a109e03e2eaa2a85fdf72bd96362b74f90a87a29 Mon Sep 17 00:00:00 2001 From: MaxUlysse Date: Wed, 24 Nov 2021 17:32:52 +0100 Subject: [PATCH] chores: update more modules --- .../qualimap/bamqc/functions.nf | 0 .../modules => local}/qualimap/bamqc/main.nf | 2 +- .../modules => local}/qualimap/bamqc/meta.yml | 0 .../modules/tabix/bgziptabix/functions.nf | 78 +++++++++++++++++++ .../nf-core/modules/tabix/bgziptabix/main.nf | 39 ++++++++++ .../nf-core/modules/tabix/bgziptabix/meta.yml | 45 +++++++++++ .../nf-core/modules/tabix/tabix/functions.nf | 78 +++++++++++++++++++ modules/nf-core/modules/tabix/tabix/main.nf | 37 +++++++++ modules/nf-core/modules/tabix/tabix/meta.yml | 41 ++++++++++ subworkflows/nf-core/ensemblvep_annotate.nf | 2 +- subworkflows/nf-core/markduplicates.nf | 4 +- subworkflows/nf-core/snpeff_annotate.nf | 2 +- 12 files changed, 323 insertions(+), 5 deletions(-) rename modules/{nf-core/modules => local}/qualimap/bamqc/functions.nf (100%) rename modules/{nf-core/modules => local}/qualimap/bamqc/main.nf (97%) rename modules/{nf-core/modules => local}/qualimap/bamqc/meta.yml (100%) create mode 100644 modules/nf-core/modules/tabix/bgziptabix/functions.nf create mode 100644 modules/nf-core/modules/tabix/bgziptabix/main.nf create mode 100644 modules/nf-core/modules/tabix/bgziptabix/meta.yml create mode 100644 modules/nf-core/modules/tabix/tabix/functions.nf create mode 100644 modules/nf-core/modules/tabix/tabix/main.nf create mode 100644 modules/nf-core/modules/tabix/tabix/meta.yml diff --git a/modules/nf-core/modules/qualimap/bamqc/functions.nf b/modules/local/qualimap/bamqc/functions.nf similarity index 100% rename from modules/nf-core/modules/qualimap/bamqc/functions.nf rename to modules/local/qualimap/bamqc/functions.nf diff --git a/modules/nf-core/modules/qualimap/bamqc/main.nf b/modules/local/qualimap/bamqc/main.nf similarity index 97% rename from modules/nf-core/modules/qualimap/bamqc/main.nf rename to modules/local/qualimap/bamqc/main.nf index d33f1e67bf..577a3c9e35 100644 --- a/modules/nf-core/modules/qualimap/bamqc/main.nf +++ b/modules/local/qualimap/bamqc/main.nf @@ -19,7 +19,7 @@ process QUALIMAP_BAMQC { } input: - tuple val(meta), path(bam) + tuple val(meta), path(bam), path(index) path gff val use_gff diff --git a/modules/nf-core/modules/qualimap/bamqc/meta.yml b/modules/local/qualimap/bamqc/meta.yml similarity index 100% rename from modules/nf-core/modules/qualimap/bamqc/meta.yml rename to modules/local/qualimap/bamqc/meta.yml diff --git a/modules/nf-core/modules/tabix/bgziptabix/functions.nf b/modules/nf-core/modules/tabix/bgziptabix/functions.nf new file mode 100644 index 0000000000..85628ee0eb --- /dev/null +++ b/modules/nf-core/modules/tabix/bgziptabix/functions.nf @@ -0,0 +1,78 @@ +// +// 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() +} + +// +// Extract name of module from process name using $task.process +// +def getProcessName(task_process) { + return task_process.tokenize(':')[-1] +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + + // Do not publish versions.yml unless running from pytest workflow + if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) { + return null + } + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${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)}/$args.filename" + } +} diff --git a/modules/nf-core/modules/tabix/bgziptabix/main.nf b/modules/nf-core/modules/tabix/bgziptabix/main.nf new file mode 100644 index 0000000000..e44a722671 --- /dev/null +++ b/modules/nf-core/modules/tabix/bgziptabix/main.nf @@ -0,0 +1,39 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process TABIX_BGZIPTABIX { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? 