Fix the coverage report, we were using the samtools flags for decont. instead of mapping

assets/multiqc_config.yml

@@ -20,3 +20,6 @@ top_modules:
 sp:
   quast_config:
     fn: "*.tsv"
+
+section_comments:
+  Samtools: Assembly coverage

conf/modules.config

@@ -72,28 +72,33 @@ process {
         ]
     }
 
-    withName: 'BWAMEM2_MEM' {
+    // This BWAMEM2_MEM belongs to the coverage module
+    withName: 'BWAMEM2_MEM_COVERAGE' {
         cpus   = { check_max( 12    * task.attempt, 'cpus'    ) }
-        memory = { check_max( 72.GB * task.attempt, 'memory'  ) }
-        time   = { check_max( 16.h  * task.attempt, 'time'    ) }
+        memory = { check_max( 12.GB * task.attempt, 'memory'  ) }
+        time   = { check_max( 1.h  * task.attempt,  'time'    ) }
 
         ext.args  = "-M"
-        ext.args2 = [
-            '-f',
-            '12',
-            '-F',
-            '256',
-            '-uS',
-        ].join(' ').trim()
+        ext.args2 = "-F 268 -uS"
     }
 
-    withName: 'SAMTOOLS_BAM2FQ' {
+    /* Decontamination */
+    withName: 'BWAMEM2DECONTNOBAMS' {
         cpus   = { check_max( 2     * task.attempt, 'cpus'    ) }
-        memory = { check_max( 12.GB * task.attempt, 'memory'  ) }
         time   = { check_max( 4.h   * task.attempt, 'time'    ) }
-        ext.prefix = "decontaminated"
+        ext.prefix = { "${meta2.id}_decontaminated" }
+    }
+
+    withName: 'HUMAN_PHIX_DECONTAMINATION' {
+        memory = { check_max( 64.GB * task.attempt, 'memory'  ) }
+    }
+
+    withName: 'HOST_DECONTAMINATION' {
+        memory = { check_max( 24.GB * task.attempt, 'memory'  ) }
     }
+    /* --------- */
 
+    /* Assembly */
     withName: 'SPADES' {
         memory = { check_max(params.assembly_memory.GB * task.attempt, 'memory') }
         cpus   = { check_max( 32 * task.attempt, 'cpus') }

modules.json

@@ -8,22 +8,12 @@
                     "bwamem2/mem": {
                         "branch": "main",
                         "git_sha": "75707538d91ddd27fb6007b4ac3710cb05154780",
-                        "installed_by": ["reads_bwamem2_decontamination"]
+                        "installed_by": ["modules"]
                     },
-                    "samtools/bam2fq": {
-                        "branch": "main",
-                        "git_sha": "88f2bfbe6f0ba858d0833db590e647c4678656a7",
-                        "installed_by": ["reads_bwamem2_decontamination"],
-                        "patch": "modules/ebi-metagenomics/samtools/bam2fq/samtools-bam2fq.diff"
-                    }
-                }
-            },
-            "subworkflows": {
-                "ebi-metagenomics": {
-                    "reads_bwamem2_decontamination": {
+                    "bwamem2decontnobams": {
                         "branch": "main",
-                        "git_sha": "0b40060df67681e0172aab145460618c08d99516",
-                        "installed_by": ["subworkflows"]
+                        "git_sha": "32049180387cf2406254acf57882fc55915cb52e",
+                        "installed_by": ["modules"]
                     }
                 }
             }

modules/ebi-metagenomics/bwamem2/mem/environment.yml

@@ -1,11 +1,10 @@
 name: bwamem2_mem
-
 channels:
   - conda-forge
   - bioconda
   - defaults
-
 dependencies:
   - bwa-mem2=2.2.1
-  - htslib=1.19.1
+  # renovate: datasource=conda depName=bioconda/samtools
   - samtools=1.19.2
+  - htslib=1.19.1

modules/ebi-metagenomics/bwamem2decontnobams/environment.yml

@@ -0,0 +1,11 @@
+name: bwamem2decontnobams
+
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+
+dependencies:
+  - bwa-mem2=2.2.1
+  - htslib=1.19.1
+  - samtools=1.19.2

