Add module: nf-core hackathon #207 : new module: msisensor/msi (#343)

* Add module: nf-core hackathon #207 : new module: msisensor/msi

* Add module: nf-core hackathon #207 : new module: msisensor/msi

* Fix 4-spacing issues (caught in PR linting)

* Code review fixes & update configs

* Code review: remove stray echo

* Code review: Add msisensor modules

* Slashes to underscores to get tests to run on github

* Update software/msisensor/scan/main.nf

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

* Update software/msisensor/scan/main.nf

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

* Update software/msisensor/msi/main.nf

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

* Update software/msisensor/msi/main.nf

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

* Add all outputs to meta.ymls

* Fixes from code review

* Fixes from code review

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

software/msisensor/msi/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/msisensor/msi/main.nf

@@ -0,0 +1,45 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process MSISENSOR_MSI {
+    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), publish_id:meta.id) }
+
+    conda (params.enable_conda ? "bioconda::msisensor=0.5" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/msisensor:0.5--hb3646a4_2"
+    } else {
+        container "quay.io/biocontainers/msisensor:0.5--hb3646a4_2"
+    }
+
+    input:
+    tuple val(meta), path(normal_bam), path(normal_bai), path(tumor_bam), path(tumor_bai), val(metascan), path(homopolymers)
+
+    output:
+    tuple val(meta), path("${prefix}")         , emit: output
+    tuple val(meta), path("${prefix}_dis")     , emit: output_dis
+    tuple val(meta), path("${prefix}_germline"), emit: output_germline
+    tuple val(meta), path("${prefix}_somatic") , emit: output_somatic
+    path "*.version.txt"                       , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    prefix       = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    msisensor \\
+        msi \\
+        -d $homopolymers \\
+        -n $normal_bam \\
+        -t $tumor_bam \\
+        -o $prefix \\
+        $options.args
+
+    echo \$(msisensor 2>&1) | sed -nE 's/Version:\\sv([0-9]\\.[0-9])/\\1/ p' > ${software}.version.txt
+    """
+}

software/msisensor/msi/meta.yml

@@ -0,0 +1,69 @@
+name: msisensor_msi
+
+description: Evaluate microsattelite instability (MSI) using paired tumor-normal sequencing data
+keywords:
+  - homoploymer,microsatellite
+tools:
+  - msisensor:
+      description: MSIsensor is a C++ program to detect replication slippage variants at microsatellite regions, and differentiate them as somatic or germline.
+      homepage: https://github.com/ding-lab/msisensor
+      documentation: None
+      tool_dev_url: None
+      doi: "10.1093/bioinformatics/btt755"
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - normal_bam:
+      type: file
+      description: Coordinate sorted BAM/CRAM/SAM file from normal tissue
+      pattern: "*.{bam,cram,sam}"
+  - normal_bai:
+      type: file
+      description: Index for coordinate sorted BAM/CRAM/SAM file from normal tissue
+      pattern: "*.{bam,cram,sam}"
+  - tumor_bam:
+      type: file
+      description: Coordinate sorted BAM/CRAM/SAM file from tumor tissue
+      pattern: "*.{bam,cram,sam}"
+  - tumor_bai:
+      type: file
+      description: Index for coordinate sorted BAM/CRAM/SAM file from tumor tissue
+      pattern: "*.{bam,cram,sam}"
+  - homopolymers:
+      type: file
+      description: Output file from MSIsensor scan module
+      pattern: "*.msisensor_scan.tab"
+
+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: "*.{version.txt}"
+  - txt:
+      type: file
+      description: MSIsensor MSI final report file
+      pattern: "*.output"
+  - txt:
+      type: file
+      description: MSIsensor MSI DIS report file
+      pattern: "*.output_dis"
+  - txt:
+      type: file
+      description: MSIsensor MSI germline report file
+      pattern: "*.output_germline"
+  - txt:
+      type: file
+      description: MSIsensor MSI somatic report file
+      pattern: "*.output_somatic"
+authors:
+  - "@kevbrick"

software/msisensor/scan/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/msisensor/scan/main.nf

