Merge pull request #252 from MaxUlysse/master_tiddit

New module: tiddit

.github/filters.yml

@@ -172,10 +172,6 @@ gunzip:
   - software/gunzip/**
   - tests/software/gunzip/**
 
-tabix_tabix:
-  - software/tabix/tabix/**
-  - tests/software/tabix/tabix/**
-
 ivar_consensus:
   - software/ivar/consensus/**
   - tests/software/ivar/consensus/**
@@ -305,6 +301,14 @@ tabix_bgzip:
   - software/tabix/bgzip/**
   - tests/software/tabix/bgzip/**
 
+tabix_tabix:
+  - software/tabix/tabix/**
+  - tests/software/tabix/tabix/**
+
+tiddit_sv:
+  - software/tiddit/sv/**
+  - tests/software/tiddit/sv/**
+
 tool_subtool:
   - software/TOOL/SUBTOOL/**
   - tests/software/TOOL/SUBTOOL/**

software/tiddit/sv/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"
+        }
+    }
+}

software/tiddit/sv/main.nf

@@ -0,0 +1,45 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process TIDDIT_SV {
+    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::tiddit=2.12.1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/tiddit:2.12.1--py38h1773678_0"
+    } else {
+        container "quay.io/biocontainers/tiddit:2.12.1--py38h1773678_0"
+    }
+
+    input:
+    tuple val(meta), path(bam)
+    path fasta
+    path fai
+
+    output:
+    tuple val(meta), path("*.vcf"),         emit: vcf
+    tuple val(meta), path("*.ploidy.tab"),  emit: ploidy
+    tuple val(meta), path("*.signals.tab"), emit: signals
+    path  "*.version.txt",                  emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def output = options.suffix ? "${meta.id}.${options.suffix}" : "${meta.id}"
+    def reference = fasta == "dummy_file.txt" ? "--ref $fasta" : ""
+    """
+    tiddit \\
+        --sv $options.args \\
+        --bam $bam \\
+        $reference \\
+        -o $output
+
+    echo \$(tiddit -h 2>&1) | sed 's/^.*Version: //; s/(.*\$//' > ${software}.version.txt
+    """
+}

software/tiddit/sv/meta.yml

@@ -0,0 +1,71 @@
+name: tiddit_sv
+description: Identify chromosomal rearrangements.
+keywords:
+    - structural
+    - variants
+    - vcf
+tools:
+    - sv:
+        description:  Search for structural variants.
+        homepage: https://github.com/SciLifeLab/TIDDIT
+        documentation: https://github.com/SciLifeLab/TIDDIT/blob/master/README.md
+        doi: 10.12688/f1000research.11168.1
+params:
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - 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 ]
+    - fasta:
+        type: file
+        description: Input FASTA file
+        pattern: "*.{fasta,fa}"
+    - fai:
+        type: file
+        description: FASTA index file
+        pattern: "*.{fai}"
+output:
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - vcf:
+        type: file
+        description: vcf
+        pattern: "*.{vcf}"
+    - ploidy:
+        type: file
+        description: tab
+        pattern: "*.{ploidy.tab}"
+    - signals:
+        type: file
+        description: tab
+        pattern: "*.{signals.tab}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@maxulysse"

tests/software/tiddit/sv/main.nf

@@ -0,0 +1,30 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { TIDDIT_SV }      from '../../../../software/tiddit/sv/main.nf'      addParams( options: [:] )
+include { SAMTOOLS_FAIDX } from '../../../../software/samtools/faidx/main.nf' addParams( options: [:] )
+
+workflow test_tiddit_sv {
+    def input = []
+    def fasta = file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa", checkIfExists: true)
+
+    input = [ [ id:'test' ], // meta map
+              [ file("${launchDir}/tests/data/bam/test.paired_end.sorted.bam", checkIfExists: true) ] ]
+
+    SAMTOOLS_FAIDX ( fasta )
+
+    TIDDIT_SV ( input, fasta, SAMTOOLS_FAIDX.out.fai )
+}
+
+workflow test_tiddit_sv_no_ref {
+    def input = []
+    def dummy_file  = file("${launchDir}/tests/data/dummy/dummy_file.txt", checkIfExists: true)
+    def dummy_file2 = file("${launchDir}/tests/data/dummy/dummy_file2.txt", checkIfExists: true)
+
+    input = [ [ id:'test' ], // meta map
+              [ file("${launchDir}/tests/data/bam/test.paired_end.sorted.bam", checkIfExists: true) ] ]
+
+
+    TIDDIT_SV ( input, dummy_file, dummy_file2 )
+}

tests/software/tiddit/sv/test.yml

@@ -0,0 +1,27 @@
+- name: tiddit sv
+  command: nextflow run ./tests/software/tiddit/sv -entry test_tiddit_sv -c tests/config/nextflow.config
+  tags:
+    - tiddit
+    - tiddit_sv
+    - vcf
+  files:
+    - path: output/tiddit/test.ploidy.tab
+      md5sum: 207bd22e75de82160f98bedc2d3d262d
+    - path: output/tiddit/test.signals.tab
+      md5sum: 67e041b737fe0fe1a33119c3109e9eff
+    - path: output/tiddit/test.vcf
+      md5sum: 24e749d49a2e91acdfb3bc13c1c6e51d
+
+- name: tiddit sv no ref
+  command: nextflow run ./tests/software/tiddit/sv -entry test_tiddit_sv_no_ref -c tests/config/nextflow.config
+  tags:
+    - tiddit
+    - tiddit_sv
+    - vcf
+  files:
+    - path: output/tiddit/test.ploidy.tab
+      md5sum: 207bd22e75de82160f98bedc2d3d262d
+    - path: output/tiddit/test.signals.tab
+      md5sum: 67e041b737fe0fe1a33119c3109e9eff
+    - path: output/tiddit/test.vcf
+      md5sum: 24e749d49a2e91acdfb3bc13c1c6e51d