Merge pull request #240 from nf-core/move-kaiju2table

Move kaiju2table to profiling

conf/modules.config

@@ -486,7 +486,16 @@ process {
         ext.args = { "${meta.db_params}" }
     }
 
-    withName: KAIJU_KAIJU2TABLE {
+    withName: '.*PROFILING:KAIJU_KAIJU2TABLE' {
+        ext.prefix = params.perform_runmerging ? { "${meta.id}_${meta.db_name}.kaijutable" } : { "${meta.id}_${meta.run_accession}_${meta.db_name}.kaijutable" }
+        publishDir = [
+            path: { "${params.outdir}/kaiju/${meta.db_name}/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{txt}'
+        ]
+    }
+
+    withName: '.*STANDARDISATION_PROFILES:KAIJU_KAIJU2TABLE' {
         ext.prefix = { "kaiju_${meta.id}_combined_reports" }
         publishDir = [
             path: { "${params.outdir}/kaiju/" },

docs/output.md

@@ -332,18 +332,20 @@ The main taxonomic classification files from Centrifuge are the `_combined_repor
 
 ### Kaiju
 
-[Kaiju](https://github.com/bioinformatics-centre/kaiju) is a taxonomic classifier that finds maximum exact matches on the protein-level using the Burrows–Wheeler transform.
+[Kaiju](https://github.com/bioinformatics-centre/kaiju) is a taxonomic classifier that finds maximum exact matches on the protein-level using the Burrows-Wheeler transform.
 
 <details markdown="1">
 <summary>Output files</summary>
 
 - `kaiju`
-  - `<sample_id>.tsv`: A file that summarises the fraction abundance, taxonomic ID, number of reads and taxonomic names
-  - `kaiju_<db_name>_combined_reports.txt`: A combined profile of all samples aligned to a given database (as generated by `kaiju2table`)
+  - `kaiju_<db_name>_combined_reports.txt`: A combined profile of all samples aligned to a given database (as generated by kaiju2table)
+  - `<db_name>/`
+    - `<sample_id>_<db_name>.kaiju.tsv`: Raw output from Kaiju with taxonomic rank, read ID and taxonic ID
+    - `<sample_id>_<db_name>.kaijutable.txt`: Summarised Kaiju output with fraction abundance, taxonomic ID, number of reads, and taxonomic names (as generated by `kaiju2table`)
 
 </details>
 
-The most summary file is the `*combined_reports.txt` file which summarises results across all samples. However if you wish to look at more precise information about each assignment, check the per-sample file. The default taxonomic rank is `species`. You can provide a different one by updating the argument `--kaiju_taxon_rank`.
+The most useful summary file is the `_combined_reports.txt` file which summarises hits across all reads and samples. Separate per-sample versions summaries can be seen in `<db>/*.txt`. However if you wish to look at more precise information on a per-read basis, see the `*tsv` file. The default taxonomic rank is `species`. You can provide a different one by updating the argument `--kaiju_taxon_rank`.
 
 ### DIAMOND
 

subworkflows/local/profiling.nf

@@ -5,12 +5,13 @@
 include { MALT_RUN                              } from '../../modules/nf-core/malt/run/main'
 include { MEGAN_RMA2INFO as MEGAN_RMA2INFO_TSV  } from '../../modules/nf-core/megan/rma2info/main'
 include { KRAKEN2_KRAKEN2                       } from '../../modules/nf-core/kraken2/kraken2/main'
-include { KRAKEN2_STANDARD_REPORT                } from '../../modules/local/kraken2_standard_report'
+include { KRAKEN2_STANDARD_REPORT               } from '../../modules/local/kraken2_standard_report'
 include { BRACKEN_BRACKEN                       } from '../../modules/nf-core/bracken/bracken/main'
 include { CENTRIFUGE_CENTRIFUGE                 } from '../../modules/nf-core/centrifuge/centrifuge/main'
 include { CENTRIFUGE_KREPORT                    } from '../../modules/nf-core/centrifuge/kreport/main'
 include { METAPHLAN3_METAPHLAN3                 } from '../../modules/nf-core/metaphlan3/metaphlan3/main'
 include { KAIJU_KAIJU                           } from '../../modules/nf-core/kaiju/kaiju/main'
+include { KAIJU_KAIJU2TABLE                     } from '../../modules/nf-core/kaiju/kaiju2table/main'
 include { DIAMOND_BLASTX                        } from '../../modules/nf-core/diamond/blastx/main'
 include { MOTUS_PROFILE                         } from '../../modules/nf-core/motus/profile/main'
 include { KRAKENUNIQ_PRELOADEDKRAKENUNIQ        } from '../../modules/nf-core/krakenuniq/preloadedkrakenuniq/main'
@@ -271,6 +272,10 @@ workflow PROFILING {
         ch_versions = ch_versions.mix( KAIJU_KAIJU.out.versions.first() )
         ch_raw_classifications = ch_raw_classifications.mix( KAIJU_KAIJU.out.results )
 
+        KAIJU_KAIJU2TABLE ( KAIJU_KAIJU.out.results, ch_input_for_kaiju.db, params.kaiju_taxon_rank)
+        ch_versions = ch_versions.mix( KAIJU_KAIJU2TABLE.out.versions )
+        ch_multiqc_files = ch_multiqc_files.mix( KAIJU_KAIJU2TABLE.out.summary )
+        ch_raw_profiles    = ch_raw_profiles.mix( KAIJU_KAIJU2TABLE.out.summary )
     }
 
     if ( params.run_diamond ) {