Deacon filter and update deacon index

modules/nf-core/deacon/filter/environment.yml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  # renovate: datasource=conda depName=bioconda/deacon
+  - bioconda::deacon=0.10.0

modules/nf-core/deacon/filter/main.nf

@@ -0,0 +1,68 @@
+process DEACON_FILTER {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/deacon:0.10.0--h4349ce8_0':
+        'biocontainers/deacon:0.10.0--h4349ce8_0' }"
+
+
+    input:
+    tuple val(meta), path(index)
+    tuple val(meta2), path(reads)
+    val (save_summary)
+
+    output:
+    tuple val(meta2), path("filtered_reads/*.fastq.gz"), emit: filtered_reads
+    tuple val(meta2), path("*.json")                   , emit: summary_json, optional: true
+    path "versions.yml"                                , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def reads_input = meta2.single_end ? reads : "${reads.sort()[0]} ${reads.sort()[1]}"
+    def summary_arg = save_summary ? "-s ${prefix}_summary.json" : ""
+    def output_arg = meta2.single_end ? "-o filtered_reads/${prefix}.fastq.gz" : "-o filtered_reads/${prefix}_1.fastq.gz -O filtered_reads/${prefix}_2.fastq.gz"
+    """
+    mkdir -p filtered_reads/
+
+    deacon \\
+        filter \\
+        $args \\
+        --threads ${task.cpus} \\
+        $index \\
+        $reads_input \\
+        $summary_arg \\
+        $output_arg
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        deacon: \$(deacon --version | head -n1 | sed 's/deacon //g')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta2.id}"
+    """
+    mkdir -p filtered_reads
+    if [[ "${meta2.single_end}" == "true" ]]; then
+        echo "" | gzip -c > filtered_reads/${prefix}.fastq.gz
+    else
+        echo "" | gzip -c > filtered_reads/ ${prefix}_1.fastq.gz
+        echo "" | gzip -c > filtered_reads/ ${prefix}_2.fastq.gz
+    fi
+
+    if [[ "${save_summary}" == "true" ]]; then
+        touch ${prefix}_summary.json
+    fi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        deacon: \$(deacon --version | head -n1 | sed 's/deacon //g')
+    END_VERSIONS
+    """
+}

modules/nf-core/deacon/filter/meta.yml

@@ -0,0 +1,80 @@
+name: "deacon_filter"
+description: write your description here
+keywords:
+  - filter
+  - decontamination
+  - minimizer
+  - alignment-free
+  - genomics
+tools:
+  - "deacon":
+      description: "Fast alignment-free sequence filter"
+      homepage: "https://github.com/bede/deacon"
+      documentation: "https://github.com/bede/deacon#readme"
+      tool_dev_url: "https://github.com/bede/deacon"
+      doi: "10.1093/bioinformatics/btae004"
+      licence: ["MIT"]
+      identifier: "biotools:deacon"
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing index information.
+          e.g. [ id:'test', single_end:false ]
+    - index:
+        type: file
+        description: Deacon minimizer index file
+        pattern: "*.idx"
+        ontologies:
+          - edam: "http://edamontology.org/data_3210" # Genome index
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map containing sample information.
+          e.g. [ id:'sample1', single_end:false ]
+    - reads:
+        type: file
+        description: Input genomic reads in FASTQ format
+        pattern: "*.{fastq,fastq.gz,fq,fq.gz}"
+        ontologies:
+          - edam: "http://edamontology.org/data_0850" # Sequence set
+          - edam: "http://edamontology.org/format_1930" # FASTQ
+
+output:
+  - reads:
+      - meta2:
+          type: map
+          description: |
+            Groovy Map containing sample information.
+            e.g. [ id:'sample1', single_end:false ]
+      - "*.fastq.gz":
+          type: file
+          description: Filtered genomic reads in compressed FASTQ format
+          pattern: "*.fastq.gz"
+          ontologies:
+            - edam: "http://edamontology.org/data_0850" # Sequence set
+            - edam: "http://edamontology.org/format_1930" # FASTQ
+  - json:
+      - meta2:
+          type: map
+          description: |
+            Groovy Map containing sample information.
+            e.g. [ id:'sample1', single_end:false ]
+      - "*.json":
+          type: file
+          description: Summary statistics in JSON format (optional)
+          pattern: "*.json"
+          ontologies:
+            - edam: "http://edamontology.org/format_3464" # JSON
+  - versions:
+      - "versions.yml":
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@mberacochea"
+  - "@sofstam"
+maintainers:
+  - "@mberacochea"
+  - "@sofstam"

