Merge pull request #55 from nf-core/megan-postprocessing

Add MEGAN for MALT postprocessing

CITATIONS.md

@@ -40,9 +40,17 @@
 
   > Vågene, Åshild J., Alexander Herbig, Michael G. Campana, Nelly M. Robles García, Christina Warinner, Susanna Sabin, Maria A. Spyrou, et al. 2018. Salmonella Enterica Genomes from Victims of a Major Sixteenth-Century Epidemic in Mexico. Nature Ecology & Evolution 2 (3): 520-28. doi: 10.1038/s41559-017-0446-6.
 
+- [MEGAN](https://doi.org/10.1371/journal.pcbi.1004957)
+
+  > Huson, Daniel H., Sina Beier, Isabell Flade, Anna Górska, Mohamed El-Hadidi, Suparna Mitra, Hans-Joachim Ruscheweyh, and Rewati Tappu. 2016. “MEGAN Community Edition - Interactive Exploration and Analysis of Large-Scale Microbiome Sequencing Data.” PLoS Computational Biology 12 (6): e1004957. doi: 10.1371/journal.pcbi.1004957.
+
 - [MetaPhlAn3](https://doi.org/10.7554/eLife.65088)
 
-  > Beghini, Francesco, Lauren J McIver, Aitor Blanco-Míguez, Leonard Dubois, Francesco Asnicar, Sagun Maharjan, Ana Mailyan, et al. 2021. “Integrating Taxonomic, Functional, and Strain-Level Profiling of Diverse Microbial Communities with BioBakery 3.” Edited by Peter Turnbaugh, Eduardo Franco, and C Titus Brown. ELife 10 (May): e65088.
+  > Beghini, Francesco, Lauren J McIver, Aitor Blanco-Míguez, Leonard Dubois, Francesco Asnicar, Sagun Maharjan, Ana Mailyan, et al. 2021. “Integrating Taxonomic, Functional, and Strain-Level Profiling of Diverse Microbial Communities with BioBakery 3.” Edited by Peter Turnbaugh, Eduardo Franco, and C Titus Brown. ELife 10 (May): e65088. doi: 10.7554/eLife.65088
+
+- [Centrifuge](https://doi.org/10.1101/gr.210641.116)
+
+  > Kim, Daehwan, Li Song, Florian P. Breitwieser, and Steven L. Salzberg. 2016. “Centrifuge: Rapid and Sensitive Classification of Metagenomic Sequences.” Genome Research 26 (12): 1721-29. doi: 10.1101/gr.210641.116.
 
 ## Software packaging/containerisation tools
 

conf/modules.config

@@ -191,11 +191,22 @@ process {
 
     withName: MALT_RUN {
         ext.args = { "${meta.db_params}" }
-        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        // one run with multiple samples, so fix ID to just db name to ensure clean log name
+        ext.prefix = { "${meta.db_name}" }
         publishDir = [
             path: { "${params.outdir}/malt/${meta.db_name}" },
             mode: params.publish_dir_mode,
-            pattern: '*.{log}'
+            pattern: '*.{rma6,log,sam}'
+        ]
+    }
+
+    withName: MEGAN_RMA2INFO {
+        ext.args = "-c2c Taxonomy"
+        ext.prefix = { "${meta.id}" }
+        publishDir = [
+            path: { "${params.outdir}/malt/${meta.db_name}" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{txt.gz,megan}'
         ]
     }
 

modules.json

@@ -36,6 +36,9 @@
             "malt/run": {
                 "git_sha": "72b96f4e504eef673f2b5c13560a9d90b669129b"
             },
+            "megan/rma2info": {
+                "git_sha": "2d38566eca4cc15142b2ffa7c11837569b39aece"
+            },
             "metaphlan3": {
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
             },

modules/nf-core/modules/megan/rma2info/main.nf

@@ -0,0 +1,38 @@
+process MEGAN_RMA2INFO {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::megan=6.21.7" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/megan:6.21.7--h9ee0642_0':
+        'quay.io/biocontainers/megan:6.21.7--h9ee0642_0' }"
+
+    input:
+    tuple val(meta), path(rma6)
+    val(megan_summary)
+
+    output:
+    tuple val(meta), path("*.txt.gz")               , emit: txt
+    tuple val(meta), path("*.megan"), optional: true, emit: megan_summary
+    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 summary = megan_summary ? "-es ${prefix}.megan" : ""
+    """
+    rma2info \\
+        -i ${rma6} \\
+        -o ${prefix}.txt.gz \\
+        ${summary} \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        megan: \$(echo \$(rma2info 2>&1) | grep version | sed 's/.*version //g;s/, built.*//g')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/megan/rma2info/meta.yml

@@ -0,0 +1,51 @@
+name: "megan_rma2info"
+description: Analyses an RMA file and exports information in text format
+keywords:
+  - megan
+  - rma6
+  - classification
+  - conversion
+tools:
+  - "megan":
+      description: "A tool for studying the taxonomic content of a set of DNA reads"
+      homepage: "https://uni-tuebingen.de/fakultaeten/mathematisch-naturwissenschaftliche-fakultaet/fachbereiche/informatik/lehrstuehle/algorithms-in-bioinformatics/software/megan6/"
+      documentation: "https://software-ab.informatik.uni-tuebingen.de/download/megan6/welcome.html"
+      tool_dev_url: "https://github.com/husonlab/megan-ce"
+      doi: "10.1371/journal.pcbi.1004957"
+      licence: "['GPL >=3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - rma6:
+      type: file
+      description: RMA6 file from MEGAN or MALT
+      pattern: "*.rma6"
+  - megan_summary:
+      type: boolean
+      description: Specify whether to generate an MEGAN summary file
+
+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: Compressed text file
+      pattern: "*.txt.gz"
+  - megan_summary:
+      type: file
+      description: Optionally generated MEGAN summary file
+      pattern: "*.megan"
+
+authors:
+  - "@jfy133"

nextflow.config

@@ -88,6 +88,7 @@ params {
     // MALT
     run_malt                   = false
     malt_mode                  = 'BlastN'
+    malt_generatemegansummary = false
 
