New modules: Fgbio callmolecularconsensusreads and sortbam (#352)

* Added fgbio callmolecularconsensusreads and sortbam modules

* Fixed naming issue in meta.yml

* fix: test.yml and config lint

* Revert "fix: test.yml and config lint"

This reverts commit 0453bc3a8dc3dab6997442a4349ee2241adcc380, which caused the sortbam tests to fail.

* style: Fix test names

* style: Remove trailing whitespace

* fixed test.yml

* fix: test data in sortbam

* fix: data format

* fix: test data for callmolecularconsensusreads

* Corrected with updated test data

* Apply suggestions from code review

Applied changes from code review, mainly syntactical changes

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

Co-authored-by: Sruthi Suresh <sps180004@ganymede.utdallas.edu>
Co-authored-by: Edmund Miller <edmund.a.miller@protonmail.com>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

software/fgbio/callmolecularconsensusreads/functions.nf

@@ -0,0 +1,60 @@
+
+/*
+ * -----------------------------------------------------
+ *  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/fgbio/callmolecularconsensusreads/main.nf

@@ -0,0 +1,38 @@
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process FGBIO_CALLMOLECULARCONSENSUSREADS {
+    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), publish_id:meta.id) }
+
+    conda (params.enable_conda ? "bioconda::fgbio=1.3.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/fgbio:1.3.0--0"
+    } else {
+        container "quay.io/biocontainers/fgbio:1.3.0--0"
+    }
+
+    input:
+    tuple val(meta), path(bam)
+
+    output:
+    tuple val(meta), path("*.bam"), emit: bam
+    path  "*.version.txt"         , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    fgbio \\
+        CallMolecularConsensusReads \\
+        -i $bam \\
+        $options.args \\
+        -o ${prefix}.bam
+    fgbio --version | sed -e "s/fgbio v//g" > ${software}.version.txt
+    """
+}

software/fgbio/callmolecularconsensusreads/meta.yml

@@ -0,0 +1,45 @@
+name: fgbio_callmolecularconsensusreads
+description: Calls consensus sequences from reads with the same unique molecular tag.
+
+keywords:
+    - UMIs
+    - consensus sequence
+    - bam
+    - sam
+tools:
+    - fgbio:
+        description: Tools for working with genomic and high throughput sequencing data.
+        homepage: https://github.com/fulcrumgenomics/fgbio
+        documentation: http://fulcrumgenomics.github.io/fgbio/
+        licence: ['MIT']
+
+input:
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false, collapse:false ]
+    - bam:
+        type: file
+        description: |
+          The input SAM or BAM file.
+        pattern: "*.{bam,sam}"
+
+output:
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - bam:
+        type: file
+        description: |
+          Output SAM or BAM file to write consensus reads.
+        pattern: "*.{bam,sam}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+
+authors:
+    - "@sruthipsuresh"

software/fgbio/sortbam/functions.nf

@@ -0,0 +1,60 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args          = args.args ?: ''
+    options.args2         = args.args2 ?: ''
+    options.args3         = args.args3 ?: ''
+    options.publish_by_id = args.publish_by_id ?: false
+    options.publish_dir   = args.publish_dir ?: ''
+    options.publish_files = args.publish_files
+    options.suffix        = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }  // Remove empty entries
+    paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_id) {
+            path_list.add(args.publish_id)
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/fgbio/sortbam/main.nf

