Merge pull request #167 from JoseEspinosa/cat_fastq

Add cat fastq module

.github/filters.yml

@@ -92,6 +92,10 @@ bwa_mem:
   - software/bwa/mem/**
   - tests/software/bwa/mem/**
 
+cat_fastq:
+  - software/cat/fastq/**
+  - tests/software/cat/fastq/**
+
 cutadapt:
   - software/cutadapt/**
   - tests/software/cutadapt/**

software/cat/fastq/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/cat/fastq/main.nf

@@ -0,0 +1,46 @@
+// Import generic module functions
+include { initOptions; saveFiles } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process CAT_FASTQ {
+    tag "$meta.id"
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'merged_fastq', publish_id:meta.id) }
+
+    conda (params.enable_conda ? "conda-forge::sed=4.7=h1bed415_1000" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img"
+    } else {
+        container "biocontainers/biocontainers:v1.2.0_cv1"
+    }
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.merged.fastq.gz"), emit: reads
+
+    script:
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def readList = reads.collect{ it.toString() }
+    if (meta.single_end) {
+        if (readList.size > 1) {
+            """
+            cat ${readList.sort().join(' ')} > ${prefix}.merged.fastq.gz
+            """
+        }
+    } else {
+        if (readList.size > 2) {
+            def read1 = []
+            def read2 = []
+            readList.eachWithIndex{ v, ix -> ( ix & 1 ? read2 : read1 ) << v }
+            """
+            cat ${read1.sort().join(' ')} > ${prefix}_1.merged.fastq.gz
+            cat ${read2.sort().join(' ')} > ${prefix}_2.merged.fastq.gz
+            """
+        }
+    }
+}

software/cat/fastq/meta.yml

@@ -0,0 +1,55 @@
+name: cat_fastq
+description: Concatenates fastq files
+keywords:
+    - fastq
+    - concatenate
+tools:
+    - cat:
+        description: |
+            The cat utility reads files sequentially, writing them to the standard output.
+        documentation: https://www.gnu.org/software/coreutils/manual/html_node/cat-invocation.html
+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:
+    input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: list
+        description: |
+            List of input FastQ files to be concatenated.
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: Merged fastq file
+        pattern: "*.{merged.fastq.gz}"
+authors:
+    - "@joseespinosa"
+    - "@drpatelh"

tests/software/cat/fastq/main.nf

@@ -0,0 +1,27 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CAT_FASTQ } from '../../../../software/cat/fastq/main.nf' addParams( options: [:] )
+
+workflow test_cat_fastq_single_end {
+
+    def input = []
+    input = [ [ id:'test', single_end:true ], // meta map
+                [ file("${launchDir}/tests/data/fastq/rna/test_R1_val_1.fq.gz", checkIfExists: true),
+                  file("${launchDir}/tests/data/fastq/rna/test_R1.fastq.gz", checkIfExists: true) ]]
+
+    CAT_FASTQ ( input )
+}
+
+workflow test_cat_fastq_paired_end {
+
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+                [ file("${launchDir}/tests/data/fastq/rna/test_R1_val_1.fq.gz", checkIfExists: true),
+                  file("${launchDir}/tests/data/fastq/rna/test_R2_val_2.fq.gz", checkIfExists: true),
+                  file("${launchDir}/tests/data/fastq/rna/test_R1.fastq.gz", checkIfExists: true),
+                  file("${launchDir}/tests/data/fastq/rna/test_R2.fastq.gz", checkIfExists: true) ]]
+
+    CAT_FASTQ ( input )
+}

tests/software/cat/fastq/test.yml

@@ -0,0 +1,21 @@
+- name: cat fastq single-end
+  command: nextflow run ./tests/software/cat/fastq -entry test_cat_fastq_single_end -c tests/config/nextflow.config
+  tags:
+    - cat
+    - cat_fastq
+    - cat_fastqc_single_end
+  files:
+    - path: output/merged_fastq/test.merged.fastq.gz
+      md5sum: 7f753b793e5b0872758b1574db84d767
+
+- name: cat fastq fastqc_paired_end
+  command: nextflow run ./tests/software/cat/fastq -entry test_cat_fastq_paired_end -c tests/config/nextflow.config
+  tags:
+    - cat
+    - cat_fastq
+    - cat_fastqc_paired_end
+  files:
+    - path: output/merged_fastq/test_1.merged.fastq.gz
+      md5sum: 7f753b793e5b0872758b1574db84d767
+    - path: output/merged_fastq/test_2.merged.fastq.gz
+      md5sum: c71ff917e002b1e852916a021d52921d