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 <drpatelh@users.noreply.github.com>
2024-12-22 02:58:17 +00:00 · 2021-07-22 16:19:42 +02:00 · 2021-07-22 16:19:42 +02:00 · 3cabc95d0e
commit 3cabc95d0e
parent 553f51d6bf
6 changed files with 302 additions and 0 deletions
--- a/modules/arriba/functions.nf
+++ b/modules/arriba/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)}/$args.filename"
+        }
+    }
+}
--- a/modules/arriba/main.nf
+++ b/modules/arriba/main.nf
@ -0,0 +1,47 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process ARRIBA {
+    tag "$meta.id"
+    label 'process_medium'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::arriba=2.1.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/arriba:2.1.0--h3198e80_1"
+    } else {
+        container "quay.io/biocontainers/arriba:2.1.0--h3198e80_1"
+    }
+
+    input:
+    tuple val(meta), path(bam)
+    path fasta
+    path gtf
+
+    output:
+    tuple val(meta), path("*.fusions.tsv")          , emit: fusions
+    tuple val(meta), path("*.fusions.discarded.tsv"), emit: fusions_fail
+    path "*.version.txt"                            , emit: version
+
+    script:
+    def software  = getSoftwareName(task.process)
+    def prefix    = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def blacklist = (options.args.contains('-b')) ? '' : '-f blacklist'
+    """
+    arriba \\
+        -x $bam \\
+        -a $fasta \\
+        -g $gtf \\
+        -o ${prefix}.fusions.tsv \\
+        -O ${prefix}.fusions.discarded.tsv \\
+        $blacklist \\
+        $options.args
+
+    echo \$(arriba -h | grep 'Version:' 2>&1) |  sed 's/Version:\s//' > ${software}.version.txt
+    """
+}
--- a/modules/arriba/meta.yml
+++ b/modules/arriba/meta.yml
@ -0,0 +1,54 @@
+name: arriba
+description: Arriba is a command-line tool for the detection of gene fusions from RNA-Seq data.
+keywords:
+  - fusion
+  - arriba
+tools:
+  - arriba:
+      description: Fast and accurate gene fusion detection from RNA-Seq data
+      homepage: https://github.com/suhrig/arriba
+      documentation: https://arriba.readthedocs.io/en/latest/
+      tool_dev_url: https://github.com/suhrig/arriba
+      doi: "10.1101/gr.257246.119"
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - fasta:
+      type: file
+      description: Assembly FASTA file
+      pattern: "*.{fasta}"
+  - gtf:
+      type: file
+      description: Annotation GTF file
+      pattern: "*.{gtf}"
+
+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}"
+  - fusions:
+      type: file
+      description: File contains fusions which pass all of Arriba's filters.
+      pattern: "*.{fusions.tsv}"
+  - fusions_fail:
+      type: file
+      description: File contains fusions that Arriba classified as an artifact or that are also observed in healthy tissue.
+      pattern: "*.{fusions.discarded.tsv}"
+
+authors:
+  - "@praveenraj2018"
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@ -10,6 +10,10 @@ allelecounter:
  - modules/allelecounter/**
  - tests/modules/allelecounter/**

+arriba:
+  - modules/arriba/**
+  - tests/modules/arriba/**
+
 artic/guppyplex:
  - modules/artic/guppyplex/**
  - tests/modules/artic/guppyplex/**
--- a/tests/modules/arriba/main.nf
+++ b/tests/modules/arriba/main.nf
@ -0,0 +1,36 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { STAR_GENOMEGENERATE   } from '../../../modules/star/genomegenerate/main.nf' addParams( options: [args: '--genomeSAindexNbases 11'] )
+include { STAR_ALIGN            } from '../../../modules/star/align/main.nf'          addParams( options: [args: '--readFilesCommand zcat --outSAMtype BAM Unsorted --outSAMunmapped Within --outBAMcompression 0 --outFilterMultimapNmax 50 --peOverlapNbasesMin 10 --alignSplicedMateMapLminOverLmate 0.5 --alignSJstitchMismatchNmax 5 -1 5 5 --chimSegmentMin 10 --chimOutType WithinBAM HardClip --chimJunctionOverhangMin 10 --chimScoreDropMax 30 --chimScoreJunctionNonGTAG 0 --chimScoreSeparation 1 --chimSegmentReadGapMax 3 --chimMultimapNmax 50'] )
+include { ARRIBA                } from '../../../modules/arriba/main.nf'              addParams( options: [:] )
+
+workflow test_arriba_single_end {
+
+    input = [ [ id:'test', single_end:true ], // meta map
+                [   file(params.test_data['homo_sapiens']['illumina']['test_rnaseq_1_fastq_gz'], checkIfExists: true) ]
+            ]
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
+
+    STAR_GENOMEGENERATE ( fasta, gtf )
+    STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf )
+    ARRIBA ( STAR_ALIGN.out.bam, fasta, gtf )
+}
+
+workflow test_arriba_paired_end {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+                [   file(params.test_data['homo_sapiens']['illumina']['test_rnaseq_1_fastq_gz'], checkIfExists: true),
