Fgbio group reads by umi (#952)

* adding template for module groupreadsbyumi

* update modules with code

* strategy is required argument so moving it to input rather than options.args

* tests successful committing yml

* added meta to output

Co-authored-by: Gregor Sturm <mail@gregor-sturm.de>

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+    // Do not publish versions.yml unless running from pytest workflow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

@@ -0,0 +1,50 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process FGBIO_GROUPREADSBYUMI {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${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::fgbio=1.4.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/fgbio:1.4.0--hdfd78af_0"
+    } else {
+        container "quay.io/biocontainers/fgbio:1.4.0--hdfd78af_0"
+    }
+
+    input:
+    tuple val(meta), path(taggedbam)
+    val(strategy)
+
+    output:
+    tuple val(meta), path("*_umi-grouped.bam")  , emit: bam
+    tuple val(meta), path("*_umi_histogram.txt"), emit: histogram
+    path "versions.yml"                         , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+
+    """
+    mkdir tmp
+
+    fgbio \\
+        --tmp-dir=${PWD}/tmp \\
+        GroupReadsByUmi \\
+        -s $strategy \\
+        ${options.args} \\
+        -i $taggedbam \\
+        -o ${prefix}_umi-grouped.bam \\
+        -f ${prefix}_umi_histogram.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( echo \$(fgbio --version 2>&1 | tr -d '[:cntrl:]' ) | sed -e 's/^.*Version: //;s/\\[.*\$//')
+    END_VERSIONS
+    """
+}

modules/fgbio/groupreadsbyumi/meta.yml

@@ -0,0 +1,59 @@
+name: fgbio_groupreadsbyumi
+description: |
+      Groups reads together that appear to have come from the same original molecule.
+      Reads are grouped by template, and then templates are sorted by the 5’ mapping positions
+      of the reads from the template, used from earliest mapping position to latest.
+      Reads that have the same end positions are then sub-grouped by UMI sequence.
+      (!) Note: the MQ tag is required on reads with mapped mates (!)
+      This can be added using samblaster with the optional argument --addMateTags.
+keywords:
+  - UMI
+  - groupreads
+  - fgbio
+tools:
+  - fgbio:
+      description: A set of tools for working with genomic and high throughput sequencing data, including UMIs
+      homepage: http://fulcrumgenomics.github.io/fgbio/
+      documentation: http://fulcrumgenomics.github.io/fgbio/tools/latest/
+      tool_dev_url: https://github.com/fulcrumgenomics/fgbio
+      doi: ""
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: |
+        BAM file. Note: the MQ tag is required on reads with mapped mates (!)
+      pattern: "*.bam"
+  - strategy:
+      type: value
+      description: |
+        Reguired argument: defines the UMI assignment strategy.
+        Must be chosen among: Identity, Edit, Adjacency, Paired.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - bam:
+      type: file
+      description: UMI-grouped BAM
+      pattern: "*.bam"
+  - histogram:
+      type: file
+      description: A text file containing the tag family size counts
+      pattern: "*.txt"
+
+authors:
+  - "@lescai"

tests/config/pytest_modules.yml

@@ -394,6 +394,10 @@ fgbio/fastqtobam:
   - modules/fgbio/fastqtobam/**
   - tests/modules/fgbio/fastqtobam/**
 
+fgbio/groupreadsbyumi:
+  - modules/fgbio/groupreadsbyumi/**
+  - tests/modules/fgbio/groupreadsbyumi/**
+
 fgbio/sortbam:
   - modules/fgbio/sortbam/**
   - tests/modules/fgbio/sortbam/**

tests/modules/fgbio/groupreadsbyumi/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { FGBIO_GROUPREADSBYUMI } from '../../../../modules/fgbio/groupreadsbyumi/main.nf' addParams( options: [:] )
+
+workflow test_fgbio_groupreadsbyumi {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['homo_sapiens']['illumina']['test_paired_end_umi_unsorted_tagged_bam'], checkIfExists: true) ]
+
+    strategy = "Adjacency"
+
+    FGBIO_GROUPREADSBYUMI ( input, strategy )
+}

tests/modules/fgbio/groupreadsbyumi/test.yml

@@ -0,0 +1,10 @@
+- name: fgbio groupreadsbyumi test_fgbio_groupreadsbyumi
+  command: nextflow run tests/modules/fgbio/groupreadsbyumi -entry test_fgbio_groupreadsbyumi -c tests/config/nextflow.config
+  tags:
+    - fgbio
+    - fgbio/groupreadsbyumi
+  files:
+    - path: output/fgbio/test_umi-grouped.bam
+      md5sum: f1e53fc845fd99a3da172eb8063dff0b
+    - path: output/fgbio/test_umi_histogram.txt
+      md5sum: d17fd167b2a765d46e4b01bf08ece01b