@@ -0,0 +1,40 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process MSISENSOR_SCAN {
+    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), publish_id:meta.id) }
+
+    conda (params.enable_conda ? "bioconda::msisensor=0.5" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/msisensor:0.5--hb3646a4_2"
+    } else {
+        container "quay.io/biocontainers/msisensor:0.5--hb3646a4_2"
+    }
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple (val(meta), path("*.tab"), emit: txt)
+    path ("*.version.txt"          , emit: version)
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    msisensor \\
+        scan \\
+        -d $fasta \\
+        -o ${prefix}.msisensor_scan.tab \\
+        $options.args
+
+    echo \$(msisensor 2>&1) | sed -nE 's/Version:\\sv([0-9]\\.[0-9])/\\1/ p' > ${software}.version.txt
+    """
+}

software/msisensor/scan/meta.yml

@@ -0,0 +1,42 @@
+name: msisensor_scan
+
+description: Scan a reference genome to get microsatellite & homopolymer information
+keywords:
+  - homoploymer,microsatellite
+tools:
+  - msisensor:
+      description: MSIsensor is a C++ program to detect replication slippage variants at microsatellite regions, and differentiate them as somatic or germline.
+      homepage: https://github.com/ding-lab/msisensor
+      documentation: None
+      tool_dev_url: None
+      doi: "10.1093/bioinformatics/btt755"
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: FASTA file
+      pattern: "*.{fa,fasta}"
+
+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: "*.{version.txt}"
+  - txt:
+      type: file
+      description: MSIsensor scan output file of homopolymers & minisatellites
+      pattern: "*.msisensor_scan.txt"
+
+authors:
+  - "@kevbrick"

tests/config/pytest_software.yml

@@ -278,6 +278,14 @@ mosdepth:
   - software/mosdepth/**
   - tests/software/mosdepth/**
 
+msisensor_scan:
+  - software/msisensor/scan/**
+  - tests/software/msisensor/scan/**
+
+msisensor_msi:
+  - software/msisensor/msi/**
+  - tests/software/msisensor/msi/**
+
 multiqc:
   - software/fastqc/**
   - software/multiqc/**

tests/software/msisensor/msi/main.nf

@@ -0,0 +1,31 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MSISENSOR_SCAN } from '../../../../software/msisensor/scan/main.nf' addParams( options: [:] )
+include { MSISENSOR_MSI } from '../../../../software/msisensor/msi/main.nf' addParams( options: [:] )
+
+workflow test_msisensor_msi {
+
+    def scaninput  = []
+    scaninput = [ [ id:'test', single_end:false ], // meta map
+                file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+    scan = MSISENSOR_SCAN ( scaninput )
+
+    // IMPERFECT TEST:
+    // USING SARS-COV2 DATA AS NORMAL:TUMOR PAIR THIS WILL SUFFICE TO
+    // TEST MODULE EXECUTION, BUT NOT FUNCTIONALITY.
+    // FUNCTIONALITY HAS BEEN TESTED MANUALY USING AUTHOR-PROVIDED TEST
+    // DATA (https://github.com/ding-lab/msisensor/tree/master/test)
+    def input      = []
+
+    input = Channel.from([ [ id:'test', single_end:false ], // meta map
+               file(params.test_data['sarscov2']['illumina']['test_methylated_paired_end_sorted_bam'],     checkIfExists: true),
+               file(params.test_data['sarscov2']['illumina']['test_methylated_paired_end_sorted_bam_bai'], checkIfExists: true),
+               file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'],         checkIfExists: true),
+               file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'],     checkIfExists: true) ])
+    //scan.txt.view()
+    input.concat(scan.txt).collect().view()
+    // BIT CLUMSY:
+    MSISENSOR_MSI ( input.concat(scan.txt).collect() )
+}

tests/software/msisensor/msi/test.yml

@@ -0,0 +1,14 @@
+- name: msisensor msi
+  command: nextflow run ./tests/software/msisensor/msi -entry test_msisensor_msi -c tests/config/nextflow.config
+  tags:
+    - msisensor
+    - msisensor_msi
+  files:
+    - path: output/msisensor/test
+      md5sum: a3290f7539dbbf83777e8590156c0e28
+    - path: output/msisensor/test_dis
+      md5sum: 060a3fc3701f3b10f6b19da9b21a32b7
+    - path: output/msisensor/test_germline
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/msisensor/test_somatic
+      md5sum: d41d8cd98f00b204e9800998ecf8427e

tests/software/msisensor/scan/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MSISENSOR_SCAN } from '../../../../software/msisensor/scan/main.nf' addParams( options: [:] )
+
+workflow test_msisensor_scan {
+
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)]
+
+    MSISENSOR_SCAN ( input )
+}

tests/software/msisensor/scan/test.yml

@@ -0,0 +1,8 @@
+- name: msisensor scan
+  command: nextflow run ./tests/software/msisensor/scan -entry test_msisensor_scan -c tests/config/nextflow.config
+  tags:
+    - msisensor
+    - msisensor_scan
+  files:
+    - path: output/msisensor/test.msisensor_scan.tab
+      md5sum: b7ae85acdcfc1a51e867ab3446d6fb59