modules/nf-core/deacon/filter/tests/main.nf.test

@@ -0,0 +1,198 @@
+
+nextflow_process {
+
+    name "Test Process DEACON_FILTER"
+    script "../main.nf"
+    process "DEACON_FILTER"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "deacon"
+    tag "deacon/filter"
+
+    setup {
+        run("DEACON_INDEX") {
+            script "../../index/main.nf"
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ]
+                """
+            }
+        }
+    }
+
+    test("sarscov2 - fastq single end") {
+
+        when {
+            process {
+                """
+                input[0] = DEACON_INDEX.out.index
+                input[1] = [
+                    [ id:'test', single_end:true ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                ]
+                input[2] = false
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out,
+                    process.out.versions.collect{ path(it).yaml }
+                ).match() }
+            )
+        }
+
+    }
+
+    test("sarscov2 - fastq paired end") {
+
+        when {
+            process {
+                """
+                input[0] = DEACON_INDEX.out.index
+                input[1] = [
+                    [ id:'test', single_end:false ],
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
+                    ]
+                ]
+                input[2] = false
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out,
+                    process.out.versions.collect{ path(it).yaml }
+                ).match() }
+            )
+        }
+
+    }
+
+    test("sarscov2 - fastq paired end - host depletion") {
+
+        config "./nextflow.config"
+
+        when {
+            params {
+                depletion = '-d'
+            }
+
+            process {
+                """
+                input[0] = DEACON_INDEX.out.index
+                input[1] = [
+                    [ id:'test', single_end:false ],
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
+                    ]
+                ]
+                input[2] = false
+                """
+            }
+        }
+
+        then {
+        assertAll(
+            { assert process.success },
+            { assert snapshot(
+                process.out.filtered_reads,
+                process.out.versions
+            ).match() }
+        )
+    }
+
+
+    }
+
+    test("sarscov2 - fastq single end with summary") {
+
+        when {
+            process {
+                """
+                input[0] = DEACON_INDEX.out.index
+                input[1] = [
+                    [ id:'test', single_end:true ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                ]
+                input[2] = true
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                // Only a subset of the summary json, as it contains non-stable values
+                { assert snapshot(
+                    process.out.filtered_reads,
+                    path(process.out.summary_json.get(0).get(1)).json.version,
+                    path(process.out.summary_json.get(0).get(1)).json.index,
+                    path(process.out.summary_json.get(0).get(1)).json.input1,
+                    path(process.out.summary_json.get(0).get(1)).json.input2,
+                    path(process.out.summary_json.get(0).get(1)).json.output,
+                    path(process.out.summary_json.get(0).get(1)).json.output2,
+                    path(process.out.summary_json.get(0).get(1)).json.k,
+                    path(process.out.summary_json.get(0).get(1)).json.w,
+                    path(process.out.summary_json.get(0).get(1)).json.match_threshold,
+                    path(process.out.summary_json.get(0).get(1)).json.prefix_length,
+                    path(process.out.summary_json.get(0).get(1)).json.deplete,
+                    path(process.out.summary_json.get(0).get(1)).json.rename,
+                    path(process.out.summary_json.get(0).get(1)).json.seqs_in,
+                    path(process.out.summary_json.get(0).get(1)).json.seqs_out,
+                    path(process.out.summary_json.get(0).get(1)).json.seqs_removed,
+                    path(process.out.summary_json.get(0).get(1)).json.seqs_removed_proportion,
+                    path(process.out.summary_json.get(0).get(1)).json.bp_in,
+                    path(process.out.summary_json.get(0).get(1)).json.bp_out,
+                    path(process.out.summary_json.get(0).get(1)).json.bp_removed,
+                    path(process.out.summary_json.get(0).get(1)).json.bp_removed_proportion,
+                    process.out.versions.collect{ path(it).yaml }
+                ).match() }
+            )
+        }
+
+    }
+
+   test("sarscov2 - fastq single end - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = DEACON_INDEX.out.index
+                input[1] = [
+                    [ id:'test', single_end:true ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                ]
+                input[2] = false
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out,
+                    process.out.versions.collect{ path(it).yaml }
+                ).match() }
+            )
+        }
+
+    }
+
+}