Merge pull request #131 from KevinMenden/fastp-module

Adding fastp module

.github/workflows/fastp.yml

@@ -0,0 +1,40 @@
+name: fastp
+on:
+  push:
+    paths:
+      - software/fastp/**
+      - .github/workflows/fastp.yml
+      - tests
+  pull_request:
+    paths:
+      - software/fastp/**
+      - .github/workflows/fastp.yml
+      - tests
+
+jobs:
+  ci_test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        nxf_version: [20.11.0-edge]
+    env:
+      NXF_ANSI_LOG: false
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Install Nextflow
+        env:
+          NXF_VER: ${{ matrix.nxf_version }}
+        run: |
+          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 fastp --symlink --wt 2

software/fastp/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/fastp/main.nf

@@ -0,0 +1,72 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process FASTP {
+    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::fastp=0.20.1' : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container 'https://depot.galaxyproject.org/singularity/fastp:0.20.1--h8b12597_0'
+    } else {
+        container 'quay.io/biocontainers/fastp:0.20.1--h8b12597_0'
+    }
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path('*.trim.fastq.gz'), emit: reads
+    tuple val(meta), path('*.json')         , emit: json
+    tuple val(meta), path('*.html')         , emit: html
+    tuple val(meta), path('*.log')          , emit: log
+    path '*.version.txt'                    , emit: version
+    tuple val(meta), path('*.fail.fastq.gz'), optional:true, emit: reads_fail
+
+    script:
+    // Added soft-links to original fastqs for consistent naming in MultiQC
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    if (meta.single_end) {
+        def fail_fastq = params.save_trimmed_fail ? "--failed_out ${prefix}.fail.fastq.gz" : ''
+        """
+        [ ! -f  ${prefix}.fastq.gz ] && ln -s $reads ${prefix}.fastq.gz
+        fastp \\
+            --in1 ${prefix}.fastq.gz \\
+            --out1 ${prefix}.trim.fastq.gz \\
+            --thread $task.cpus \\
+            --json ${prefix}.fastp.json \\
+            --html ${prefix}.fastp.html \\
+            $fail_fastq \\
+            $options.args \\
+            2> ${prefix}.fastp.log
+        echo \$(fastp --version 2>&1) | sed -e "s/fastp //g" > ${software}.version.txt
+        """
+    } else {
+        def fail_fastq = params.save_trimmed_fail ? "--unpaired1 ${prefix}_1.fail.fastq.gz --unpaired2 ${prefix}_2.fail.fastq.gz" : ''
+        """
+        [ ! -f  ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz
+        [ ! -f  ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz
+        fastp \\
+            --in1 ${prefix}_1.fastq.gz \\
+            --in2 ${prefix}_2.fastq.gz \\
+            --out1 ${prefix}_1.trim.fastq.gz \\
+            --out2 ${prefix}_2.trim.fastq.gz \\
+            --json ${prefix}.fastp.json \\
+            --html ${prefix}.fastp.html \\
+            $fail_fastq \\
+            --thread $task.cpus \\
+            --detect_adapter_for_pe \\
+            $options.args \\
+            2> ${prefix}.fastp.log
+
+        echo \$(fastp --version 2>&1) | sed -e "s/fastp //g" > ${software}.version.txt
+        """
+    }
+}

software/fastp/meta.yml

@@ -0,0 +1,79 @@
+name: fastp
+description: Perform adapter/quality trimming on sequencing reads
+keywords:
+  - trimming
+  - quality control
+  - fastq
+tools:
+  - fastq:
+      description: |
+        A tool designed to provide fast all-in-one preprocessing for FastQ files. This tool is developed in C++ with multithreading supported to afford high performance.
+      documentation: https://github.com/OpenGene/fastp
+      doi: https://doi.org/10.1093/bioinformatics/bty560
+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 ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: The trimmed/modified fastq reads
+      pattern: "*trim.fastq.gz"
+  - json:
+      type: file
+      description: Results in JSON format
+      pattern: "*.json"
+  - html:
+      type: file
+      description: Results in HTML format
+      pattern: "*.thml"
+  - log:
+      type: file
+      description: fastq log file
+      pattern: "*.log"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - reads_fail:
+      type: file
+      description: Reads the failed the preprocessing
+      pattern: "*fail.fastq.gz"
+authors:
+  - "@drpatelh"
+  - "@kevinmenden"

tests/software/fastp/main.nf

@@ -0,0 +1,30 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { FASTP } from '../../../software/fastp/main.nf'  addParams( options: [:] )
+
+/*
+ * Test with single-end data
+ */
+workflow test_fastp_se {
+    def input = []
+    input = [ [ id:'test', single_end:true ], // meta map
+              [ file("${launchDir}/tests/data/fastq/rna/test_single_end.fastq.gz", checkIfExists: true) ] ]
+
+    FASTP( input )
+}
+
+/*
+ * Test with paired-end data
+ */
+
+workflow test_fastp_pe {
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file("${launchDir}/tests/data/fastq/rna/test_R1.fastq.gz", checkIfExists: true),
+                file("${launchDir}/tests/data/fastq/rna/test_R2.fastq.gz", checkIfExists: true) ] ]
+
+    FASTP( input )
+}
+

tests/software/fastp/test.yml

@@ -0,0 +1,27 @@
+- name: fastp_se
+  command: nextflow run ./tests/software/fastp -profile docker -entry test_fastp_se -c ./tests/config/nextflow.config
+  tags:
+    - fastp
+    - fastp_se
+  files:
+    - path: ./output/fastp/test.fastp.json
+      md5sum: b81d53bfa5c1553bed89f6475edcf437
+    - path: ./output/fastp/test.trim.fastq.gz
+      md5sum: 2f5516df477b123e3f78adb67effa3bc
+    - path: ./output/fastp/test.fastp.log
+    - path: ./output/fastp/test.fastp.html
+
+- name: fastp_pe
+  command: nextflow run ./tests/software/fastp -profile docker -entry test_fastp_pe -c ./tests/config/nextflow.config
+  tags:
+    - fastp
+    - fastp_pe
+  files:
+    - path: ./output/fastp/test.fastp.html
+    - path: ./output/fastp/test.fastp.json
+      md5sum: 40db7fcbed478b0a96a1c5c1bb5f737b
+    - path: ./output/fastp/test.fastp.log
+    - path: ./output/fastp/test_1.trim.fastq.gz
+      md5sum: c8844c05194b50ae368e6825e997aa7f
+    - path: ./output/fastp/test_2.trim.fastq.gz
+      md5sum: 9238b07bb1609e939be7c8889b72c209