Add generation of taxon-table like output for MALT

2024-09-21 02:42:04 +00:00 · 2022-04-16 07:42:30 +02:00 · 2022-04-16 07:42:30 +02:00 · cc73cdd51d
commit cc73cdd51d
parent 6fecb3eeb7
6 changed files with 52 additions and 52 deletions
--- a/CITATIONS.md
+++ b/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

--- a/conf/modules.config
+++ b/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}'
        ]
    }

--- a/nextflow.config
+++ b/nextflow.config
@ -88,6 +88,7 @@ params {
    // MALT
    run_malt                   = false
    malt_mode                  = 'BlastN'
+    malt_generatemegansummary = false

    // kraken2
    run_kraken2                = false
--- a/nextflow_schema.json
+++ b/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"
        }
    }
 }
--- a/subworkflows/local/profiling.nf
+++ b/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'
@ -95,33 +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_raw_profiles    = ch_raw_profiles.mix( MALT_RUN.out.rma6 )
+
+        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.name - ( '.' + rma.extension )
+                                        [ 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_versions             = ch_versions.mix( KRAKEN2_KRAKEN2.out.versions.first() )
+        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_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:
-    profiles = ch_raw_profiles    // channel: [ val(meta), [ reads ] ]
+    profiles = ch_raw_profiles    // channel: [ val(meta), [ reads ] ] - should be text files or biom
    versions = ch_versions          // channel: [ versions.yml ]
    mqc      = ch_multiqc_files
 }
--- a/subworkflows/local/shortread_postprocessing.nf
+++ b/subworkflows/local/shortread_postprocessing.nf
@ -1,39 +0,0 @@
-//
-// Perform read trimming and merging
-//
-
-
-include { SHORTREAD_FASTP             } from './shortread_fastp'
-include { SHORTREAD_ADAPTERREMOVAL    } from './shortread_adapterremoval'
-include { FASTQC as FASTQC_PROCESSED       } from '../../modules/nf-core/modules/fastqc/main'
-
-workflow SHORTREAD_POSTPROCESSING {
-    take:
-    input //  [ [ meta ], [ taxon_table/file ] ]
-
-    main:
-    ch_versions       = Channel.empty()
-    ch_multiqc_files  = Channel.empty()
-
-    if ( params.shortread_clipmerge_tool == "fastp" ) {
-        ch_processed_reads = SHORTREAD_FASTP ( reads ).reads
-        ch_versions        =  ch_versions.mix( SHORTREAD_FASTP.out.versions )
-        ch_multiqc_files   =  ch_multiqc_files.mix( SHORTREAD_FASTP.out.mqc )
-    } else if ( params.shortread_clipmerge_tool == "adapterremoval" ) {
-        ch_processed_reads = SHORTREAD_ADAPTERREMOVAL ( reads ).reads
-        ch_versions        = ch_versions.mix( SHORTREAD_ADAPTERREMOVAL.out.versions )
-        ch_multiqc_files   = ch_multiqc_files.mix( SHORTREAD_ADAPTERREMOVAL.out.mqc )
-    } else {
-        ch_processed_reads = reads
-    }
-
-    FASTQC_PROCESSED ( ch_processed_reads )
-    ch_versions = ch_versions.mix( FASTQC_PROCESSED.out.versions )
-    ch_multiqc_files = ch_multiqc_files.mix( FASTQC_PROCESSED.out.zip )
-
-    emit:
-    output   = output   // channel: [ val(meta), taxon_table ]
-    versions = ch_versions          // channel: [ versions.yml ]
-    mqc      = ch_multiqc_files
-}
-