Tool/elprep split (#1533)

* tool: elprep split

* fixes for testing

* fix tests

* fix test outputs

* create test-yaml

* fix suggestions by @jfy133

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

modules/elprep/split/main.nf

@@ -0,0 +1,44 @@
+process ELPREP_SPLIT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::elprep=5.1.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/elprep:5.1.2--he881be0_0':
+        'quay.io/biocontainers/elprep:5.1.2--he881be0_0' }"
+
+    input:
+    tuple val(meta), path(bam)
+
+    output:
+    tuple val(meta), path("**.{bam,sam}"), emit: bam
+    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}"
+    meta.single_end ? args += " --single-end": ""
+
+    """
+    # create directory and move all input so elprep can find and merge them before splitting
+    mkdir input
+    mv ${bam} input/
+
+    mkdir ${prefix}
+
+    elprep split \\
+        input \\
+        . \\
+        $args \\
+        --nr-of-threads $task.cpus \\
+        --output-prefix $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        elprep: \$(elprep 2>&1 | head -n2 | tail -n1 |sed 's/^.*version //;s/ compiled.*\$//')
+    END_VERSIONS
+    """
+}

modules/elprep/split/meta.yml

@@ -0,0 +1,43 @@
+name: "elprep_split"
+description: Split bam file into manageable chunks
+keywords:
+  - bam
+  - split by chromosome
+tools:
+  - "elprep":
+      description: "elPrep is a high-performance tool for preparing .sam/.bam files for variant calling in sequencing pipelines. It can be used as a drop-in replacement for SAMtools/Picard/GATK4."
+      homepage: "https://github.com/ExaScience/elprep"
+      documentation: "https://github.com/ExaScience/elprep"
+      tool_dev_url: "https://github.com/ExaScience/elprep"
+      doi: "10.1371"
+      licence: "['AGPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: List of BAM/SAM files
+      pattern: "*.{bam,sam}"
+
+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"
+  - bam:
+      type: file
+      description: List of split BAM/SAM files
+      pattern: "*.{bam,sam}"
+
+authors:
+  - "@matthdsm"

tests/config/pytest_modules.yml

@@ -599,6 +599,10 @@ ectyper:
   - modules/ectyper/**
   - tests/modules/ectyper/**
 
+elprep/split:
+  - modules/elprep/split/**
+  - tests/modules/elprep/split/**
+
 emmtyper:
   - modules/emmtyper/**
   - tests/modules/emmtyper/**

tests/modules/elprep/split/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ELPREP_SPLIT } from '../../../../modules/elprep/split/main.nf'
+
+workflow test_elprep_split {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
+    ]
+
+    ELPREP_SPLIT ( input )
+}

tests/modules/elprep/split/nextflow.config

@@ -0,0 +1,9 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName : ELPREP_SPLIT {
+        ext.args = "--contig-group-size 1 --output-type bam"
+    }
+
+}

tests/modules/elprep/split/test.yml

@@ -0,0 +1,10 @@
+- name: elprep split test_elprep_split
+  command: nextflow run tests/modules/elprep/split -entry test_elprep_split -c tests/config/nextflow.config
+  tags:
+    - elprep
+    - elprep/split
+  files:
+    - path: output/elprep/splits/test-group00001.bam
+    - path: output/elprep/splits/test-unmapped.bam
+    - path: output/elprep/test-spread.bam
+    - path: output/elprep/versions.yml