Merge branch 'master' into motus_profile

modules/bedtools/split/main.nf

@@ -0,0 +1,38 @@
+process BEDTOOLS_SPLIT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::bedtools=2.30.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bedtools:2.30.0--h468198e_3':
+        'quay.io/biocontainers/bedtools:2.30.0--h7d7f7ad_2' }"
+
+    input:
+    tuple val(meta), path(bed)
+    val(number_of_files)
+
+    output:
+    tuple val(meta), path("*.bed"), emit: beds
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    bedtools \\
+        split \\
+        $args \\
+        -i $bed \\
+        -p $prefix \\
+        -n $number_of_files
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+}

modules/bedtools/split/meta.yml

@@ -0,0 +1,41 @@
+name: "bedtools_split"
+description: Split BED files into several smaller BED files
+keywords:
+  - sort
+tools:
+  - "bedtools":
+      description: "A powerful toolset for genome arithmetic"
+      documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/sort.html"
+      licence: "['MIT', 'GPL v2']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+  - bed:
+      type: value
+      description: The number of files to split the BED into
+
+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"
+  - beds:
+      type: file
+      description: list of split BED files
+      pattern: "*.bed"
+
+authors:
+  - "@nvnieuwk"

modules/biobambam/bammerge/main.nf

@@ -0,0 +1,38 @@
+process BIOBAMBAM_BAMMERGE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::biobambam=2.0.183" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/biobambam:2.0.183--h9f5acd7_1':
+        'quay.io/biocontainers/biobambam:2.0.183--h9f5acd7_1' }"
+
+    input:
+    tuple val(meta), path(bam)
+
+    output:
+    tuple val(meta), path("${prefix}.bam")  ,emit: bam
+    tuple val(meta), path("*.bai")          ,optional:true, emit: bam_index
+    tuple val(meta), path("*.md5")          ,optional:true, emit: checksum
+    path "versions.yml"                     ,emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    def input_string = bam.join(" I=")
+
+    """
+    bammerge \\
+        I=${input_string} \\
+        $args \\
+        > ${prefix}.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bammerge: \$( bammerge --version |& sed '1!d; s/.*version //; s/.\$//' )
+    END_VERSIONS
+    """
+}

modules/biobambam/bammerge/meta.yml

@@ -0,0 +1,46 @@
+name: biobambam_bammerge
+description: Merge a list of sorted bam files
+keywords:
+  - merge
+  - bam
+tools:
+  - biobambam:
+      description: |
+        biobambam is a set of tools for early stage alignment file processing.
+      homepage: https://gitlab.com/german.tischler/biobambam2
+      documentation: https://gitlab.com/german.tischler/biobambam2/-/blob/master/README.md
+      doi: 10.1186/1751-0473-9-13
+      licence: ["GPL v3"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: List containing 1 or more bam files
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: Merged BAM file
+      pattern: "*.bam"
+  - bam_index:
+      type: file
+      description: BAM index file
+      pattern: "*"
+  - checksum:
+      type: file
+      description: Checksum file
+      pattern: "*"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@matthdsm"

modules/hmtnote/main.nf

@@ -0,0 +1,45 @@
+process HMTNOTE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::hmtnote=0.7.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/hmtnote:0.7.2--pyhdfd78af_0':
+        'quay.io/biocontainers/hmtnote:0.7.2--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(vcf)
+
+    output:
+    tuple val(meta), path("*_annotated.vcf"), emit: vcf
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    hmtnote \\
+        annotate \\
+        $vcf \\
+        ${prefix}_annotated.vcf \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        hmtnote: \$(echo \$(hmtnote --version 2>&1) | sed 's/^.*hmtnote, version //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_annotated.vcf
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        hmtnote: \$(echo \$(hmtnote --version 2>&1) | sed 's/^.*hmtnote, version //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+}

modules/hmtnote/meta.yml

@@ -0,0 +1,39 @@
+name: hmtnote
+description: Human mitochondrial variants annotation using HmtVar.
+keywords:
+  - hmtnote mitochondria annotation
+tools:
+  - hmtnote:
+      description: Human mitochondrial variants annotation using HmtVar.
+      homepage: https://github.com/robertopreste/HmtNote
+      documentation: https://hmtnote.readthedocs.io/en/latest/usage.html
+      tool_dev_url: None
+      doi: "https://doi.org/10.1101/600619"
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+  - vcf:
+      type: file
+      description: vcf file
+      pattern: "*.vcf"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - vcf:
+      type: file
+      description: annotated vcf
+      pattern: "*_annotated.vcf"
+
+authors:
+  - "@sysbiocoder"

tests/config/nextflow.config

@@ -19,6 +19,7 @@ if ("$PROFILE" == "singularity") {
 } else {
     docker.enabled = true
     docker.userEmulation = true
+    docker.runOptions = "--platform linux/x86_64"
 }
 
 // Increase time available to build Conda environment

tests/config/pytest_modules.yml

@@ -222,6 +222,10 @@ bedtools/sort:
   - modules/bedtools/sort/**
   - tests/modules/bedtools/sort/**
 
