Add samtools stats for short-reads

assets/multiqc_config.yml

@@ -21,6 +21,7 @@ run_modules:
   - adapterRemoval
   - fastp
   - bowtie2
+  - samtools
   - kraken
   - malt
   - custom_content

conf/modules.config

@@ -233,6 +233,18 @@ process {
         ]
     }
 
+     withName: SAMTOOLS_STATS {
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/samtools/stats" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_unmapped,
+            pattern: '*stats'
+        ]
+    }
+
+
+
     withName: BBMAP_BBDUK {
         ext.args =  [
                 "entropy=${params.shortread_complexityfilter_entropy}",

modules.json

@@ -153,6 +153,14 @@
                         "branch": "master",
                         "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
                     },
+                    "samtools/index": {
+                        "branch": "master",
+                        "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
+                    },
+                    "samtools/stats": {
+                        "branch": "master",
+                        "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
+                    },
                     "samtools/view": {
                         "branch": "master",
                         "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"

modules/nf-core/samtools/index/main.nf

@@ -0,0 +1,48 @@
+process SAMTOOLS_INDEX {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
+    container "${ 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)
+
+    output:
+    tuple val(meta), path("*.bai") , optional:true, emit: bai
+    tuple val(meta), path("*.csi") , optional:true, emit: csi
+    tuple val(meta), path("*.crai"), optional:true, emit: crai
+    path  "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    samtools \\
+        index \\
+        -@ ${task.cpus-1} \\
+        $args \\
+        $input
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    touch ${input}.bai
+    touch ${input}.crai
+    touch ${input}.csi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/samtools/index/meta.yml

@@ -0,0 +1,53 @@
+name: samtools_index
+description: Index SAM/BAM/CRAM file
+keywords:
+  - index
+  - bam
+  - sam
+  - 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 ]
+  - bam:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bai:
+      type: file
+      description: BAM/CRAM/SAM index file
+      pattern: "*.{bai,crai,sai}"
+  - crai:
+      type: file
+      description: BAM/CRAM/SAM index file
+      pattern: "*.{bai,crai,sai}"
+  - csi:
+      type: file
+      description: CSI index file
+      pattern: "*.{csi}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@drpatelh"
+  - "@ewels"
+  - "@maxulysse"

modules/nf-core/samtools/stats/main.nf

@@ -0,0 +1,49 @@
+process SAMTOOLS_STATS {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
+    container "${ 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(input_index)
+    path fasta
+
+    output:
+    tuple val(meta), path("*.stats"), emit: stats
+    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 reference = fasta ? "--reference ${fasta}" : ""
+    """
+    samtools \\
+        stats \\
+        --threads ${task.cpus} \\
+        ${reference} \\
+        ${input} \\
+        > ${prefix}.stats
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.stats
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/samtools/stats/meta.yml

@@ -0,0 +1,53 @@
+name: samtools_stats
+description: Produces comprehensive statistics from SAM/BAM/CRAM file
+keywords:
+  - statistics
+  - counts
+  - bam
+  - sam
+  - 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/CRAM file from alignment
+    pattern: "*.{bam,cram}"
+  - input_index:
+    type: file
+    description: BAI/CRAI file from alignment
+    pattern: "*.{bai,crai}"
+  - fasta:
+      type: optional file
+      description: Reference file the CRAM was created with
+      pattern: "*.{fasta,fa}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - stats:
+      type: file
+      description: File containing samtools stats output
+      pattern: "*.{stats}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@drpatelh"
+  - "@FriederikeHanssen"

subworkflows/local/shortread_hostremoval.nf

@@ -4,6 +4,8 @@
 
 include { BOWTIE2_BUILD             } from '../../modules/nf-core/bowtie2/build/main'
 include { BOWTIE2_ALIGN             } from '../../modules/nf-core/bowtie2/align/main'
+include { SAMTOOLS_INDEX             } from '../../modules/nf-core/samtools/index/main'
+include { SAMTOOLS_STATS             } from '../../modules/nf-core/samtools/stats/main'
 
 workflow SHORTREAD_HOSTREMOVAL {
     take:
@@ -26,7 +28,17 @@ workflow SHORTREAD_HOSTREMOVAL {
     ch_versions      = ch_versions.mix( BOWTIE2_ALIGN.out.versions.first() )
     ch_multiqc_files = ch_multiqc_files.mix( BOWTIE2_ALIGN.out.log )
 
+    SAMTOOLS_INDEX ( BOWTIE2_ALIGN.out.bam )
+
+    bam_bai = BOWTIE2_ALIGN.out.bam
+        .join(SAMTOOLS_INDEX.out.bai, remainder: true)
+
+    SAMTOOLS_STATS ( bam_bai, reference )
+    ch_versions = ch_versions.mix(SAMTOOLS_STATS.out.versions.first())
+    ch_multiqc_files = ch_multiqc_files.mix( SAMTOOLS_STATS.out.stats )
+
     emit:
+    stats    = SAMTOOLS_STATS.out.stats 
     reads    = BOWTIE2_ALIGN.out.fastq   // channel: [ val(meta), [ reads ] ]
     versions = ch_versions               // channel: [ versions.yml ]
     mqc      = ch_multiqc_files