modules/ebi-metagenomics/bwamem2decontnobams/main.nf

@@ -0,0 +1,56 @@
+process BWAMEM2DECONTNOBAMS {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-e5d375990341c5aef3c9aff74f96f66f65375ef6:2d15960ccea84e249a150b7f5d4db3a42fc2d6c3-0' :
+        'biocontainers/mulled-v2-e5d375990341c5aef3c9aff74f96f66f65375ef6:2d15960ccea84e249a150b7f5d4db3a42fc2d6c3-0' }"
+
+
+    input:
+    tuple val(meta), path(reads)
+    tuple val(meta2), path(index)
+
+    output:
+    tuple val(meta), path("*{_1,_2,_interleaved}.fq.gz"), emit: decont_reads
+    path "versions.yml",                                  emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def ref_prefix = task.ext.ref_prefix ?: "${meta2.id}"
+    """
+    INDEX=`find -L ./ -name "*.amb" | sed 's/\\.amb\$//'`
+    if [[ "${meta.single_end}" == "true" ]]; then
+        bwa-mem2 \\
+            mem \\
+            -M \\
+            -t $task.cpus \\
+            \$INDEX \\
+            $reads \\
+            | samtools view -@ ${task.cpus} -f 4 -F 256 -uS - \\
+            | samtools sort -@ ${task.cpus} -n -O bam - \\
+            | samtools bam2fq -@ $task.cpus - | gzip --no-name > ${ref_prefix}_${prefix}_interleaved.fq.gz
+    else
+        bwa-mem2 \\
+            mem \\
+            -M \\
+            -t $task.cpus \\
+            \$INDEX \\
+            $reads \\
+            | samtools view -@ ${task.cpus} -f 4 -F 256 -uS - \\
+            | samtools sort -@ ${task.cpus} -n -O bam - \\
+            | samtools bam2fq -@ ${task.cpus} -1 ${ref_prefix}_${prefix}_1.fq.gz -2 ${ref_prefix}_${prefix}_2.fq.gz -0 /dev/null -s /dev/null
+    fi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bwa-mem2: \$(bwa-mem2 version 2> /dev/null)
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/ebi-metagenomics/bwamem2decontnobams/meta.yml

@@ -0,0 +1,56 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "bwamem2decontnobams"
+description: Decontamination module using bwamem2 and samtools that generates fastq files on the fly
+keywords:
+  - alignment
+  - decontamination
+  - fastq
+tools:
+  - bwamem2:
+      description: "Mapping DNA sequences against a large reference genome"
+      tool_dev_url: "https://github.com/bwa-mem2/bwa-mem2"
+  - samtools:
+      description: "Tools for dealing with SAM, BAM and CRAM files"
+      documentation: "http://www.htslib.org/doc/1.1/samtools.html"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2
+        for single-end and paired-end data, respectively
+  - meta2:
+      type: map
+      description: |
+        Groovy Map containing reference genome information
+        e.g. [ id:'ref_name' ]
+  - index:
+      type: file
+      description: |
+        A list of BWA index files
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - decont_reads:
+      type: file
+      description: |
+        List of fastq files. Two files for paired-end reads and one file for single-end reads
+
+authors:
+  - "@EBI-metagenomics"
+maintainers:
+  - "@EBI-metagenomics"

subworkflows/ebi-metagenomics/reads_bwamem2_decontamination/tests/main.nf.test → modules/ebi-metagenomics/bwamem2decontnobams/tests/main.nf.test

@@ -1,14 +1,12 @@
 nextflow_workflow {
 
-    name "Test Subworkflow READS_BWAMEM2_DECONTAMINATION"
+    name "Test module bwamem2decontnobams"
     script "../main.nf"
-    workflow "READS_BWAMEM2_DECONTAMINATION"
+    workflow "BWAMEM2DECONTNOBAMS"
 
-    tag "subworkflows"
-    tag "subworkflows_nfcore"
-    tag "subworkflows/reads_bwamem2_decontamination"
-    tag "bwamem2/mem"
-    tag "samtools/bam2fq"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "bwamem2decontnobams"
 
     test("Illumina paired_end decontamination with MGYG000317500") {
         when {
@@ -42,8 +40,8 @@ nextflow_workflow {
                 { assert workflow.success },
                 // gzip stores extra information in the header, which makes comparing checksums impossible between operating systems.
                 // that is why we use the sizes of files, and that sort of thing
-                { assert path(workflow.out.decontaminated_reads.get(0).get(1).get(0)).linesGzip.size() == 374028 },
-                { assert path(workflow.out.decontaminated_reads.get(0).get(1).get(1)).linesGzip.size() == 374028 }
+                { assert path(workflow.out.decont_reads.get(0).get(1).get(0)).linesGzip.size() == 374028 },
+                { assert path(workflow.out.decont_reads.get(0).get(1).get(1)).linesGzip.size() == 374028 }
             )
         }
     }
@@ -79,7 +77,7 @@ nextflow_workflow {
         then {
             assertAll(
                 { assert workflow.success },
-                { assert path(workflow.out.decontaminated_reads.get(0).get(1)).linesGzip.size() == 378312 }
+                { assert path(workflow.out.decont_reads.get(0).get(1)).linesGzip.size() == 378312 }
             )
         }
     }

modules/ebi-metagenomics/bwamem2decontnobams/tests/tags.yml

@@ -0,0 +1,2 @@
+bwamem2decontnobams:
+  - modules/ebi-metagenomics/bwamem2decontnobams/**