Merge pull request #188 from nf-core/bracken-mergetables

Add Bracken mergetables

conf/modules.config

@@ -321,12 +321,21 @@ process {
         ]
     }
 
-    withName: KRAKENTOOLS_COMBINEKREPORTS {
+    withName: BRACKEN_COMBINEBRACKENOUTPUTS {
+        ext.prefix = { "bracken_${meta.id}_combined_reports" }
+        publishDir = [
+            path: { "${params.outdir}/bracken/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{txt}'
+        ]
+    }
+
+    withName: KRAKENTOOLS_COMBINEKREPORTS_KRAKEN {
         ext.prefix = { "kraken2_${meta.id}_combined_reports" }
         publishDir = [
             path: { "${params.outdir}/kraken2/" },
             mode: params.publish_dir_mode,
-            pattern: '*.{txt}'
+            pattern: '*.txt'
         ]
     }
 

modules.json

@@ -30,6 +30,11 @@
                         "git_sha": "8cab56516076b23c6f8eb1ac20ba4ce9692c85e1",
                         "installed_by": ["modules"]
                     },
+                    "bracken/combinebrackenoutputs": {
+                        "branch": "master",
+                        "git_sha": "9c87d5fdad182590a370ea43a4ecebd200a6f6fb",
+                        "installed_by": ["modules"]
+                    },
                     "cat/fastq": {
                         "branch": "master",
                         "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905",

modules/nf-core/bracken/combinebrackenoutputs/main.nf

@@ -0,0 +1,37 @@
+process BRACKEN_COMBINEBRACKENOUTPUTS {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::bracken=2.7" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bracken:2.7--py39hc16433a_0':
+        'quay.io/biocontainers/bracken:2.7--py39hc16433a_0' }"
+
+    input:
+    tuple val(meta), path(input)
+
+    output:
+    tuple val(meta), path("*.txt"), emit: txt
+    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}"
+    // WARN: Version information not provided by tool on CLI.
+    // Please update version string below when bumping container versions.
+    def VERSION = '2.7'
+    """
+    combine_bracken_outputs.py \\
+        $args \\
+        --files ${input} \\
+        -o ${prefix}.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        combine_bracken_output: ${VERSION}
+    END_VERSIONS
+    """
+}

modules/nf-core/bracken/combinebrackenoutputs/meta.yml

@@ -0,0 +1,41 @@
+name: "bracken_combinebrackenoutputs"
+description: Combine output of metagenomic samples analyzed by bracken.
+keywords:
+  - sort
+tools:
+  - "bracken":
+      description: Bracken (Bayesian Reestimation of Abundance with KrakEN) is a highly accurate statistical method that computes the abundance of species in DNA sequences from a metagenomics sample.
+      homepage: https://ccb.jhu.edu/software/bracken/
+      documentation: https://ccb.jhu.edu/software/bracken/index.shtml?t=manual
+      tool_dev_url: https://github.com/jenniferlu717/Bracken
+      doi: "10.7717/peerj-cs.104"
+      licence: ["GPL v3"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: List of output files from bracken
+      pattern: "*"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - txt:
+      type: file
+      description: Combined output in table format
+      pattern: "*.txt"
+
+authors:
+  - "@jfy133"

subworkflows/local/standardisation_profiles.nf

@@ -2,6 +2,7 @@
 // Standardise output files e.g. aggregation
 //
 
+include { BRACKEN_COMBINEBRACKENOUTPUTS                                         } from '../../modules/nf-core/bracken/combinebrackenoutputs/main'
 include { KAIJU_KAIJU2TABLE                                                     } from '../../modules/nf-core/kaiju/kaiju2table/main'
 include { KRAKENTOOLS_COMBINEKREPORTS as KRAKENTOOLS_COMBINEKREPORTS_KRAKEN     } from '../../modules/nf-core/krakentools/combinekreports/main'
 include { KRAKENTOOLS_COMBINEKREPORTS as KRAKENTOOLS_COMBINEKREPORTS_CENTRIFUGE } from '../../modules/nf-core/krakentools/combinekreports/main'
@@ -25,10 +26,11 @@ workflow STANDARDISATION_PROFILES {
     */
     ch_input_profiles = profiles
         .branch {
-            motus: it[0]['tool'] == 'motus'
+            bracken: it[0]['tool'] == 'bracken'
-            kraken2: it[0]['tool'] == 'kraken2'
             centrifuge: it[0]['tool'] == 'centrifuge'
+            kraken2: it[0]['tool'] == 'kraken2'
             metaphlan3: it[0]['tool'] == 'metaphlan3'
+            motus: it[0]['tool'] == 'motus'
             unknown: true
         }
 
@@ -49,7 +51,18 @@ workflow STANDARDISATION_PROFILES {
         Standardise and aggregate
     */
 
-        // CENTRIFUGE
+    // Bracken
+
+    ch_profiles_for_bracken = ch_input_profiles.bracken
+                            .map { [it[0]['db_name'], it[1]] }
+                            .groupTuple()
+                            .map {
+                                [[id:it[0]], it[1]]
+                            }
+
+    BRACKEN_COMBINEBRACKENOUTPUTS ( ch_profiles_for_bracken )
+
+    // CENTRIFUGE
 
     // Collect and replace id for db_name for prefix
     // Have to sort by size to ensure first file actually has hits otherwise