@@ -0,0 +1,39 @@
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process FGBIO_SORTBAM {
+    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), publish_id:meta.id) }
+
+    conda (params.enable_conda ? "bioconda::fgbio=1.3.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/fgbio:1.3.0--0"
+    } else {
+        container "quay.io/biocontainers/fgbio:1.3.0--0"
+    }
+
+    input:
+    tuple val(meta), path(bam)
+
+    output:
+    tuple val(meta), path("*.bam"), emit: bam
+    path  "*.version.txt"         , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    fgbio \\
+        SortBam \\
+        -i $bam \\
+        $options.args \\
+        -o ${prefix}.bam
+    fgbio --version | sed -e "s/fgbio v//g" > ${software}.version.txt
+    """
+}
+

software/fgbio/sortbam/meta.yml

@@ -0,0 +1,43 @@
+name: fgbio_sortbam
+description: Sorts a SAM or BAM file. Several sort orders are available, including coordinate, queryname, random, and randomquery.
+keywords:
+    - sort
+    - bam
+    - sam
+tools:
+    - fgbio:
+        description: Tools for working with genomic and high throughput sequencing data.
+        homepage: https://github.com/fulcrumgenomics/fgbio
+        documentation: http://fulcrumgenomics.github.io/fgbio/
+        licence: ['MIT']
+
+input:
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false, collapse:false ]
+    - bam:
+        type: file
+        description: |
+          The input SAM or BAM file to be sorted.
+        pattern: "*.{bam,sam}"
+
+output:
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - bam:
+        type: file
+        description: |
+          Output SAM or BAM file.
+        pattern: "*.{bam,sam}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+
+authors:
+    - "@sruthipsuresh"

tests/config/pytest_software.yml

@@ -178,6 +178,14 @@ fastqc:
   - software/fastqc/**
   - tests/software/fastqc/**
 
+fgbio_callmolecularconsensusreads:
+  - software/fgbio/callmolecularconsensusreads/**
+  - tests/software/fgbio/callmolecularconsensusreads/**
+
+fgbio_sortbam:
+  - software/fgbio/sortbam/**
+  - tests/software/fgbio/sortbam/**
+
 flash:
   - software/flash/**
   - tests/software/flash/**

tests/software/fgbio/callmolecularconsensusreads/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { FGBIO_SORTBAM } from '../../../../software/fgbio/sortbam/main.nf' addParams( options: [args: '-s TemplateCoordinate', suffix: '_out'] )
+include { FGBIO_CALLMOLECULARCONSENSUSREADS } from '../../../../software/fgbio/callmolecularconsensusreads/main.nf' addParams( options: [args: '-M 1', suffix: '_molreads'] )
+
+workflow test_fgbio_callmolecularconsensusreads {
+    input = [ [ id:'test' ], // meta map
+                file(params.test_data['sarscov2']['illumina']['test_single_end_bam'], checkIfExists: true) ]
+    FGBIO_SORTBAM ( input )
+    FGBIO_CALLMOLECULARCONSENSUSREADS ( FGBIO_SORTBAM.out.bam  )
+}

tests/software/fgbio/callmolecularconsensusreads/test.yml

@@ -0,0 +1,10 @@
+- name: fgbio callmolecularconsensusreads
+  command: nextflow run tests/software/fgbio/callmolecularconsensusreads -entry test_fgbio_callmolecularconsensusreads -c tests/config/nextflow.config
+  tags:
+    - fgbio_callmolecularconsensusreads
+    - fgbio
+  files:
+    - path: output/fgbio/test_molreads.bam
+      md5sum: 7010bcdc037c36af13dbc370c06c76d3
+    - path: output/fgbio/test_out.bam
+      md5sum: d84e28fecc90c0752c543e934f10aa31

tests/software/fgbio/sortbam/main.nf

@@ -0,0 +1,11 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { FGBIO_SORTBAM } from '../../../../software/fgbio/sortbam/main.nf' addParams( options: [:] )
+
+workflow test_fgbio_sortbam {
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ]
+    FGBIO_SORTBAM ( input )
+}

tests/software/fgbio/sortbam/test.yml

@@ -0,0 +1,8 @@
+- name: fgbio sortbam
+  command: nextflow run tests/software/fgbio/sortbam -entry test_fgbio_sortbam -c tests/config/nextflow.config
+  tags:
+    - fgbio_sortbam
+    - fgbio
+  files:
+    - path: output/fgbio/test.bam
+      md5sum: 56987f74214cdc72ae840e0007ff4935