Add TIDDIT cov (#822)

* added template for tiddit/cov

* test finished

* quick fix to meta info

* Apply suggestions from code review

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* applying suggestions

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

modules/tiddit/cov/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+    // Do not publish versions.yml unless running from pytest workflow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"
+    }
+}

modules/tiddit/cov/main.nf

@@ -0,0 +1,49 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process TIDDIT_COV {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${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::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
+
+    output:
+    tuple val(meta), path("*.tab"), optional: true, emit: cov
+    tuple val(meta), path("*.wig"), optional: true, emit: wig
+
+    path  "versions.yml"          , emit: versions
+
+    script:
+    def software  = getSoftwareName(task.process)
+    def prefix    = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+
+    def reference = fasta ? "--ref $fasta" : ""
+    """
+    tiddit \\
+        --cov \\
+        -o $prefix \\
+        $options.args \\
+        --bam $bam \\
+        $reference
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$(tiddit 2>&1) | sed 's/^.*TIDDIT-//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/tiddit/cov/meta.yml

@@ -0,0 +1,52 @@
+name: tiddit_cov
+description: Computes the coverage of different regions from the bam file.
+keywords:
+  - coverage
+  - bam
+  - statistics
+  - chromosomal rearrangements
+tools:
+  - tiddit:
+      description: TIDDIT - structural variant calling.
+      homepage: https://github.com/SciLifeLab/TIDDIT
+      documentation: https://github.com/SciLifeLab/TIDDIT/blob/master/README.md
+      doi: "10.12688/f1000research.11168.1"
+      licence: ["GPL v3"]
+
+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}"
+  - fasta:
+      type: file
+      description: |
+        Reference genome file. Only needed when passing in CRAM instead of BAM.
+        If not using CRAM, please pass an empty file instead.
+      pattern: "*.fasta"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - cov:
+      type: file
+      description: The coverage of different regions. Optional.
+      pattern: "*.tab"
+  - wig:
+      type: file
+      description: The coverage of different regions in WIG format. Optional.
+      pattern: "*.wig"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@projectoriented"

tests/config/pytest_modules.yml

@@ -1039,6 +1039,10 @@ tabix/tabix:
   - modules/tabix/tabix/**
   - tests/modules/tabix/tabix/**
 
+tiddit/cov:
+  - modules/tiddit/cov/**
+  - tests/modules/tiddit/cov/**
+
 tiddit/sv:
   - modules/tiddit/sv/**
   - tests/modules/tiddit/sv/**

tests/modules/tiddit/cov/main.nf

@@ -0,0 +1,23 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { TIDDIT_COV } from '../../../../modules/tiddit/cov/main.nf' addParams( options: [:] )
+
+workflow test_tiddit_cov {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ]
+
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+
+    TIDDIT_COV ( input, fasta )
+}
+
+workflow test_tiddit_cov_no_ref {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ]
+
+    TIDDIT_COV ( input, [] )
+}

tests/modules/tiddit/cov/test.yml

@@ -0,0 +1,17 @@
+- name: tiddit cov test_tiddit_cov
+  command: nextflow run tests/modules/tiddit/cov -entry test_tiddit_cov -c tests/config/nextflow.config
+  tags:
+    - tiddit
+    - tiddit/cov
+  files:
+    - path: output/tiddit/test.tab
+      md5sum: f7974948f809f94879d8a60b726194f5
+
+- name: tiddit cov test_tiddit_cov_no_ref
+  command: nextflow run tests/modules/tiddit/cov -entry test_tiddit_cov_no_ref -c tests/config/nextflow.config
+  tags:
+    - tiddit
+    - tiddit/cov
+  files:
+    - path: output/tiddit/test.tab
+      md5sum: f7974948f809f94879d8a60b726194f5