Added fasta_kraken2

conf/modules.config

@@ -71,7 +71,15 @@ process {
         ]
     }
 
-    withName: RUN_KRAKEN2 {
+    withName: KRAKEN2 {
+        publishDir = [
+            path: { "${params.outdir}/kraken2" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals("versions.yml") ? null : filename }
+        ]
+    }
+
+    withName: KRAKEN2_KRONA_PLOT {
         publishDir = [
             path: { "${params.outdir}/kraken2" },
             mode: params.publish_dir_mode,

lib/WorkflowMain.groovy

@@ -57,6 +57,11 @@ class WorkflowMain {
         if (!params.busco_skip && !params.busco_lineage_datasets) {
             Nextflow.error('busco_lineage_datasets must be provided when executing BUSCO')
         }
+
+        // Check for kraken2_db_path
+        if (!params.kraken2_skip && !params.kraken2_db_path) {
+            Nextflow.error('kraken2_db_path must be provided when executing Kraken2')
+        }
     }
     //
     // Get attribute from genome config file e.g. fasta

modules.json

@@ -119,6 +119,11 @@
                         "branch": "master",
                         "git_sha": "669a329f4aa37f5b7f03776c2ed1cd0ef122c626",
                         "installed_by": ["fasta_explore_search_plot_tidk"]
+                    },
+                    "untar": {
+                        "branch": "master",
+                        "git_sha": "e719354ba77df0a1bd310836aa2039b45c29d620",
+                        "installed_by": ["modules"]
                     }
                 }
             },

modules/local/kraken2.nf

@@ -0,0 +1,47 @@
+process KRAKEN2 {
+    tag "${asm_tag}"
+    label 'process_single'
+    label 'process_high_memory'
+
+    container "${ workflow.containerEngine == 'singularity' || workflow.containerEngine == 'apptainer' ?
+        'https://depot.galaxyproject.org/singularity/kraken2:2.1.2--pl5321h9f5acd7_2':
+        'biocontainers/kraken2:2.1.2--pl5321h9f5acd7_2' }"
+
+    input:
+    tuple val(asm_tag), path(fasta_file)
+    path db_path
+
+    output:
+    tuple val(asm_tag), path("*.kraken2.cut"), path("*.kraken2.report") , emit: report
+    path "versions.yml"                                                 , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    """
+    kraken2 \\
+        --output "${asm_tag}.kraken2.cut" \\
+        --report "${asm_tag}.kraken2.report" \\
+        --use-names \\
+        --db $db_path \\
+        --threads ${task.cpus} \\
+        $fasta_file > kraken2.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kraken2: \$(echo \$(kraken2 --version 2>&1) | sed 's/^.*Kraken version //; s/ .*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    touch "${asm_tag}.kraken2.cut"
+    touch "${asm_tag}.kraken2.report"
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kraken2: \$(echo \$(kraken2 --version 2>&1) | sed 's/^.*Kraken version //; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/local/kraken2_krona_plot.nf

@@ -0,0 +1,27 @@
+process KRAKEN2_KRONA_PLOT {
+    tag "${hap_name}"
+    label 'process_single'
+
+    container "docker.io/nanozoo/krona:2.7.1--e7615f7"
+
+    input:
+    tuple val(hap_name), path(kraken2_cut), path(kraken2_report)
+
+    output:
+    tuple path("*.kraken2.krona.cut"), path("*.kraken2.krona.html") , emit: plot
+    path "versions.yml"                                             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    """
+    perl -lane '@a=split /\\t/; if (\$a[2] =~ /taxid\\s+(\\d+)/) {print "\$a[1]\\t\$1\\t1\\t\$a[3]";}' $kraken2_cut > "${hap_name}.kraken2.krona.cut"
+    ktImportTaxonomy -i -o "${hap_name}.kraken2.krona.html" -m "4" "${hap_name}.kraken2.krona.cut"
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        KronaTools: \$(ktImportTaxonomy | sed -n '/KronaTools/s/KronaTools//p' | tr -d ' _/[:space:]' | sed 's/-ktImportTaxonomy\\\\//1')
+    END_VERSIONS
+    """
+}

subworkflows/local/fasta_kraken2.nf

@@ -0,0 +1,44 @@
+include { UNTAR                 } from '../../modules/nf-core/untar/main'
+include { KRAKEN2               } from '../../modules/local/kraken2'
+include { KRAKEN2_KRONA_PLOT    } from '../../modules/local/kraken2_krona_plot'
+
+workflow FASTA_KRAKEN2 {
+    take:
+    tuple_of_hap_file
+    db_path                     // channel: path
+
+    main:
+    ch_tar_db                   = db_path
+                                | filter { db -> "$db".endsWith('.tar.gz') }
+
+    ch_untar_db                 = db_path
+                                | filter { db -> !( "$db".endsWith('.tar.gz') ) }
+
+    // MODULE: UNTAR
+    UNTAR ( ch_tar_db.map { tar -> [ [ id: "kraken2_db" ], tar ] } )
+
+    ch_kraken2_inputs           = UNTAR.out.untar
+                                | map { meta, untar -> untar }
+                                | mix(
+                                    ch_untar_db
+                                )
+                                | combine(tuple_of_hap_file)
+
+    // MODULE: KRAKEN2
+    KRAKEN2(
+        ch_kraken2_inputs.map { db, tag, fasta -> [ tag, fasta ] },
+        ch_kraken2_inputs.map { db, tag, fasta -> db }
+    )
+
+    // MODULE: KRAKEN2_KRONA_PLOT
+    KRAKEN2_KRONA_PLOT ( KRAKEN2.out.report )
+
+    ch_versions                 = Channel.empty()
+                                | mix(KRAKEN2.out.versions.first())
+                                | mix(UNTAR.out.versions.first())
+                                | mix(KRAKEN2_KRONA_PLOT.out.versions.first())
+
+    emit:
+    plot                        = KRAKEN2_KRONA_PLOT.out.plot
+    versions                    = ch_versions
+}

tests/stub/stub.config

@@ -17,6 +17,9 @@ params {
 
     lai_skip                    = false
 
+    kraken2_skip                = false
+    kraken2_db_path             = 'tests/stub/kraken2/k2_minusb_20231009.tar.gz'
+
     // Limit resources so that this can run on GitHub Actions
     max_cpus                    = 2
     max_memory                  = '6.GB'