1976 msisensor2 (#1977)

* msisensor2: Add msisensor2 module

* msisensor2/scan module added

* msisensor2 tests added

Changes:
 - tests added for msisensor2 from the msisensor2 github repo. No
 available tests from NF-Core test repo.

Relates to #1976

* msisensor2 slight bump in stuff

* msisensor2: Replaced spelling of 'tumour' with 'tumor'

* msisensor2: fix linting, testing and containers

Relates to #1976

Co-authored-by: Maxime U. Garcia <max.u.garcia@gmail.com>

modules/msisensor2/msi/main.nf

@@ -0,0 +1,48 @@
+process MSISENSOR2_MSI {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::msisensor2=0.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/msisensor2:0.1--hd03093a_0':
+        'quay.io/biocontainers/msisensor2:0.1--hd03093a_0' }"
+
+    input:
+    tuple val(meta), path(tumor_bam), path(tumor_bam_index), path(normal_bam), path(normal_bam_index), path(intervals)
+    path scan
+    path(models, stageAs: "models/*")
+
+    output:
+    tuple val(meta), path("${prefix}")        , emit: msi
+    tuple val(meta), path("${prefix}_dis")    , emit: distribution
+    tuple val(meta), path("${prefix}_somatic"), emit: somatic
+    path "versions.yml"                       , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    def scan_cmd          = scan       ? "-d $scan"       : ""
+    def model_cmd         = models     ? "-M models/"     : ""
+    def tumor_bam_cmd     = tumor_bam  ? "-t $tumor_bam"  : ""
+    def normal_bam_cmd    = normal_bam ? "-n $normal_bam" : ""
+    def interval_command  = intervals  ? "-e $intervals"  : ""
+    """
+    msisensor2 msi \\
+        -b ${task.cpus} \\
+        $args \\
+        $model_cmd \\
+        $scan_cmd \\
+        $interval_command \\
+        $tumor_bam_cmd \\
+        $normal_bam_cmd \\
+        -o $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        msisensor2: \$(echo \$(msisensor2 2> >(grep Version) | sed 's/Version: v//g'))
+    END_VERSIONS
+    """
+}

modules/msisensor2/msi/meta.yml

@@ -0,0 +1,59 @@
+name: "msisensor2_msi"
+description: msisensor2 detection of MSI regions.
+keywords:
+  - msi
+tools:
+  - "msisensor2":
+      description: "MSIsensor2 is a novel algorithm based machine learning, featuring a large upgrade in the microsatellite instability (MSI) detection for tumor only sequencing data, including Cell-Free DNA (cfDNA), Formalin-Fixed Paraffin-Embedded(FFPE) and other sample types. The original MSIsensor is specially designed for tumor/normal paired sequencing data."
+      homepage: "https://github.com/niu-lab/msisensor2"
+      documentation: "https://github.com/niu-lab/msisensor2/blob/master/README.md"
+      tool_dev_url: "https://github.com/niu-lab/msisensor2"
+      doi: ""
+      licence: "GPL-3.0"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  #
+  - tumor_bam:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - normal_bam:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - intervals:
+      type: file
+      description: BED
+      pattern: "*.bed"
+  - models:
+      type: file
+      description: Folder of MSISensor2 models (available from Github or as a product of msisensor2/scan)
+      pattern: "*/*"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - msi:
+      type: file
+      description: MSI classifications as a text file
+  - distribution:
+      type: file
+      description: Read count distributions of MSI regions
+  - somatic:
+      type: file
+      description: Somatic MSI regions detected.
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@adamrtalbot"

modules/msisensor2/scan/main.nf

@@ -0,0 +1,36 @@
+process MSISENSOR2_SCAN {
+    tag '$fasta'
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::msisensor2=0.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/msisensor2:0.1--hd03093a_0':
+        'quay.io/biocontainers/msisensor2:0.1--hd03093a_0' }"
+
+    input:
+    path fasta
+    val output
+
+    output:
+    path output_path   , emit: scan
+    path "versions.yml", emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args        = task.ext.args ?: ''
+    def inputs      = fasta.collect{ "-d $it"}.join(" ")
+    output_path = output ?: "output.scan"
+    """
+    msisensor2 scan \\
+        $args \\
+        $inputs \\
+        -o $output_path
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        msisensor2: \$(echo \$(msisensor2 2> >(grep Version) | sed 's/Version: v//g'))
+    END_VERSIONS
+    """
+}

