New module: isoseq3/refine (#748)

* 📦 NEW: Add isoseq3/refine module

* 👌 IMPROVE: Add some pacbio test files

* 🐛 FIX: Add Pacbio index to test_data.config

* 👌 IMPROVE: Re add 10000 data test

* 👌 IMPROVE: Add parallelization

* 🐛 FIX: Correct Typo

* 👌 IMPROVE: Add some pbindex

* 🐛 FIX: Add pbi extension to files

* 👌 IMPROVE: The module accept one channel (primers moved into the first channel)

* 👌 IMPROVE: Assign a value channel to primers input 

Improve workflow code readability

* 👌 IMPROVE: Update to the version of templates

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Remove pbi from input files

* 👌 IMPROVE: Update test file

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Fill contains args

* 📦 NEW: Add isoseq3/refine module

* 👌 IMPROVE: Add parallelization

* 🐛 FIX: Correct Typo

* 👌 IMPROVE: Add some pacbio test files

* 🐛 FIX: Add Pacbio index to test_data.config

* 👌 IMPROVE: Re add 10000 data test

* 👌 IMPROVE: Add some pbindex

* 🐛 FIX: Add pbi extension to files

* 👌 IMPROVE: The module accept one channel (primers moved into the first channel)

* 👌 IMPROVE: Assign a value channel to primers input 

Improve workflow code readability

* 👌 IMPROVE: Update to the version of templates

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Remove pbi from input files

* 👌 IMPROVE: Update test file

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Fill contains args

* 👌 IMPROVE: Add one channel per output file

* 👌 IMPROVE: Minor updates

* 👌 IMPROVE: Minors Update

- Remove TODO from test.yml
- Remove useless piece of code

* 📦 NEW: Add isoseq3/refine module

* 👌 IMPROVE: Add parallelization

* 🐛 FIX: Correct Typo

* 👌 IMPROVE: Add some pacbio test files

* 🐛 FIX: Add Pacbio index to test_data.config

* 👌 IMPROVE: Re add 10000 data test

* 👌 IMPROVE: Add some pbindex

* 🐛 FIX: Add pbi extension to files

* 👌 IMPROVE: The module accept one channel (primers moved into the first channel)

* 👌 IMPROVE: Assign a value channel to primers input 

Improve workflow code readability

* 👌 IMPROVE: Update to the version of templates

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Remove pbi from input files

* 👌 IMPROVE: Update test file

* 👌 IMPROVE: Fill contains args

* 📦 NEW: Add isoseq3/refine module

* 👌 IMPROVE: Add parallelization

* 🐛 FIX: Correct Typo

* 👌 IMPROVE: Add some pacbio test files

* 🐛 FIX: Add Pacbio index to test_data.config

* 👌 IMPROVE: Re add 10000 data test

* 👌 IMPROVE: Add some pbindex

* 🐛 FIX: Add pbi extension to files

* 👌 IMPROVE: The module accept one channel (primers moved into the first channel)

* 👌 IMPROVE: Assign a value channel to primers input 

Improve workflow code readability

* 👌 IMPROVE: Update to the version of templates

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Remove pbi from input files

* 👌 IMPROVE: Update test file

* 👌 IMPROVE: Add one channel per output file

* 👌 IMPROVE: Minor updates

* 👌 IMPROVE: Minors Update

- Remove TODO from test.yml
- Remove useless piece of code

* 🐛 FIX: Remove unwanted files

* 🐛 FIX: Protect \

* 🐛 FIX: Remove test files

* Apply suggestions from code review

* Apply suggestions from code review

* Update tests/modules/isoseq3/refine/test.yml

Co-authored-by: Gregor Sturm <mail@gregor-sturm.de>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

modules/isoseq3/refine/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/isoseq3/refine/main.nf