'bioconda::tabix=1.11' : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/tabix:1.11--hdfd78af_0" + } else { + container "quay.io/biocontainers/tabix:1.11--hdfd78af_0" + } + + input: + tuple val(meta), path(input) + + output: + tuple val(meta), path("*.gz"), path("*.tbi"), emit: tbi + path "versions.yml" , emit: versions + + script: + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + bgzip -c $options.args $input > ${prefix}.gz + tabix $options.args2 ${prefix}.gz + + cat <<-END_VERSIONS > versions.yml + ${getProcessName(task.process)}: + ${getSoftwareName(task.process)}: \$(echo \$(tabix -h 2>&1) | sed 's/^.*Version: //; s/ .*\$//') + END_VERSIONS + """ +} diff --git a/modules/nf-core/modules/tabix/bgziptabix/meta.yml b/modules/nf-core/modules/tabix/bgziptabix/meta.yml new file mode 100644 index 0000000000..f2aed84d13 --- /dev/null +++ b/modules/nf-core/modules/tabix/bgziptabix/meta.yml @@ -0,0 +1,45 @@ +name: tabix_bgziptabix +description: bgzip a sorted tab-delimited genome file and then create tabix index +keywords: + - bgzip + - compress + - index + - tabix + - vcf +tools: + - tabix: + description: Generic indexer for TAB-delimited genome position files. + homepage: https://www.htslib.org/doc/tabix.html + documentation: https://www.htslib.org/doc/tabix.1.html + doi: 10.1093/bioinformatics/btq671 + licence: ['MIT'] +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - tab: + type: file + description: TAB-delimited genome position file + pattern: "*.{bed,gff,sam,vcf}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - gz: + type: file + description: Output compressed file + pattern: "*.{gz}" + - tbi: + type: file + description: tabix index file + pattern: "*.{gz.tbi}" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@maxulysse" diff --git a/modules/nf-core/modules/tabix/tabix/functions.nf b/modules/nf-core/modules/tabix/tabix/functions.nf new file mode 100644 index 0000000000..85628ee0eb --- /dev/null +++ b/modules/nf-core/modules/tabix/tabix/functions.nf @@ -0,0 +1,78 @@ +// +// 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() +} + +// +// Extract name of module from process name using $task.process +// +def getProcessName(task_process) { + return task_process.tokenize(':')[-1] +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + + // Do not publish versions.yml unless running from pytest workflow + if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) { + return null + } + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${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)}/$args.filename" + } +} diff --git a/modules/nf-core/modules/tabix/tabix/main.nf b/modules/nf-core/modules/tabix/tabix/main.nf new file mode 100644 index 0000000000..1574c0b558 --- /dev/null +++ b/modules/nf-core/modules/tabix/tabix/main.nf @@ -0,0 +1,37 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process TABIX_TABIX { + tag "$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::tabix=1.11' : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/tabix:1.11--hdfd78af_0" + } else { + container "quay.io/biocontainers/tabix:1.11--hdfd78af_0" + } + + input: + tuple val(meta), path(tab) + + output: + tuple val(meta), path("*.tbi"), emit: tbi + path "versions.yml" , emit: versions + + script: + """ + tabix $options.args $tab + + cat <<-END_VERSIONS > versions.yml + ${getProcessName(task.process)}: + ${getSoftwareName(task.process)}: \$(echo \$(tabix -h 2>&1) | sed 's/^.*Version: //; s/ .