     // kraken2
     run_kraken2                = false

nextflow_schema.json

@@ -364,11 +364,14 @@
         },
         "shortread_hostremoval_reference": {
             "type": "string",
-            "default": null
+            "default": "None"
         },
         "shortread_hostremoval_index": {
             "type": "string",
-            "default": null
+            "default": "None"
+        },
+        "malt_generatemegansummary": {
+            "type": "boolean"
         }
     }
 }

subworkflows/local/profiling.nf

@@ -3,6 +3,7 @@
 //
 
 include { MALT_RUN                    } from '../../modules/nf-core/modules/malt/run/main'
+include { MEGAN_RMA2INFO              } from '../../modules/nf-core/modules/megan/rma2info/main'
 include { KRAKEN2_KRAKEN2             } from '../../modules/nf-core/modules/kraken2/kraken2/main'
 include { CENTRIFUGE_CENTRIFUGE       } from '../../modules/nf-core/modules/centrifuge/centrifuge/main'
 include { METAPHLAN3                  } from '../../modules/nf-core/modules/metaphlan3/main'
@@ -13,8 +14,9 @@ workflow PROFILING {
     databases // [ [ meta ], path ]
 
     main:
-    ch_versions       = Channel.empty()
+    ch_versions             = Channel.empty()
-    ch_multiqc_files  = Channel.empty()
+    ch_multiqc_files        = Channel.empty()
+    ch_raw_profiles    = Channel.empty()
 
 /*
         COMBINE READS WITH POSSIBLE DATABASES
@@ -94,30 +96,48 @@ workflow PROFILING {
 
     if ( params.run_malt ) {
         MALT_RUN ( ch_input_for_malt.reads, params.malt_mode, ch_input_for_malt.db )
-        ch_multiqc_files = ch_multiqc_files.mix( MALT_RUN.out.log.collect{it[1]}.ifEmpty([])  )
+
-        ch_versions = ch_versions.mix( MALT_RUN.out.versions.first() )
+        ch_maltrun_for_megan = MALT_RUN.out.rma6
+                                .transpose()
+                                .map{
+                                    meta, rma ->
+                                            // re-extract meta from file names, use filename without rma to
+                                            // ensure we keep paired-end information in downstream filenames
+                                            // when no pair-merging
+                                            def meta_new = meta.clone()
+                                            meta_new['db_name'] = meta.id
+                                            meta_new['id'] = rma.baseName
+                                        [ meta_new, rma ]
+                                }
+
+        MEGAN_RMA2INFO (ch_maltrun_for_megan, params.malt_generatemegansummary )
+        ch_multiqc_files   = ch_multiqc_files.mix( MALT_RUN.out.log.collect{it[1]}.ifEmpty([])  )
+        ch_versions        = ch_versions.mix( MALT_RUN.out.versions.first() )
+        ch_raw_profiles    = ch_raw_profiles.mix( MEGAN_RMA2INFO.out.txt )
     }
 
     if ( params.run_kraken2 ) {
         KRAKEN2_KRAKEN2 ( ch_input_for_kraken2.reads, ch_input_for_kraken2.db  )
-        ch_multiqc_files = ch_multiqc_files.mix( KRAKEN2_KRAKEN2.out.txt.collect{it[1]}.ifEmpty([])  )
+        ch_multiqc_files   = ch_multiqc_files.mix( KRAKEN2_KRAKEN2.out.txt.collect{it[1]}.ifEmpty([])  )
-        ch_versions = ch_versions.mix( KRAKEN2_KRAKEN2.out.versions.first() )
+        ch_versions        = ch_versions.mix( KRAKEN2_KRAKEN2.out.versions.first() )
+        ch_raw_profiles    = ch_raw_profiles.mix( KRAKEN2_KRAKEN2.out.txt )
     }
 
     if ( params.run_centrifuge ) {
         CENTRIFUGE_CENTRIFUGE ( ch_input_for_centrifuge.reads, ch_input_for_centrifuge.db, params.centrifuge_save_unaligned, params.centrifuge_save_aligned, params.centrifuge_sam_format  )
-        ch_versions = ch_versions.mix( CENTRIFUGE_CENTRIFUGE.out.versions.first() )
+        ch_versions        = ch_versions.mix( CENTRIFUGE_CENTRIFUGE.out.versions.first() )
+        ch_raw_profiles    = ch_raw_profiles.mix( CENTRIFUGE_CENTRIFUGE.out.report )
     }
 
     if ( params.run_metaphlan3 ) {
         METAPHLAN3 ( ch_input_for_metaphlan3.reads, ch_input_for_metaphlan3.db )
-        ch_versions = ch_versions.mix( METAPHLAN3.out.versions.first() )
+        ch_versions        = ch_versions.mix( METAPHLAN3.out.versions.first() )
+        ch_raw_profiles    = ch_raw_profiles.mix( METAPHLAN3.out.biom )
     }
 
 
     emit:
-    // TODO work out if there is enough standardisation of output to export as one?
+    profiles = ch_raw_profiles    // channel: [ val(meta), [ reads ] ] - should be text files or biom
-    //output    = ch_filtered_reads    // channel: [ val(meta), [ reads ] ]
     versions = ch_versions          // channel: [ versions.yml ]
     mqc      = ch_multiqc_files
 }