4557 new module kaijumergeoutputs + stub Kraken2/Kraken2

modules/nf-core/kaiju/mergeoutputs/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "kaiju_mergeoutputs"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::kaiju=1.10.0"

modules/nf-core/kaiju/mergeoutputs/main.nf

@@ -0,0 +1,51 @@
+process KAIJU_MERGEOUTPUTS {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/kaiju:1.10.0--h43eeafb_0':
+        'biocontainers/kaiju:1.10.0--h43eeafb_0' }"
+
+    input:
+    tuple val(meta), path(kaiju), path(kraken)
+    path (db)
+
+    output:
+    tuple val(meta), path("*_merged.tsv"), emit: merged
+    path "versions.yml"                  , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args    = task.ext.args ?: ''
+    def prefix  = task.ext.prefix ?: "${meta.id}"
+    def dbnodes = db ? '-t <(find -L ${db} -name "*nodes.dmp")' : ''
+    """
+    kaiju-mergeOutputs \\
+        -i <(sort -k2,2 ${kaiju}) \\
+        -j <(sort -k2,2 ${kraken}) \\
+        -o ${prefix}_merged.tsv \\
+        $dbnodes \\
+        $args
+
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kaiju: \$(echo \$( kaiju -h 2>&1 | sed -n 1p | sed 's/^.*Kaiju //' ))
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_merged.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kaiju: \$(echo \$( kaiju -h 2>&1 | sed -n 1p | sed 's/^.*Kaiju //' ))
+    END_VERSIONS
+    """
+}

modules/nf-core/kaiju/mergeoutputs/meta.yml

@@ -0,0 +1,53 @@
+name: kaiju_mergeoutputs
+description: Merge two tab-separated output files of Kaiju and Kraken in the column format
+keywords:
+  - classify
+  - metagenomics
+  - fastq
+  - taxonomic profiling
+tools:
+  - kaiju:
+      description: Fast and sensitive taxonomic classification for metagenomics
+      homepage: https://kaiju.binf.ku.dk/
+      documentation: https://github.com/bioinformatics-centre/kaiju/blob/master/README.md
+      tool_dev_url: https://github.com/bioinformatics-centre/kaiju
+      doi: "10.1038/ncomms11257"
+      licence: ["GNU GPL v3"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - kaiju:
+      type: file
+      description: |
+        Results with taxonomic classification of each read from Kaiju
+  - kraken:
+      type: file
+      description: |
+        Results with taxonomic classification of each read from Kraken
+      pattern: "*.{tsv}"
+  - db:
+      type: directory
+      description: |
+        List containing the database and nodes files for Kaiju
+        e.g. [ 'database.fmi', 'nodes.dmp' ]
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - merged:
+      type: file
+      description: Results with merged taxonomic classification of each read based on the given strategy '1', '2', 'lca' [default] or 'lowest'
+      pattern: "*.tsv"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@Joon-Klaps"
+maintainers:
+  - "@Joon-Klaps"

modules/nf-core/kaiju/mergeoutputs/tests/main.nf.test

@@ -0,0 +1,129 @@
+nextflow_process {
+
+    name "Test Process KAIJU_MERGEOUTPUTS"
+    script "../main.nf"
+    process "KAIJU_MERGEOUTPUTS"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "kaiju"
+    tag "untar"
+    tag "kaiju/kaiju"
+    tag "kraken2/kraken2"
+    tag "kaiju/mergeoutputs"
+
+    setup {
+        run("UNTAR",alias: "UNTAR_KRAKEN2" ) {
+            script "../../../untar/main.nf"
+            process {
+                """
+                input[0] = Channel.of([
+                    [],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/db/kraken2.tar.gz', checkIfExists: true)
+                ])
+                """
+            }
+        }
+        run("KRAKEN2_KRAKEN2") {
+            script "../../../kraken2/kraken2/main.nf"
+            process {
+                """
+                input[0] = [
+                        [ id:'test', single_end:true ],
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                        ]
+                input[1] = UNTAR_KRAKEN2.out.untar.map{ it[1] }
+                input[2] = false
+                input[3] = true
+                """
+            }
+        }
+        run("UNTAR",alias: "UNTAR_KAIJU" ) {
+            script "../../../untar/main.nf"
+            process {
+                """
+                input[0] = Channel.of([
+                    [],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/db/kaiju.tar.gz', checkIfExists: true)
+                ])
+                """
+            }
+        }
+        run("KAIJU_KAIJU") {
+            script "../../../kaiju/kaiju/main.nf"
+            process {
+                """
+                input[0] = [
+                        [ id:'test', single_end:true ],
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                        ]
+                input[1] = UNTAR_KAIJU.out.untar.map{ it[1] }
+                """
+            }
+        }
+    }
+
+    test("sarscov2 - kraken2.kaiju.classified - noDB ") {
+        config "./nodb.config"
+
+        when {
+            process {
+                """
+                input[0] = KAIJU_KAIJU.out.results.join(KRAKEN2_KRAKEN2.out.classified_reads_assignment)
+                input[1] = [ ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("sarscov2 - kraken2.kaiju.classified - kaiju.DB ") {
+
+        when {
+            process {
+                """
+                input[0] = KAIJU_KAIJU.out.results.join(KRAKEN2_KRAKEN2.out.classified_reads_assignment)
+                input[1] = UNTAR_KAIJU.out.untar.map{ it[1] }
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("sarscov2 - kraken2.kaiju.classified - noDB - stub ") {
+        config "./nodb.config"
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = KAIJU_KAIJU.out.results.join(KRAKEN2_KRAKEN2.out.classified_reads_assignment)
+                input[1] = []
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

modules/nf-core/kaiju/mergeoutputs/tests/nodb.config

@@ -0,0 +1,5 @@
+process {
+    withName: KAIJU_MERGEOUTPUTS{
+        ext.args=  "-c 1"
+    }
+}

modules/nf-core/kaiju/mergeoutputs/tests/tags.yml

@@ -0,0 +1,2 @@
+kaiju/mergeoutputs:
+  - "modules/nf-core/kaiju/mergeoutputs/**"

modules/nf-core/kraken2/kraken2/main.nf

@@ -55,4 +55,31 @@ process KRAKEN2_KRAKEN2 {
         pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
     END_VERSIONS
     """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def paired       = meta.single_end ? "" : "--paired"
+    def classified   = meta.single_end ? "${prefix}.classified.fastq.gz"   : "${prefix}.classified_1.fastq.gz ${prefix}.classified_2.fastq.gz"
+    def unclassified = meta.single_end ? "${prefix}.unclassified.fastq.gz" : "${prefix}.unclassified_1.fastq.gz ${prefix}.unclassified_2.fastq.gz"
+    def readclassification_option = save_reads_assignment ? "--output ${prefix}.kraken2.classifiedreads.txt" : "--output /dev/null"
+    def compress_reads_command = save_output_fastqs ? "pigz -p $task.cpus *.fastq" : ""
+
+    """
+    touch ${prefix}.kraken2.report.txt
+    if [ "$save_output_fastqs" == "true" ]; then
+        touch $classified
+        touch $unclassified
+    fi
+    if [ "$save_reads_assignment" == "true" ]; then
+        touch ${prefix}.kraken2.classifiedreads.txt
+    fi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kraken2: \$(echo \$(kraken2 --version 2>&1) | sed 's/^.*Kraken version //; s/ .*\$//')
+        pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
+    END_VERSIONS
+    """
+
 }