New module: umitools/group (#3765)

* init umitools/group

* remove todo's umitools/group

* fix prettier

* remove redundant variables stub

modules/nf-core/umitools/group/main.nf

@@ -0,0 +1,62 @@
+process UMITOOLS_GROUP {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "bioconda::umi_tools=1.1.4"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/umi_tools:1.1.4--py38hbff2b2d_1' :
+        'biocontainers/umi_tools:1.1.4--py38hbff2b2d_1' }"
+
+    input:
+    tuple val(meta), path(bam), path(bai)
+    val create_bam
+    val get_group_info
+
+    output:
+    tuple val(meta), path("*.log")        , emit: log
+    tuple val(meta), path("${prefix}.bam"), optional: true, emit: bam
+    tuple val(meta), path("*.tsv")        , optional: true, emit: tsv
+    path "versions.yml"                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args    = task.ext.args   ?: ''
+    prefix      = task.ext.prefix ?: "${meta.id}"
+    def paired  = meta.single_end ? "" : "--paired"
+    output_bam  = create_bam      ? "--output-bam -S ${prefix}.bam" : ""
+    group_info  = get_group_info  ? "--group-out ${prefix}.tsv"     : ""
+
+    if (create_bam && "$bam" == "${prefix}.bam") { error "Input and output names are the same, set prefix in module configuration to disambiguate!" }
+
+    if (!(args ==~ /.*--random-seed.*/)) {args += " --random-seed=100"}
+    """
+    PYTHONHASHSEED=0 umi_tools \\
+        group \\
+        -I $bam \\
+        $output_bam \\
+        -L ${prefix}.log \\
+        $group_info \\
+        $paired \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        umitools: \$(umi_tools --version 2>&1 | sed 's/^.*UMI-tools version://; s/ *\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.bam
+    touch ${prefix}.log
+    touch ${prefix}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        umitools: \$(umi_tools --version 2>&1 | sed 's/^.*UMI-tools version://; s/ *\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/umitools/group/meta.yml

@@ -0,0 +1,62 @@
+name: umitools_group
+description: Group reads based on their UMI and mapping coordinates
+keywords:
+  - umitools
+  - umi
+  - deduplication
+  - dedup
+  - clustering
+tools:
+  - umi_tools:
+      description: >
+        UMI-tools contains tools for dealing with Unique Molecular Identifiers (UMIs)/Random Molecular Tags (RMTs)
+        and single cell RNA-Seq cell barcodes
+      documentation: https://umi-tools.readthedocs.io/en/latest/
+      license: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: |
+        BAM file containing reads to be deduplicated via UMIs.
+      pattern: "*.{bam}"
+  - bai:
+      type: file
+      description: |
+        BAM index files corresponding to the input BAM file.
+      pattern: "*.{bai}"
+  - create_bam:
+      type: boolean
+      description: |
+        Whether or not to create a read group tagged BAM file.
+  - get_group_info:
+      type: boolean
+      description: |
+        Whether or not to generate the flatfile describing the read groups, see docs for complete info of all columns
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: a read group tagged BAM file.
+      pattern: "${prefix}.{bam}"
+  - log:
+      type: file
+      description: File with logging information
+      pattern: "*.{log}"
+  - tsv:
+      type: file
+      description: Flatfile describing the read groups, see docs for complete info of all columns
+      pattern: "*.{tsv}"
+
+authors:
+  - "@Joon-Klaps"

tests/config/pytest_modules.yml

@@ -4029,6 +4029,10 @@ umitools/extract:
   - modules/nf-core/umitools/extract/**
   - tests/modules/nf-core/umitools/extract/**
 
+umitools/group:
+  - modules/nf-core/umitools/group/**
+  - tests/modules/nf-core/umitools/group/**
+
 unicycler:
   - modules/nf-core/unicycler/**
   - tests/modules/nf-core/unicycler/**