+                    file(params.test_data['homo_sapiens']['illumina']['test_rnaseq_2_fastq_gz'], checkIfExists: true) ]
+            ]
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
+
+    STAR_GENOMEGENERATE ( fasta, gtf )
+    STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf )
+    ARRIBA ( STAR_ALIGN.out.bam, fasta, gtf )
+}
--- a/tests/modules/arriba/test.yml
+++ b/tests/modules/arriba/test.yml
@ -0,0 +1,93 @@
+- name: arriba test_arriba_single_end
+  command: nextflow run tests/modules/arriba -entry test_arriba_single_end -c tests/config/nextflow.config
+  tags:
+    - arriba
+  files:
+    - path: output/arriba/test.fusions.discarded.tsv
+      md5sum: cad8c215b938d1e45b747a5b7898a4c2
+    - path: output/arriba/test.fusions.tsv
+      md5sum: 7c3383f7eb6d79b84b0bd30a7ef02d70
+    - path: output/index/star/Genome
+      md5sum: a654229fbca6071dcb6b01ce7df704da
+    - path: output/index/star/Log.out
+    - path: output/index/star/SA
+      md5sum: 8c3edc46697b72c9e92440d4cf43506c
+    - path: output/index/star/SAindex
+      md5sum: 9f085c626553b1c52f2827421972ac10
+    - path: output/index/star/chrLength.txt
+      md5sum: c81f40f27e72606d7d07097c1d56a5b5
+    - path: output/index/star/chrName.txt
+      md5sum: 5ae68a67b70976ee95342a7451cb5af1
+    - path: output/index/star/chrNameLength.txt
+      md5sum: b190587cae0531f3cf25552d8aa674db
+    - path: output/index/star/chrStart.txt
+      md5sum: 8d3291e6bcdbe9902fbd7c887494173f
+    - path: output/index/star/exonGeTrInfo.tab
+      md5sum: d04497f69d6ef889efd4d34fe63edcc4
+    - path: output/index/star/exonInfo.tab
+      md5sum: 0d560290fab688b7268d88d5494bf9fe
+    - path: output/index/star/geneInfo.tab
+      md5sum: 8b608537307443ffaee4927d2b428805
+    - path: output/index/star/genomeParameters.txt
+      md5sum: 9e42067b1ec70b773257529230dd7b3a
+    - path: output/index/star/sjdbInfo.txt
+      md5sum: 5690ea9d9f09f7ff85b7fd47bd234903
+    - path: output/index/star/sjdbList.fromGTF.out.tab
+      md5sum: 8760c33e966dad0b39f440301ebbdee4
+    - path: output/index/star/sjdbList.out.tab
+      md5sum: 9e4f991abbbfeb3935a2bb21b9e258f1
+    - path: output/index/star/transcriptInfo.tab
+      md5sum: 0c3a5adb49d15e5feff81db8e29f2e36
+    - path: output/star/test.Aligned.out.bam
+      md5sum: 29c99195dcc79ff4df1f754ff16aac78
+    - path: output/star/test.Log.final.out
+    - path: output/star/test.Log.out
+    - path: output/star/test.Log.progress.out
+    - path: output/star/test.SJ.out.tab
+
+- name: arriba test_arriba_paired_end
+  command: nextflow run tests/modules/arriba -entry test_arriba_paired_end -c tests/config/nextflow.config
+  tags:
+    - arriba
+  files:
+    - path: output/arriba/test.fusions.discarded.tsv
+      md5sum: 85e36c887464e4deaa65f45174d3b8fd
+    - path: output/arriba/test.fusions.tsv
+      md5sum: 7c3383f7eb6d79b84b0bd30a7ef02d70
+    - path: output/index/star/Genome
+      md5sum: a654229fbca6071dcb6b01ce7df704da
+    - path: output/index/star/Log.out
+    - path: output/index/star/SA
+      md5sum: 8c3edc46697b72c9e92440d4cf43506c
+    - path: output/index/star/SAindex
+      md5sum: 9f085c626553b1c52f2827421972ac10
+    - path: output/index/star/chrLength.txt
+      md5sum: c81f40f27e72606d7d07097c1d56a5b5
+    - path: output/index/star/chrName.txt
+      md5sum: 5ae68a67b70976ee95342a7451cb5af1
+    - path: output/index/star/chrNameLength.txt
+      md5sum: b190587cae0531f3cf25552d8aa674db
+    - path: output/index/star/chrStart.txt
+      md5sum: 8d3291e6bcdbe9902fbd7c887494173f
+    - path: output/index/star/exonGeTrInfo.tab
+      md5sum: d04497f69d6ef889efd4d34fe63edcc4
+    - path: output/index/star/exonInfo.tab
+      md5sum: 0d560290fab688b7268d88d5494bf9fe
+    - path: output/index/star/geneInfo.tab
+      md5sum: 8b608537307443ffaee4927d2b428805
+    - path: output/index/star/genomeParameters.txt
+      md5sum: 9e42067b1ec70b773257529230dd7b3a
+    - path: output/index/star/sjdbInfo.txt
+      md5sum: 5690ea9d9f09f7ff85b7fd47bd234903
+    - path: output/index/star/sjdbList.fromGTF.out.tab
+      md5sum: 8760c33e966dad0b39f440301ebbdee4
+    - path: output/index/star/sjdbList.out.tab
+      md5sum: 9e4f991abbbfeb3935a2bb21b9e258f1
+    - path: output/index/star/transcriptInfo.tab
+      md5sum: 0c3a5adb49d15e5feff81db8e29f2e36
+    - path: output/star/test.Aligned.out.bam
+      md5sum: d724ca90a102347b9c5052a33ea4d308
+    - path: output/star/test.Log.final.out
+    - path: output/star/test.Log.out
+    - path: output/star/test.Log.progress.out
+    - path: output/star/test.SJ.out.tab