modules/msisensor2/scan/meta.yml

@@ -0,0 +1,34 @@
+name: "msisensor2_scan"
+description: msisensor2 detection of MSI regions.
+keywords:
+  - msi
+tools:
+  - "msisensor2":
+      description: "MSIsensor2 is a novel algorithm based machine learning, featuring a large upgrade in the microsatellite instability (MSI) detection for tumor only sequencing data, including Cell-Free DNA (cfDNA), Formalin-Fixed Paraffin-Embedded(FFPE) and other sample types. The original MSIsensor is specially designed for tumor/normal paired sequencing data."
+      homepage: "https://github.com/niu-lab/msisensor2"
+      documentation: "https://github.com/niu-lab/msisensor2/blob/master/README.md"
+      tool_dev_url: "https://github.com/niu-lab/msisensor2"
+      doi: ""
+      licence: "GPL-3.0"
+
+input:
+  - fasta:
+      type: file
+      description: Path to reference genome.
+      pattern: "*.fasta"
+  - output:
+      type: val
+      description: Name of output MSI scan to write.
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - output:
+      type: file
+      description: Output scan of MSI regions in FASTA file.
+      pattern: "*"
+
+authors:
+  - "@adamrtalbot"

tests/config/pytest_modules.yml

@@ -1570,6 +1570,14 @@ msisensor/scan:
   - modules/msisensor/scan/**
   - tests/modules/msisensor/scan/**
 
+msisensor2/msi:
+  - modules/msisensor2/msi/**
+  - tests/modules/msisensor2/msi/**
+
+msisensor2/scan:
+  - modules/msisensor2/scan/**
+  - tests/modules/msisensor2/scan/**
+
 msisensorpro/msi_somatic:
   - modules/msisensorpro/msi_somatic/**
   - tests/modules/msisensorpro/msi_somatic/**

tests/modules/msisensor2/msi/main.nf

@@ -0,0 +1,84 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MSISENSOR2_SCAN } from '../../../../modules/msisensor2/scan/main.nf'
+include { MSISENSOR2_MSI } from '../../../../modules/msisensor2/msi/main.nf'
+
+workflow test_msisensor2_msi_tumor_only {
+
+    reference = [
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+
+    MSISENSOR2_SCAN ( reference, "outputfile" )
+
+    input = [
+        [ id:'test' ],
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+        [],
+        [],
+        [],
+    ]
+
+    MSISENSOR2_MSI ( input, MSISENSOR2_SCAN.out.scan, [] )
+}
+
+
+workflow test_msisensor2_msi_tumor_normal {
+
+    reference = [
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+
+    MSISENSOR2_SCAN ( reference, "outputfile" )
+
+    input = [
+        [ id:'test' ],
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam_bai'], checkIfExists: true),
+        [],
+    ]
+
+    MSISENSOR2_MSI ( input, MSISENSOR2_SCAN.out.scan, [] )
+}
+
+workflow test_msisensor2_msi_tumor_only_ml {
+
+    input = [
+        [ id:'test' ],
+        file('https://github.com/niu-lab/msisensor2/raw/master/test/example.tumor.only.hg19.bam', checkIfExists: true),
+        file('https://github.com/niu-lab/msisensor2/raw/master/test/example.tumor.only.hg19.bam.bai', checkIfExists: true),
+        [],
+        [],
+        [],
+    ]
+
+    models = Channel.fromPath(
+        [
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/016a16e12aca2bdba3713a3be76f72cd",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/02d42c2bda19aac304d6e86390c7f328",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/1030c0aa35ca5c263daeae866ad18632",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/15c3f5ec1c020d8f44283e40a2d9b6bb",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/15d6012f9a234b7adbbeecec524aea7d",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/2cf9a58f57e78b88acd86d792fe6a7b3",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/3ba04410c7ccbfc33e8b1b11d8132ae9",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/4431c9dc08be932c460a9e67192e7c57",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/4f5fa7bed97b48093375222d242fc982",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/71e6c0d59ea09d2a7acc566560841e34",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/8144b15900bba7086e86b31a0e1f8cfd",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/9bf6f7a544f369c3262a3a6f72cfdd7b",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/b8a36f2274b33cb0ed932e85cd1ddd5a",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/c08f164ded323a8c2606c408c555d73d",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/ceaa36ddbb76dc6eb6199ed946945788",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/e05d5da7208a924762311eddc4ec96c0",
+            "https://github.com/niu-lab/msisensor2/raw/master/test/tmp/models_hg19_17sites/f8a20acf51ccb2b0ce6af42f24a8b5ef",
+        ],
+        checkIfExists: true
+    )
+
+    MSISENSOR2_MSI ( input, [], models.collect() )
+}

