New module: kraken2/build (#5212)

* first commit

* use mkdir -p flag

* update assertions

* Update modules/nf-core/kraken2/build/main.nf

Co-authored-by: James A. Fellows Yates <[email protected]>

* update dependencies

* add args_id

* option for cleaning files

* Update modules/nf-core/kraken2/build/main.nf

Co-authored-by: James A. Fellows Yates <[email protected]>

* remove trailing whitespace

* remove trailing whitespace

* check prefix and database name

* Add slightly relaxed assrtions opts.k2d

* Change unmapped as well due to occasional variation

---------

Co-authored-by: James A. Fellows Yates <[email protected]>

modules/nf-core/kraken2/build/environment.yml

@@ -0,0 +1,10 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "kraken2_build"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::kraken2=2.1.3"
+  - "coreutils=9.4"

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

@@ -0,0 +1,51 @@
+process KRAKEN2_BUILD {
+    tag "$meta.id"
+    label 'process_medium'
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-f8c4015c836dd3ce5c118cfed97ec8259bab9e9d:2e0b144854b4a3d69b5df7a0340a60db846cc8bf-0':
+        'biocontainers/mulled-v2-f8c4015c836dd3ce5c118cfed97ec8259bab9e9d:2e0b144854b4a3d69b5df7a0340a60db846cc8bf-0' }"
+
+    input:
+    tuple val(meta), path(db)
+    val cleaning
+
+    output:
+    tuple val(meta), path("$prefix"), emit: db
+    path "versions.yml"             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    runclean = cleaning ? "kraken2-build --clean --db ${db}" : ""
+    """
+    kraken2-build \\
+        --build \\
+        $args \\
+        --threads ${task.cpus} \\
+        --db ${db}
+    $runclean
+    if [[ \$(basename ${db}) != "${prefix}" ]]; then
+        mv ${db}/* ${prefix}
+    fi
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kraken2: \$(echo \$(kraken2 --version 2>&1) | sed 's/^.*Kraken version //; s/ .*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    mkdir -p "$prefix"
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kraken2: \$(echo \$(kraken2 --version 2>&1) | sed 's/^.*Kraken version //; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/kraken2/build/meta.yml

@@ -0,0 +1,48 @@
+name: "kraken2_build"
+description: Builds Kraken2 database
+keywords:
+  - metagenomics
+  - db
+  - classification
+  - build
+  - kraken2
+tools:
+  - kraken2:
+      description: "Kraken2 is a system for assigning taxonomic labels to short DNA sequences, usually obtained through metagenomic studies."
+      homepage: https://ccb.jhu.edu/software/kraken2/
+      documentation: https://github.com/DerrickWood/kraken2/wiki/Manual
+      tool_dev_url: "https://github.com/DerrickWood/kraken2"
+      doi: 10.1186/s13059-019-1891-0
+      licence: ["MIT"]
+      args_id: "$args"
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  - db:
+      type: directory
+      description: contains required files to build the database
+      pattern: "*/"
+  - cleaning:
+      type: boolean
+      description: activate or deactivate (true or false) cleaning of intermediate files
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  - db:
+      type: directory
+      description: contains the database that can be used to perform taxonomic classification
+      pattern: "*/"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@alxndrdiaz"
+maintainers:
+  - "@alxndrdiaz"

modules/nf-core/kraken2/build/tests/main.nf.test

@@ -0,0 +1,101 @@
+nextflow_process {
+
+    name "Test Process KRAKEN2_BUILD"
+    script "../main.nf"
+    process "KRAKEN2_BUILD"
+    config "./nextflow.config"
+    tag "kraken2"
+    tag "kraken2/build"
+    tag "kraken2/add"
+    tag "gunzip"
+    tag "modules"
+    tag "modules_nfcore"
+
+    setup {
+
+        run("GUNZIP") {
+            script "modules/nf-core/gunzip/main.nf"
+            process {
+                """
+                input[0] = Channel.of([
+                    [],
+                    file(
+                        params.test_data['sarscov2']['metagenome']['prot_accession2taxid_gz'],
+                        checkIfExists: true
+                    )
+                ])
+                """
+            }
+        }
+
+        run("KRAKEN2_ADD") {
+            script "modules/nf-core/kraken2/add/main.nf"
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                        [
+                        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true),
+                        file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true)
+                        ]
+                    ]
+                input[1] = file(params.test_data['sarscov2']['metagenome']['prot_names_dmp'], checkIfExists: true)
+                input[2] = file(params.test_data['sarscov2']['metagenome']['prot_nodes_dmp'], checkIfExists: true)
+                input[3] = GUNZIP.out.gunzip.map{ it[1] }
+                """
+            }
+        }
+
+    }
+
+    test("sarscov2 protein_db") {
+
+        when {
+            process {
+                """
+                input[0] = KRAKEN2_ADD.out.db
+                input[1] = true
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.db.get(0).get(1) ==~ ".*/test" },
+                { assert snapshot (
+                        path("${process.out.db[0][1]}/hash.k2d"),
+                        path("${process.out.db[0][1]}/taxo.k2d"),
+                        file("${process.out.db[0][1]}/opts.k2d").name,
+                        file("${process.out.db[0][1]}/unmapped.txt").name
+                    ).match()
+                }
+            )
+        }
+
+    }
+
+    test("sarscov2 protein_db stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = KRAKEN2_ADD.out.db
+                input[1] = true
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot (process.out).match()
+                }
+            )
+        }
+
+    }
+
+}

modules/nf-core/kraken2/build/tests/nextflow.config

@@ -0,0 +1,9 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: KRAKEN2_BUILD {
+        ext.args = '--protein'
+    }
+
+}

modules/nf-core/kraken2/build/tests/tags.yml

@@ -0,0 +1,4 @@
+kraken2/build:
+  - modules/nf-core/kraken2/build/**
+  - modules/nf-core/kraken2/add/**
+  - modules/nf-core/gunzip/**