New tool: biobambam/bamsormadup (#1478)

* add bamsormadup

* fix yaml

* add test.yml

* Update tests/modules/biobambam/bamsormadup/test.yml

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

* test meta.yaml: remove md5sums

* Tool bamsormadup:
- add (optional) reference input
- add bam index ouput
- add cram output option
- make metrics output: more general

* fix input and output formats

* update input file description

* drop sam output, goes against nf-core regs; add input check for cram files

* fix typo

* Update modules/biobambam/bamsormadup/main.nf

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

* improve ref fasta name

* fix if else shorthand

* fix syntax error

* kind of fix tests

* set fixed suffix for metrics file to keep it in line with picard and bammarkduplicates2

* fix command line

* update test.yml

* add support for multiple input bams

* Update modules/biobambam/bamsormadup/meta.yml

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

* Update modules/biobambam/bamsormadup/meta.yml

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

* Update tests/modules/biobambam/bamsormadup/test.yml

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

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

modules/biobambam/bamsormadup/main.nf

@@ -0,0 +1,46 @@
+process BIOBAMBAM_BAMSORMADUP {
+    tag "$meta.id"
+    label "process_medium"
+
+    conda (params.enable_conda ? "bioconda::biobambam=2.0.183" : null)
+    container "${ 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(bams)
+    path(fasta)
+
+    output:
+    tuple val(meta), path("*.{bam,cram}")       ,emit: bam
+    tuple val(meta), path("*.bam.bai")          ,optional:true, emit: bam_index
+    tuple val(meta), path("*.metrics.txt")      ,emit: metrics
+    path "versions.yml"                         ,emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def suffix = args.contains("outputformat=cram") ? "cram" : "bam"
+    def input_string = bams.join(" I=")
+
+    if (args.contains("outputformat=cram") && reference == null) error "Reference required for CRAM output."
+
+    """
+    bamcat \\
+        I=${input_string} \\
+        level=0 \\
+    | bamsormadup \\
+        $args \\
+        M=${prefix}.metrics.txt \\
+        tmpfile=$prefix \\
+        threads=$task.cpus \\
+        > ${prefix}.${suffix}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bamcat: \$(echo \$(bamsormadup --version 2>&1) | sed 's/^This is biobambam2 version //; s/..biobambam2 is .*\$//' )
+        bamsormadup: \$(echo \$(bamsormadup --version 2>&1) | sed 's/^This is biobambam2 version //; s/..biobambam2 is .*\$//' )
+    END_VERSIONS
+    """
+}

modules/biobambam/bamsormadup/meta.yml

@@ -0,0 +1,52 @@
+name: biobambam_bamsormadup
+description: Parallel sorting and duplicate marking
+keywords:
+  - markduplicates
+  - sort
+  - bam
+  - cram
+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 ]
+  - bams:
+      type: file
+      description: List containing 1 or more bam files
+  - fasta:
+      type: file
+      description: Reference genome in FASTA format (optional)
+      pattern: "*.{fa,fasta}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: BAM/CRAM file with duplicate reads marked/removed
+      pattern: "*.{bam,cram}"
+  - bam_index:
+      type: file
+      description: BAM index file
+      pattern: "*.{bai}"
+  - metrics:
+      type: file
+      description: Duplicate metrics file generated by biobambam
+      pattern: "*.{metrics.txt}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@matthdsm"

tests/config/pytest_modules.yml

@@ -214,6 +214,10 @@ biobambam/bammarkduplicates2:
   - modules/biobambam/bammarkduplicates2/**
   - tests/modules/biobambam/bammarkduplicates2/**
 
+biobambam/bamsormadup:
+  - modules/biobambam/bamsormadup/**
+  - tests/modules/biobambam/bamsormadup/**
+
 biscuit/align:
   - modules/biscuit/index/**
   - modules/biscuit/align/**

tests/modules/biobambam/bamsormadup/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BIOBAMBAM_BAMSORMADUP } from '../../../../modules/biobambam/bamsormadup/main.nf'
+
+workflow test_biobambam_bamsormadup {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true), file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)],
+    ]
+
+    BIOBAMBAM_BAMSORMADUP ( input, [] )
+}

tests/modules/biobambam/bamsormadup/nextflow.config

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

tests/modules/biobambam/bamsormadup/test.yml

@@ -0,0 +1,11 @@
+- name: biobambam bamsormadup test_biobambam_bamsormadup
+  command: nextflow run tests/modules/biobambam/bamsormadup -entry test_biobambam_bamsormadup -c tests/config/nextflow.config
+  tags:
+    - biobambam/bamsormadup
+    - biobambam
+  files:
+    - path: output/biobambam/test.bam
+      md5sum: 243a77fb0642fd46bb16a4d3432d19dc
+    - path: output/biobambam/test.metrics.txt
+      md5sum: 1721879bea1f3888ecd33b35e6ee0e72
+    - path: output/biobambam/versions.yml