Add phyloflash module (#786)

* initial stubs [ci skip]

* remove comments and add main command [ci skip]

* design iteration [ci skip]

* add new standard functions.nf [ci skip]

* update the version string [ci skip]

* accomodate the db stubs and single/double ends [ci skip]

* add FIXME for missing info [ci skip]

* Accomodate the results folder [ci skip]

* Update main.nf

* Apply suggestions from code review

* Update main.nf

* Apply suggestions from code review

* Add version file to stubs [ci skip]

* Tweak the output dir pattern [ci skip]

* Update modules/phyloflash/main.nf

* Update modules/phyloflash/main.nf

* Update modules/phyloflash/main.nf

Co-authored-by: Robert A. Petit III <robbie.petit@gmail.com>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>

modules/phyloflash/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+    // Do not publish versions.yml unless running from pytest workflow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/phyloflash/main.nf

@@ -0,0 +1,85 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process PHYLOFLASH {
+    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), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::phyloflash=3.4" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/phyloflash:3.4--hdfd78af_1"
+    } else {
+        container "quay.io/biocontainers/phyloflash:3.4--hdfd78af_1"
+    }
+
+    input:
+    tuple val(meta), path(reads)
+    path  silva_db
+    path  univec_db
+
+    output:
+    tuple val(meta), path("${meta.id}*/*"), emit: results
+    path "versions.yml"                   , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+
+    if (meta.single_end) {
+        """
+        phyloFlash.pl \\
+            $options.args \\
+            -read1 ${reads[0]} \\
+            -lib $prefix \\
+            -interleaved \\
+            -dbhome . \\
+            -CPUs $task.cpus
+
+        mkdir $prefix
+        mv ${prefix}.* $prefix
+
+        cat <<-END_VERSIONS > versions.yml
+        ${getProcessName(task.process)}:
+            ${getSoftwareName(task.process)}: \$(echo \$(phyloFlash.pl -version 2>&1) | sed "s/^.*phyloFlash v//")
+        END_VERSIONS
+        """
+    } else {
+        """
+        phyloFlash.pl \\
+            $options.args \\
+            -read1 ${reads[0]} \\
+            -read2 ${reads[1]} \\
+            -lib $prefix \\
+            -dbhome . \\
+            -CPUs $task.cpus
+
+        mkdir $prefix
+        mv ${prefix}.* $prefix
+
+        cat <<-END_VERSIONS > versions.yml
+        ${getProcessName(task.process)}:
+            ${getSoftwareName(task.process)}: \$(echo \$(phyloFlash.pl -version 2>&1) | sed "s/^.*phyloFlash v//")
+        END_VERSIONS
+        """
+    }
+
+    stub:
+
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+
+    """
+    mkdir ${prefix}
+    touch ${prefix}/${prefix}.SSU.collection.fasta
+    touch ${prefix}/${prefix}.phyloFlash
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$(phyloFlash.pl -version 2>&1) | sed "s/^.*phyloFlash v//")
+    END_VERSIONS
+    """
+}

modules/phyloflash/meta.yml

@@ -0,0 +1,51 @@
+name: phyloflash
+description: phyloFlash is a pipeline to rapidly reconstruct the SSU rRNAs and explore phylogenetic composition of an illumina (meta)genomic dataset.
+keywords:
+  - metagenomics
+  - illumina datasets
+  - phylogenetic composition
+tools:
+  - phyloflash:
+      description: phyloFlash is a pipeline to rapidly reconstruct the SSU rRNAs and explore phylogenetic composition of an illumina (meta)genomic dataset.
+
+      homepage: https://hrgv.github.io/phyloFlash/
+      documentation: https://hrgv.github.io/phyloFlash/usage.html
+      tool_dev_url: https://github.com/HRGV/phyloFlash
+      doi: "10.1128/mSystems.00920-20"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: Channel containing single or paired-end reads
+      pattern: "*.{fastq.gz,fq.gz}"
+  - sliva_db:
+      type: folder
+      description: Folder containing the SILVA database
+      pattern: "ref"
+  - univec_db:
+      type: folder
+      description: Folder containing UniVec database
+      pattern: "UniVec"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - results:
+      type: folder
+      description: Folder containing the results of phyloFlash analysis
+      pattern: "${prefix}*"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@abhi18av"

tests/config/pytest_modules.yml

@@ -1011,6 +1011,10 @@ pbccs:
   - modules/pbccs/**
   - tests/modules/pbccs/**
 
+phyloflash:
+  - modules/phyloflash/**
+  - tests/modules/phyloflash/**
+
 picard/collecthsmetrics:
   - modules/picard/collecthsmetrics/**
   - tests/modules/picard/collecthsmetrics/**

tests/modules/phyloflash/main.nf

@@ -0,0 +1,44 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PHYLOFLASH } from '../../../modules/phyloflash/main.nf' addParams( options: [:] )
+
+process STUB_PHYLOFLASH_DATABASE {
+    output:
+    path "ref"    , emit: silva_db
+    path "UniVec" , emit: univec_db
+
+    stub:
+    """
+    mkdir ref
+    touch UniVec
+    """
+}
+
+workflow test_phyloflash_single_end {
+
+    STUB_PHYLOFLASH_DATABASE ()
+    
+    input = [ 
+        [ id:'test', single_end:true ], // meta map
+        [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
+    ]
+
+    PHYLOFLASH ( input, STUB_PHYLOFLASH_DATABASE.out.silva_db,  STUB_PHYLOFLASH_DATABASE.out.univec_db )
+}
+
+workflow test_phyloflash_paired_end {
+
+    STUB_PHYLOFLASH_DATABASE ()
+
+    input = [ 
+        [ id:'test', single_end:false ], // meta map
+        [ 
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+
+    PHYLOFLASH ( input, STUB_PHYLOFLASH_DATABASE.out.silva_db,  STUB_PHYLOFLASH_DATABASE.out.univec_db )
+}

tests/modules/phyloflash/test.yml

@@ -0,0 +1,15 @@
+- name: phyloflash single-end
+  command: nextflow run ./tests/modules/phyloflash -entry test_phyloflash_single_end -c tests/config/nextflow.config -stub-run
+  tags:
+    - phyloflash
+  files:
+    - path: output/phyloflash/test/test.SSU.collection.fasta
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+
+- name: phyloflash paired-end
+  command: nextflow run ./tests/modules/phyloflash -entry test_phyloflash_paired_end -c tests/config/nextflow.config -stub-run
+  tags:
+    - phyloflash
+  files:
+    - path: output/phyloflash/test/test.SSU.collection.fasta
+      md5sum: d41d8cd98f00b204e9800998ecf8427e