New module: isoseq3/cluster (#801)

* 📦 NEW: Add isoseq3/cluster module

* 🐛FIX: Fix reports channel and add .pbi to it

* 🐛FIX: Fix report channel definition

* 👌IMPROVE: Move .pbi file into reports channel

* 👌IMPROVE: remove --use_qvs option from command line

* 👌 IMPROVE: Add in addParams removed options from command line

* 👌 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)

* 📦 NEW: Add galgal6 chr30 test data

* 📦 NEW: Add bamtools module

* 👌 IMPROVE: Ignore test data

* 👌 IMPROVE: Update to last templates version

* 👌 IMPROVE: Update to last templates version

* 👌 IMPROVE: add singletons parameter and improve outputs

* 🐛 FIX: Update test with last module model

* 👌 IMPROVE: Add test tag

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Update test data config

* 👌 IMPROVE: Remove pbi from input files

* 👌 IMPROVE: Remove unused index

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Fill contains args

* 📦 NEW: Add isoseq3/cluster module

* 🐛FIX: Fix reports channel and add .pbi to it

* 🐛FIX: Fix report channel definition

* 👌IMPROVE: Move .pbi file into reports channel

* 👌IMPROVE: remove --use_qvs option from command line

* 👌 IMPROVE: Add in addParams removed options from command line

* 👌 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: Update to last templates version

* 👌 IMPROVE: add singletons parameter and improve outputs

* 🐛 FIX: Update test with last module model

* 👌 IMPROVE: Add test tag

* 👌 IMPROVE: Update test data config

* 👌 IMPROVE: Remove pbi from input files

* 👌 IMPROVE: Remove unused index

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Fill contains args

* 👌 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

* 📦 NEW: Add galgal6 chr30 test data

* 📦 NEW: Add bamtools module

* 👌 IMPROVE: Ignore test data

* 👌 IMPROVE: Update to last templates version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Update code to new versions capture + better output channels

* 👌 IMPROVE: Update with new versions.yml file

* 🐛 FIX: Update meta.yml + correct typos

* 👌 IMPROVE: Clean output file names + correct typo

* 🐛 FIX: Remove bamtools/split module from isoseq3/cluster

.gitignore

@@ -5,11 +5,9 @@ test_output/
 output/
 .DS_Store
 *.code-workspace
+tests/data/
 .screenrc
 .*.sw?
 __pycache__
 *.pyo
 *.pyc
-tests/data/
-modules/modtest/
-tests/modules/modtest/

modules/isoseq3/cluster/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/cluster/main.nf

@@ -0,0 +1,53 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process ISOSEQ3_CLUSTER {
+    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)
+
+    output:
+    tuple val(meta), path("*.bam")               , emit: bam
+    tuple val(meta), path("*.bam.pbi")           , emit: pbi
+    tuple val(meta), path("*.cluster")           , emit: cluster
+    tuple val(meta), path("*.cluster_report.csv"), emit: cluster_report
+    tuple val(meta), path("*.transcriptset.xml") , emit: transcriptset
+    tuple val(meta), path("*.hq.bam")            , emit: hq_bam
+    tuple val(meta), path("*.hq.bam.pbi")        , emit: hq_pbi
+    tuple val(meta), path("*.lq.bam")            , emit: lq_bam
+    tuple val(meta), path("*.lq.bam.pbi")        , emit: lq_pbi
+    path  "versions.yml"                         , emit: versions
+
+    tuple val(meta), path("*.singletons.bam")    , optional: true, emit: singletons_bam
+    tuple val(meta), path("*.singletons.bam.pbi"), optional: true, emit: singletons_pbi
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    isoseq3 \\
+        cluster \\
+        $bam \\
+        ${prefix}.bam \\
+        $options.args
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        isoseq3 cluster: \$( isoseq3 cluster --version|sed 's/isoseq cluster //g'|sed 's/ (.*//g' )
+    END_VERSIONS
+    """
+}

