add samtools/bamtocram modules (#1561)

* add new samtools/bamtocram module

* fix md5sum

* remove md5sum

* Update modules/samtools/bamtocram/main.nf

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

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

modules/samtools/bamtocram/main.nf

@@ -0,0 +1,35 @@
+//There is a -L option to only output alignments in interval, might be an option for exons/panel data?
+process SAMTOOLS_BAMTOCRAM {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' :
+        'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }"
+
+    input:
+    tuple val(meta), path(input), path(index)
+    path  fasta
+    path  fai
+
+    output:
+    tuple val(meta), path("*.cram"), path("*.crai"), emit: cram_crai
+    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}"
+    """
+    samtools view --threads ${task.cpus} --reference ${fasta} -C $args $input > ${prefix}.cram
+    samtools index -@${task.cpus} ${prefix}.cram
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/samtools/bamtocram/meta.yml

@@ -0,0 +1,52 @@
+name: samtools_bamtocram
+description: filter/convert and then index CRAM file
+keywords:
+  - view
+  - index
+  - bam
+  - cram
+tools:
+  - samtools:
+      description: |
+        SAMtools is a set of utilities for interacting with and post-processing
+        short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li.
+        These files are generated as output by short read aligners like BWA.
+      homepage: http://www.htslib.org/
+      documentation: hhttp://www.htslib.org/doc/samtools.html
+      doi: 10.1093/bioinformatics/btp352
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: BAM/SAM file
+      pattern: "*.{bam,sam}"
+  - index:
+      type: file
+      description: BAM/SAM index file
+      pattern: "*.{bai,sai}"
+  - fasta:
+      type: file
+      description: Reference file to create the CRAM file
+      pattern: "*.{fasta,fa}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - cram_crai:
+      type: file
+      description: filtered/converted CRAM file + index
+      pattern: "*{.cram,.crai}"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+authors:
+  - "@FriederikeHanssen"
+  - "@maxulysse"

tests/config/pytest_modules.yml

@@ -1595,6 +1595,10 @@ samtools/bam2fq:
   - modules/samtools/bam2fq/**
   - tests/modules/samtools/bam2fq/**
 
+samtools/bamtocram:
+  - modules/samtools/bamtocram/**
+  - tests/modules/samtools/bamtocram/**
+
 samtools/collatefastq:
   - modules/samtools/collatefastq/**
   - tests/modules/samtools/collatefastq/**

tests/modules/samtools/bamtocram/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SAMTOOLS_BAMTOCRAM } from '../../../../modules/samtools/bamtocram/main.nf'
+
+workflow test_samtools_bamtocram {
+
+    input = [ [ id:'test', single_end:false ], // 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)]
+
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    fai   = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+
+    SAMTOOLS_BAMTOCRAM ( input, fasta, fai )
+}

tests/modules/samtools/bamtocram/nextflow.config

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

tests/modules/samtools/bamtocram/test.yml

@@ -0,0 +1,9 @@
+- name: samtools bamtocram test_samtools_bamtocram
+  command: nextflow run ./tests/modules/samtools/bamtocram -entry test_samtools_bamtocram -c ./tests/config/nextflow.config -c ./tests/modules/samtools/bamtocram/nextflow.config
+  tags:
+    - samtools/bamtocram
+    - samtools
+  files:
+    - path: output/samtools/test.cram
+    - path: output/samtools/test.cram.crai
+    - path: output/samtools/versions.yml