tests/modules/nf-core/umitools/group/main.nf

@@ -0,0 +1,96 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { UMITOOLS_EXTRACT                               } from '../../../../../modules/nf-core/umitools/extract/main.nf'
+include { BWA_INDEX                                      } from '../../../../../modules/nf-core/bwa/index/main.nf'
+include { BWA_MEM                                        } from '../../../../../modules/nf-core/bwa/mem/main.nf'
+include { SAMTOOLS_INDEX                                 } from '../../../../../modules/nf-core/samtools/index/main.nf'
+include { UMITOOLS_GROUP         } from '../../../../../modules/nf-core/umitools/group/main.nf'
+
+//
+// Test with no UMI
+//
+workflow test_umitools_group_no_umi {
+    input = [
+        [ id:'test'], // meta map
+        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)
+    ]
+    create_bam     = true
+    get_group_info = true
+
+    UMITOOLS_GROUP ( input, create_bam, get_group_info )
+}
+
+//
+// Test with single-end data with BAM false and group info true
+//
+workflow test_umitools_group_single_end_info {
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+    ]
+    fasta = [
+        [ id:'sarscov2'],
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+    create_bam     = false
+    get_group_info = true
+
+    UMITOOLS_EXTRACT ( input )
+    BWA_INDEX ( fasta )
+    BWA_MEM ( UMITOOLS_EXTRACT.out.reads, BWA_INDEX.out.index, true )
+    SAMTOOLS_INDEX ( BWA_MEM.out.bam )
+    UMITOOLS_GROUP ( BWA_MEM.out.bam.join(SAMTOOLS_INDEX.out.bai, by: [0]), create_bam, get_group_info )
+}
+
+//
+// Test with paired-end data with BAM true and group info false
+//
+workflow test_umitools_group_paired_end_bam {
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+    fasta = [
+        [ id:'sarscov2'],
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+    create_bam     = true
+    get_group_info = false
+
+    UMITOOLS_EXTRACT ( input )
+    BWA_INDEX ( fasta )
+    BWA_MEM ( UMITOOLS_EXTRACT.out.reads, BWA_INDEX.out.index, true )
+    SAMTOOLS_INDEX ( BWA_MEM.out.bam )
+    UMITOOLS_GROUP ( BWA_MEM.out.bam.join(SAMTOOLS_INDEX.out.bai, by: [0]), create_bam, get_group_info )
+}
+
+//
+// Test with paired-end data BAM true and group info true
+//
+workflow test_umitools_group_paired_bam_info {
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+    fasta = [
+        [ id:'sarscov2'],
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+    create_bam     = true
+    get_group_info = true
+
+    UMITOOLS_EXTRACT ( input )
+    BWA_INDEX ( fasta )
+    BWA_MEM ( UMITOOLS_EXTRACT.out.reads, BWA_INDEX.out.index, true )
+    SAMTOOLS_INDEX ( BWA_MEM.out.bam )
+    UMITOOLS_GROUP ( BWA_MEM.out.bam.join(SAMTOOLS_INDEX.out.bai, by: [0]), create_bam, get_group_info )
+}

tests/modules/nf-core/umitools/group/nextflow.config

@@ -0,0 +1,27 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+
+    withName: BWA_INDEX {
+        publishDir = [enabled : false ]
+    }
+
+    withName: BWA_MEM {
+        publishDir = [enabled : false ]
+    }
+
+    withName: SAMTOOLS_INDEX {
+        publishDir = [enabled : false ]
+    }
+
+    withName: UMITOOLS_EXTRACT {
+        ext.args = '--bc-pattern="NNNN"'
+        publishDir = [ enabled : false ]
+    }
+
+    withName: UMITOOLS_GROUP {
+        ext.prefix = { "${meta.id}.group" }
+    }
+
+}

tests/modules/nf-core/umitools/group/test.yml

@@ -0,0 +1,51 @@
+- name: umitools group test_umitools_group_no_umi
+  command: nextflow run ./tests/modules/nf-core/umitools/group -entry test_umitools_group_no_umi -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/umitools/group/nextflow.config
+  tags:
+    - umitools/group
+    - umitools
+  files:
+    - path: output/umitools/test.group.bam
+      md5sum: fb90b49a90c2b3e8ddfedd9c95361625
+    - path: output/umitools/test.group.log
+      contains: ["# UMI-tools version:"]
+    - path: output/umitools/test.group.tsv
+      md5sum: 1a3ccdc00df59fa89c79ad482980a003
+    - path: output/umitools/versions.yml
+
+- name: umitools group test_umitools_group_single_end_info
+  command: nextflow run ./tests/modules/nf-core/umitools/group -entry test_umitools_group_single_end_info -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/umitools/group/nextflow.config
+  tags:
+    - umitools/group
+    - umitools
+  files:
+    - path: output/umitools/test.group.log
+      contains: ["# UMI-tools version:"]
+    - path: output/umitools/test.group.tsv
+      md5sum: e7d46166eb3d8f42d73032e44f313b71
+    - path: output/umitools/versions.yml
+
+- name: umitools group test_umitools_group_paired_end_bam
+  command: nextflow run ./tests/modules/nf-core/umitools/group -entry test_umitools_group_paired_end_bam -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/umitools/group/nextflow.config
+  tags:
+    - umitools/group
+    - umitools
+  files:
+    - path: output/umitools/test.group.bam
+      md5sum: 8f9250416a7ccbe970f5034826c318f5
+    - path: output/umitools/test.group.log
+      contains: ["# UMI-tools version:"]
+    - path: output/umitools/versions.yml
+
+- name: umitools group test_umitools_group_paired_bam_info
+  command: nextflow run ./tests/modules/nf-core/umitools/group -entry test_umitools_group_paired_bam_info -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/umitools/group/nextflow.config
+  tags:
+    - umitools/group
+    - umitools
+  files:
+    - path: output/umitools/test.group.bam
+      md5sum: 8f9250416a7ccbe970f5034826c318f5
+    - path: output/umitools/test.group.log
+      contains: ["# UMI-tools version:"]
+    - path: output/umitools/test.group.tsv
+      md5sum: d652eb6570057e9e709e8cac5f43d00c
+    - path: output/umitools/versions.yml