tests/modules/msisensor2/msi/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}

tests/modules/msisensor2/msi/test.yml

@@ -0,0 +1,39 @@
+- name: msisensor2 msi test_msisensor2_msi_tumor_only
+  command: nextflow run ./tests/modules/msisensor2/msi -entry test_msisensor2_msi_tumor_only -c ./tests/config/nextflow.config  -c ./tests/modules/msisensor2/msi/nextflow.config
+  tags:
+    - msisensor2
+    - msisensor2/msi
+  files:
+    - path: output/msisensor2/outputfile
+      md5sum: b1fa373ada56fd5027b705d5e2faa374
+    - path: output/msisensor2/test
+      md5sum: a3290f7539dbbf83777e8590156c0e28
+    - path: output/msisensor2/test_dis
+      md5sum: 236e814ddeb95e21a17b48250f92250d
+    - path: output/msisensor2/test_somatic
+
+- name: msisensor2 msi test_msisensor2_msi_tumor_normal
+  command: nextflow run ./tests/modules/msisensor2/msi -entry test_msisensor2_msi_tumor_normal -c ./tests/config/nextflow.config  -c ./tests/modules/msisensor2/msi/nextflow.config
+  tags:
+    - msisensor2
+    - msisensor2/msi
+  files:
+    - path: output/msisensor2/outputfile
+      md5sum: b1fa373ada56fd5027b705d5e2faa374
+    - path: output/msisensor2/test
+      md5sum: a3290f7539dbbf83777e8590156c0e28
+    - path: output/msisensor2/test_dis
+      md5sum: d47b22c13092707ed64645f118e82cc1
+    - path: output/msisensor2/test_somatic
+
+- name: msisensor2 msi test_msisensor2_msi_tumor_only_ml
+  command: nextflow run ./tests/modules/msisensor2/msi -entry test_msisensor2_msi_tumor_only_ml -c ./tests/config/nextflow.config  -c ./tests/modules/msisensor2/msi/nextflow.config
+  tags:
+    - msisensor2
+    - msisensor2/msi
+  files:
+    - path: output/msisensor2/test
+      md5sum: a3290f7539dbbf83777e8590156c0e28
+    - path: output/msisensor2/test_dis
+      md5sum: 85205504ea8652ebdee46ac07ee1a8f6
+    - path: output/msisensor2/test_somatic

tests/modules/msisensor2/scan/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MSISENSOR2_SCAN } from '../../../../modules/msisensor2/scan/main.nf'
+
+workflow test_msisensor2_scan {
+
+    input = [
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome2_fasta'], checkIfExists: true)
+    ]
+
+    MSISENSOR2_SCAN ( input, "outputfile" )
+}

tests/modules/msisensor2/scan/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}

tests/modules/msisensor2/scan/test.yml

@@ -0,0 +1,8 @@
+- name: msisensor2 scan test_msisensor2_scan
+  command: nextflow run ./tests/modules/msisensor2/scan -entry test_msisensor2_scan -c ./tests/config/nextflow.config  -c ./tests/modules/msisensor2/scan/nextflow.config
+  tags:
+    - msisensor2/scan
+    - msisensor2
+  files:
+    - path: output/msisensor2/outputfile
+      md5sum: bdc0a576f37bd95a59692f387d083092