*\$//') + END_VERSIONS + """ +} diff --git a/modules/nf-core/modules/tabix/tabix/meta.yml b/modules/nf-core/modules/tabix/tabix/meta.yml new file mode 100644 index 0000000000..2e37c4ff90 --- /dev/null +++ b/modules/nf-core/modules/tabix/tabix/meta.yml @@ -0,0 +1,41 @@ +name: tabix_tabix +description: create tabix index from a sorted bgzip tab-delimited genome file +keywords: + - index + - tabix + - vcf +tools: + - tabix: + description: Generic indexer for TAB-delimited genome position files. + homepage: https://www.htslib.org/doc/tabix.html + documentation: https://www.htslib.org/doc/tabix.1.html + doi: 10.1093/bioinformatics/btq671 + licence: ['MIT'] +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - tab: + type: file + description: TAB-delimited genome position file compressed with bgzip + pattern: "*.{bed.gz,gff.gz,sam.gz,vcf.gz}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - tbi: + type: file + description: tabix index file + pattern: "*.{tbi}" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@joseespinosa" + - "@drpatelh" + - "@maxulysse" diff --git a/subworkflows/nf-core/ensemblvep_annotate.nf b/subworkflows/nf-core/ensemblvep_annotate.nf index 9b1cbbc951..67cd0e116f 100644 --- a/subworkflows/nf-core/ensemblvep_annotate.nf +++ b/subworkflows/nf-core/ensemblvep_annotate.nf @@ -13,7 +13,7 @@ include { ENSEMBLVEP } from '../../modules/nf-core/modules/ensemblvep/main' addP vep_tag: params.vep_tag ) -include { TABIX_BGZIPTABIX } from '../../modules/nf-core/modules/tabix/bgziptabix/main' addParams(options: params.bgziptabix_vep_options) +include { TABIX_BGZIPTABIX } from '../../modules/local/tabix/bgziptabix/main' addParams(options: params.bgziptabix_vep_options) workflow ENSEMBLVEP_ANNOTATE { take: diff --git a/subworkflows/nf-core/markduplicates.nf b/subworkflows/nf-core/markduplicates.nf index 1b85ba9ba1..670886b63b 100644 --- a/subworkflows/nf-core/markduplicates.nf +++ b/subworkflows/nf-core/markduplicates.nf @@ -14,7 +14,7 @@ params.samtools_view_options = [:] include { GATK4_ESTIMATELIBRARYCOMPLEXITY } from '../../modules/local/gatk4/estimatelibrarycomplexity/main' addParams(options: params.estimatelibrarycomplexity_options) include { GATK4_MARKDUPLICATES } from '../../modules/local/gatk4/markduplicates/main' addParams(options: params.markduplicates_options) include { GATK4_MARKDUPLICATES_SPARK } from '../../modules/local/gatk4/markduplicatesspark/main' addParams(options: params.markduplicatesspark_options) -include { QUALIMAP_BAMQC } from '../../modules/nf-core/modules/qualimap/bamqc/main' addParams(options: params.qualimap_bamqc_options) +include { QUALIMAP_BAMQC } from '../../modules/local/qualimap/bamqc/main' addParams(options: params.qualimap_bamqc_options) include { SAMTOOLS_INDEX } from '../../modules/local/samtools/index/main' addParams(options: params.samtools_index_options) include { SAMTOOLS_STATS } from '../../modules/nf-core/modules/samtools/stats/main' addParams(options: params.samtools_stats_options) include { SAMTOOLS_VIEW as SAMTOOLS_BAM_TO_CRAM } from '../../modules/local/samtools/view/main' addParams(options: params.samtools_view_options) @@ -94,7 +94,7 @@ workflow MARKDUPLICATES { //After bamqc finishes, convert to cram for further analysis samtools_stats = Channel.empty() if (!skip_samtools) { - SAMTOOLS_STATS(cram_markduplicates, fasta, fasta_fai) + SAMTOOLS_STATS(cram_markduplicates, fasta) samtools_stats = SAMTOOLS_STATS.out.stats ch_versions = ch_versions.mix(SAMTOOLS_STATS.out.versions.first()) diff --git a/subworkflows/nf-core/snpeff_annotate.nf b/subworkflows/nf-core/snpeff_annotate.nf index 8589400b9a..2fbe4b21f6 100644 --- a/subworkflows/nf-core/snpeff_annotate.nf +++ b/subworkflows/nf-core/snpeff_annotate.nf @@ -13,7 +13,7 @@ include { SNPEFF } from '../../modules/nf-core/modules/snpeff/main' addParams( use_cache: params.use_cache ) -include { TABIX_BGZIPTABIX } from '../../modules/nf-core/modules/tabix/bgziptabix/main' addParams(options: params.bgziptabix_snpeff_options) +include { TABIX_BGZIPTABIX } from '../../modules/local/tabix/bgziptabix/main' addParams(options: params.bgziptabix_snpeff_options) workflow SNPEFF_ANNOTATE { take: