Merge pull request #82 from abhi18av/master

Add multiqc module

.github/workflows/multiqc.yml

@@ -0,0 +1,38 @@
+name: multiqc
+on:
+  push:
+    paths:
+      - software/multiqc/**
+      - .github/workflows/multiqc.yml
+      - tests
+  pull_request:
+    paths:
+      - software/multiqc/**
+      - .github/workflows/multiqc.yml
+      - tests
+
+jobs:
+  ci_test:
+    runs-on: ubuntu-latest
+    env:
+      NXF_ANSI_LOG: false
+    steps:
+
+    - uses: actions/checkout@v2
+
+    - name: Install Nextflow
+      run: |
+        export NXF_VER="20.07.1"
+        wget -qO- get.nextflow.io | bash
+        sudo mv nextflow /usr/local/bin/
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: "3.x"
+    - name: Install dependencies
+      run: python -m pip install --upgrade pip pytest-workflow
+
+    # Test the module
+    - run: pytest --tag multiqc --symlink --wt 2
+

software/multiqc/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/multiqc/main.nf

@@ -0,0 +1,31 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process MULTIQC {
+    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: '') }
+
+    conda     (params.enable_conda ? "bioconda::multiqc=1.9" : null)
+    container "quay.io/biocontainers/multiqc:1.9--pyh9f0ad1d_0"
+
+    input:
+    path multiqc_files
+
+    output:
+    path "*multiqc_report.html", emit: report
+    path "*_data"              , emit: data
+    path "*_plots"             , optional:true, emit: plots
+    path "*.version.txt"       , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    """
+    multiqc -f $options.args .
+    multiqc --version | sed -e "s/multiqc, version //g" > ${software}.version.txt
+    """
+}

software/multiqc/meta.yml

@@ -0,0 +1,55 @@
+name: MultiQC
+description: Aggregate results from bioinformatics analyses across many samples into a single report
+keywords:
+    - QC
+    - bioinformatics tools
+    - Beautiful stand-alone HTML report
+tools:
+    - multiqc:
+        description: |
+            MultiQC searches a given directory for analysis logs and compiles a HTML report.
+            It's a general use tool, perfect for summarising the output from numerous bioinformatics tools.
+        homepage: https://multiqc.info/
+        documentation: https://multiqc.info/docs/
+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
+input:
+    - multiqc_files:
+        type: file
+        description: |
+            List of reports / files recognised by MultiQC, for example the html and zip output of FastQC
+output:
+    - report:
+        type: file
+        description: MultiQC report file
+        pattern: "multiqc_report.html"
+    - data:
+        type: dir
+        description: MultiQC data dir
+        pattern: "multiqc_data"
+    - plots:
+        type: file
+        description: Plots created by MultiQC
+        pattern: "*_data"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@abhi18av"
+    - "@bunop"
+    - "@drpatelh"

tests/software/fastqc/main.nf

@@ -23,11 +23,16 @@ workflow test_single_end {
 workflow test_paired_end {
 
     def input = []
-    input = [ [ id:'test', single_end:false ], // meta map
-              [ file("${launchDir}/tests/data/fastq/rna/test_R1.fastq.gz", checkIfExists: true),
-                file("${launchDir}/tests/data/fastq/rna/test_R2.fastq.gz", checkIfExists: true) ] ]
+    input = [[id: 'test', single_end: false], // meta map
+             [file("${launchDir}/tests/data/fastq/rna/test_R1.fastq.gz", checkIfExists: true),
+              file("${launchDir}/tests/data/fastq/rna/test_R2.fastq.gz", checkIfExists: true)]]
+
+    FASTQC_PE(input)
+
+    emit:
+    html = FASTQC_PE.out.html
+    zip  = FASTQC_PE.out.zip
 
-    FASTQC_PE ( input )
 }
 
 // TODO Test e2e

tests/software/multiqc/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MULTIQC } from '../../../software/multiqc/main.nf' addParams(options: [publish_dir: 'test_multiqc'])
+include { test_paired_end } from '../fastqc/main.nf' addParams(options: [publish_dir: 'test_paired_end'])
+
+workflow test_multiqc {
+    test_paired_end()
+
+    input = [
+        test_paired_end.out.zip.collect { it[1] }.ifEmpty([])
+    ]
+
+    MULTIQC(*input)
+}

tests/software/multiqc/test.yml

@@ -0,0 +1,7 @@
+- name: Run multiqc test workflow
+  command: nextflow run ./tests/software/multiqc/ -profile docker -entry test_multiqc -c tests/config/nextflow.config
+  tags:
+    - multiqc
+  files:
+    - path: output/test_multiqc/multiqc_report.html
+