@@ -0,0 +1,49 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process ISOSEQ3_REFINE {
+    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::isoseq3=3.4.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/isoseq3:3.4.0--0"
+    } else {
+        container "quay.io/biocontainers/isoseq3:3.4.0--0"
+    }
+
+    input:
+    tuple val(meta), path(bam)
+    path primers
+
+    output:
+    tuple val(meta), path("*.bam")                 , emit: bam
+    tuple val(meta), path("*.bam.pbi")             , emit: pbi
+    tuple val(meta), path("*.consensusreadset.xml"), emit: consensusreadset
+    tuple val(meta), path("*.filter_summary.json") , emit: summary
+    tuple val(meta), path("*.report.csv")          , emit: report
+    path  "versions.yml"                           , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    isoseq3 \\
+        refine \\
+        -j $task.cpus \\
+        $options.args \\
+        $bam \\
+        $primers \\
+        ${prefix}.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( isoseq3 refine --version|sed 's/isoseq refine //'|sed 's/ (commit.\\+//' )
+    END_VERSIONS
+    """
+}

modules/isoseq3/refine/meta.yml

@@ -0,0 +1,62 @@
+name: isoseq3_refine
+description: Generate transcripts by clustering HiFi reads
+keywords:
+  - isoseq3
+  - isoseq3/refine
+tools:
+  - isoseq3:
+      description: IsoSeq3 - Scalable De Novo Isoform Discovery
+      homepage: https://github.com/PacificBiosciences/IsoSeq/blob/master/isoseq-clustering.md
+      documentation: https://github.com/PacificBiosciences/IsoSeq/blob/master/isoseq-clustering.md
+      tool_dev_url: https://github.com/PacificBiosciences/IsoSeq/blob/master/isoseq-clustering.md
+      doi: ""
+      licence: ['BSD-3-clause-Clear']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test ]
+  - bam:
+      type: file
+      description: BAM file, cleaned ccs generated by lima
+      pattern: "*.bam"
+  - primers:
+      type: file
+      description: fasta file of primers
+      pattern: "*.fasta"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - bam:
+      type: file
+      description: Set of complete reads (with polyA tail), where the polyA has been trimmed
+      pattern: "*.bam"
+  - pbi:
+      type: file
+      description: Pacbio index file from polyA trimmed reads
+      pattern: "*.pbi"
+  - consensusreadset:
+      type: file
+      description: Metadata about read library
+      pattern: "*.xml"
+  - summary:
+      type: file
+      description: json file describing number of full length reads, full length non chimeric reads and full length non chimeric polyA reads
+      pattern: "*.json"
+  - report:
+      type: file
+      description: Metadata about primer and polyA detection (primers/polyA/insert length, strand, primer name)
+      pattern: "*.csv"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@sguizard"

tests/config/pytest_modules.yml

@@ -525,6 +525,10 @@ iqtree:
   - modules/iqtree/**
   - tests/modules/iqtree/**
 
+isoseq3/refine:
+  - modules/isoseq3/refine/**
+  - tests/modules/isoseq3/refine/**
+
 ismapper:
   - modules/ismapper/**
   - tests/modules/ismapper/**

tests/modules/isoseq3/refine/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ISOSEQ3_REFINE } from '../../../../modules/isoseq3/refine/main' addParams( options: [suffix:'.refine'] )
+
+workflow test_isoseq3_refine {
+
+    input = [
+            [ id:'test' ], // meta map
+            file(params.test_data['homo_sapiens']['pacbio']['lima'], checkIfExists: true),
+    ]
+    primers = file(params.test_data['homo_sapiens']['pacbio']['primers'], checkIfExists: true)
+
+    ISOSEQ3_REFINE ( input, primers )
+}

tests/modules/isoseq3/refine/test.yml

@@ -0,0 +1,16 @@
+- name: isoseq3 refine test_isoseq3_refine
+  command: nextflow run tests/modules/isoseq3/refine -entry test_isoseq3_refine -c tests/config/nextflow.config
+  tags:
+    - isoseq3
+    - isoseq3/refine
+  files:
+    - path: output/isoseq3/test.refine.bam
+      md5sum: e8387afd5f66a7f6a89f90a0dcf3b823
+    - path: output/isoseq3/test.refine.bam.pbi
+      md5sum: 8097cad9e472f2f79de6de5fe3dcc822
+    - path: output/isoseq3/test.refine.consensusreadset.xml
+      contains: [ 'pbds:ConsensusReadSet' ]
+    - path: output/isoseq3/test.refine.filter_summary.json
+      md5sum: 87f8bdd5c60741f47b8a991e002f7ef3
+    - path: output/isoseq3/test.refine.report.csv
+      md5sum: d42a139e5d9b08396bdb087c01243ea9