modules/isoseq3/cluster/meta.yml

@@ -0,0 +1,81 @@
+name: isoseq3_cluster
+description: IsoSeq3 - Cluster - Cluster trimmed consensus sequences
+keywords:
+  - cluster
+tools:
+  - isoseq3:
+      description: IsoSeq3 - Cluster - Cluster trimmed consensus sequences
+      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 generated by isoseq3 refine
+      pattern: "*.bam"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "versions.yml"
+  - bam:
+      type: file
+      description: BAM file of clustered consensus
+      pattern: "*.bam"
+  - pbi:
+      type: file
+      description: Pacbio Index of consensus reads generated by clustering
+      pattern: "*.pbi"
+  - cluster:
+      type: file
+      description: A two columns (from, to) file describing original read name to new read name
+      pattern: "*.cluster"
+  - cluster_report:
+      type: file
+      description: A table files clusters (transcripts) members (read)
+      pattern: "*.cluster_report.csv"
+  - transcriptset:
+      type: file
+      description: A metadata xml file which contains full paths to data files
+      pattern: "*.clustered.transcriptset.xml"
+  - hq_bam:
+      type: file
+      description: High quality reads
+      pattern: "*.hq.bam"
+  - hq_pbi:
+      type: file
+      description: Pacbio index of high quality reads
+      pattern: "*.hq.bam.pbi"
+  - lq_bam:
+      type: file
+      description: Low quality reads
+      pattern: "*.lq.bam"
+  - lq_pbi:
+      type: file
+      description: Pacbio index of low quality reads
+      pattern: "*.lq.bam.pbi"
+  - singletons_bam:
+      type: file
+      description: Unclustered reads
+      pattern: "*.singletons.bam"
+  - singletons_pbi:
+      type: file
+      description: Pacbio index of unclustered reads
+      pattern: "*.singletons.bam.pbi"
+
+authors:
+  - "@sguizard"

tests/config/pytest_modules.yml

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

tests/modules/isoseq3/cluster/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ISOSEQ3_CLUSTER } from '../../../../modules/isoseq3/cluster/main.nf' addParams( options: [args: '--singletons --use-qvs --verbose'] )
+
+workflow test_isoseq3_cluster {
+
+    input = [
+            [ id:'test' ], // meta map
+            file(params.test_data['homo_sapiens']['pacbio']['refine'], checkIfExists: true),
+        ]
+
+    ISOSEQ3_CLUSTER ( input )
+}

tests/modules/isoseq3/cluster/test.yml

@@ -0,0 +1,28 @@
+- name: isoseq3 cluster test_isoseq3_cluster
+  command: nextflow run tests/modules/isoseq3/cluster -entry test_isoseq3_cluster -c tests/config/nextflow.config
+  tags:
+    - isoseq3
+    - isoseq3/cluster
+  files:
+    - path: output/isoseq3/test.bam
+      md5sum: ca8277f4d8fe1bba68ba266c42b46dd1
+    - path: output/isoseq3/test.bam.pbi
+      md5sum: cbc06657b4543faba7ff886b3b12b862
+    - path: output/isoseq3/test.cluster
+      md5sum: d5059d856763fc5591332980bfc0d57b
+    - path: output/isoseq3/test.cluster_report.csv
+      md5sum: 342d97dc10aedf80a45977edcb491c62
+    - path: output/isoseq3/test.hq.bam
+      md5sum: e93ea85776c35c246364d954032c2ea9
+    - path: output/isoseq3/test.hq.bam.pbi
+      md5sum: 5a8ea7668e8f8e173478b28cbb6ab515
+    - path: output/isoseq3/test.lq.bam
+      md5sum: 4ea0e4f4a6cc689dcc275adcdf688fad
+    - path: output/isoseq3/test.lq.bam.pbi
+      md5sum: f5edc24711b2c8d6474d60cb69022af0
+    - path: output/isoseq3/test.singletons.bam
+      md5sum: 73d131920bd42e1fc5fca2e6cb71f4b2
+    - path: output/isoseq3/test.singletons.bam.pbi
+      md5sum: 73980863be4b5bda2846325c737f0b5e
+    - path: output/isoseq3/test.transcriptset.xml
+      contains: [ 'PacBio.DataSet.TranscriptSet' ]