+bedtools/split:
+  - modules/bedtools/split/**
+  - tests/modules/bedtools/split/**
+
 bedtools/subtract:
   - modules/bedtools/subtract/**
   - tests/modules/bedtools/subtract/**
@@ -230,6 +234,10 @@ biobambam/bammarkduplicates2:
   - modules/biobambam/bammarkduplicates2/**
   - tests/modules/biobambam/bammarkduplicates2/**
 
+biobambam/bammerge:
+  - modules/biobambam/bammerge/**
+  - tests/modules/biobambam/bammerge/**
+
 biobambam/bamsormadup:
   - modules/biobambam/bamsormadup/**
   - tests/modules/biobambam/bamsormadup/**
@@ -966,6 +974,10 @@ hmmer/hmmsearch:
   - modules/hmmer/hmmsearch/**
   - tests/modules/hmmer/hmmsearch/**
 
+hmtnote:
+  - modules/hmtnote/**
+  - tests/modules/hmtnote/**
+
 homer/annotatepeaks:
   - modules/homer/annotatepeaks/**
   - tests/modules/homer/annotatepeaks/**

tests/modules/bedtools/split/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BEDTOOLS_SPLIT } from '../../../../modules/bedtools/split/main.nf'
+
+workflow test_bedtools_split {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['genome']['genome_multi_interval_bed'], checkIfExists: true)
+    ]
+
+    number_of_files = 2
+
+    BEDTOOLS_SPLIT ( input, number_of_files )
+}

tests/modules/bedtools/split/nextflow.config

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

tests/modules/bedtools/split/test.yml

@@ -0,0 +1,10 @@
+- name: bedtools split test_bedtools_split
+  command: nextflow run ./tests/modules/bedtools/split -entry test_bedtools_split -c ./tests/config/nextflow.config  -c ./tests/modules/bedtools/split/nextflow.config
+  tags:
+    - bedtools
+    - bedtools/split
+  files:
+    - path: output/bedtools/test.00001.bed
+      md5sum: d58e5e46c2fcc3b8be5db0f023e93cb5
+    - path: output/bedtools/test.00002.bed
+      md5sum: 03caf952e9297a54620d2bbba8dc2823

tests/modules/biobambam/bammerge/main.nf

@@ -0,0 +1,30 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BIOBAMBAM_BAMMERGE } from '../../../../modules/biobambam/bammerge/main.nf'
+
+workflow test_biobambam_bammerge_paired {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [
+            file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+            file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true)
+        ]
+    ]
+
+    BIOBAMBAM_BAMMERGE ( input )
+}
+
+workflow test_biobambam_bammerge_single {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_single_end_sorted_bam'], checkIfExists: true),
+        ]
+    ]
+
+    BIOBAMBAM_BAMMERGE ( input )
+}

tests/modules/biobambam/bammerge/nextflow.config

@@ -0,0 +1,13 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    withName: BIOBAMBAM_BAMMERGE {
+        ext.args = {[
+            "md5=1",
+            "md5filename=${meta.id}.md5",
+            "index=1",
+            "indexfilename=${meta.id}.bam.bai"
+        ].join(" ").trim()}
+    }
+
+}

tests/modules/biobambam/bammerge/test.yml

@@ -0,0 +1,25 @@
+- name: biobambam bammerge test_biobambam_bammerge_paired
+  command: nextflow run ./tests/modules/biobambam/bammerge -entry test_biobambam_bammerge_paired -c ./tests/config/nextflow.config  -c ./tests/modules/biobambam/bammerge/nextflow.config
+  tags:
+    - biobambam/bammerge
+    - biobambam
+  files:
+    - path: output/biobambam/test.bam
+      md5sum: bc3d32ab6a54d1894ca7cc79387dec57
+    - path: output/biobambam/test.bam.bai
+      md5sum: b8ae542a37a73d79de1c15c765207c53
+    - path: output/biobambam/test.md5
+      md5sum: 31c59857990ceb392242136429e30243
+
+- name: biobambam bammerge test_biobambam_bammerge_single
+  command: nextflow run ./tests/modules/biobambam/bammerge -entry test_biobambam_bammerge_single -c ./tests/config/nextflow.config  -c ./tests/modules/biobambam/bammerge/nextflow.config
+  tags:
+    - biobambam/bammerge
+    - biobambam
+  files:
+    - path: output/biobambam/test.bam
+      md5sum: 86185d3d6895a7722d3b3a09c6f91bfc
+    - path: output/biobambam/test.bam.bai
+      md5sum: 973680feb6bc73cd1051ea83c7219418
+    - path: output/biobambam/test.md5
+      md5sum: 244a9d1cbc6d74724285c80220e5e427

tests/modules/hmtnote/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { HMTNOTE } from '../../../modules/hmtnote/main.nf'
+
+workflow test_hmtnote {
+    
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
+            ]
+
+    HMTNOTE ( input)
+}

tests/modules/hmtnote/nextflow.config

@@ -0,0 +1,7 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    withName: HMTNOTE {
+        ext.args = '--basic --variab'
+    }
+}

tests/modules/hmtnote/test.yml

@@ -0,0 +1,6 @@
+- name: hmtnote test_hmtnote
+  command: nextflow run ./tests/modules/hmtnote -entry test_hmtnote -c ./tests/config/nextflow.config -c ./tests/modules/hmtnote/nextflow.config
+  tags:
+    - hmtnote
+  files:
+    - path: output/hmtnote/test_annotated.vcf