Merge pull request #491 from sofstam/bracken_inter_files

Add flag to publish intermediate bracken files

CHANGELOG.md

@@ -12,6 +12,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Fixed`
 
 - [#484](https://github.com/nf-core/taxprofiler/pull/484) Improved input validation to immediately fail if run accession IDs within a given sample ID are not unique (❤️ to @sofstam for reporting, fixed by @jfy133)
+- [#491](https://github.com/nf-core/taxprofiler/pull/491) Added flag to publish intermediate bracken files (❤️ to @ewissel for reporting, fixed by @sofstam and @jfy133)
+- [489](https://github.com/nf-core/taxprofiler/pull/489) Fix KrakenUniq classified reads output format mismatch (❤️ to @SannaAb for reporting, fixed by @jfy133)
 
 ### `Dependencies`
 

conf/modules.config

@@ -467,7 +467,8 @@ process {
         publishDir = [
             path: { "${params.outdir}/kraken2/${meta.db_name}/" },
             mode: params.publish_dir_mode,
-            pattern: '*.{txt,fastq.gz}'
+            pattern: '*.{txt,fastq.gz}',
+            saveAs: {  !params.bracken_save_intermediatekraken2 && meta.tool == "bracken" ? null : it  }
         ]
     }
 

docs/output.md

@@ -376,11 +376,11 @@ The main taxonomic profiling file from Bracken is the `*.tsv` file. This provide
 
 - `kraken2/`
   - `<db_name>_combined_reports.txt`: A combined profile of all samples aligned to a given database (as generated by `krakentools`)
-    - If you have also run Bracken, the original Kraken report (i.e., _before_ read re-assignment) will also be included in this directory with `-bracken` suffixed to your Bracken database name. For example: `kraken2-<mydatabase>-bracken.tsv`. However in most cases you want to use the actual Bracken file (i.e., `bracken_<mydatabase>.tsv`).
+    - If you have also run Bracken, the original Kraken report (i.e., _before_ read re-assignment) will also be included in this directory with `-bracken` suffixed to your Bracken database name if you supply `--bracken_save_intermediatekraken2` to the run. For example: `kraken2-<mydatabase>-bracken.tsv`. However in most cases you want to use the actual Bracken file (i.e., `bracken_<mydatabase>.tsv`).
   - `<db_name>/`
     - `<sample_id>_<db_name>.classified.fastq.gz`: FASTQ file containing all reads that had a hit against a reference in the database for a given sample
     - `<sample_id>_<db_name>.unclassified.fastq.gz`: FASTQ file containing all reads that did not have a hit in the database for a given sample
-    - `<sample_id>_<db_name>.<kraken2/bracken2>report.txt`: A Kraken2 report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits in the Kraken2 run for a given sample. Will be 6 column rather than 8 if `--save_minimizers` specified.
+    - `<sample_id>_<db_name>.<kraken2/bracken2>report.txt`: A Kraken2 report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits in the Kraken2 run for a given sample. Will be 6 column rather than 8 if `--save_minimizers` specified. This report will **only** be included if you supply `--bracken_save_intermediatekraken2` to the run.
     - `<sample_id>_<db_name>.classifiedreads.txt`: A list of read IDs and the hits each read had against each database for a given sample
 
 </details>
@@ -389,6 +389,8 @@ The main taxonomic classification file from Kraken2 is the `_combined_reports.tx
 
 You will only receive the `.fastq` and `*classifiedreads.txt` file if you supply `--kraken2_save_reads` and/or `--kraken2_save_readclassifications` parameters to the pipeline.
 
+When running Bracken, you will only get the 'intermediate' Kraken2 report files in this directory if you supply `--bracken_save_intermediatekraken2` to the run.
+
 ### KrakenUniq
 
 [KrakenUniq](https://github.com/fbreitwieser/krakenuniq) (formerly KrakenHLL) is an extension to the fast k-mer-based classification performed by [Kraken](https://github.com/DerrickWood/kraken) with an efficient algorithm for additionally assessing the coverage of unique k-mers found in each species in a dataset.

nextflow.config

@@ -135,7 +135,8 @@ params {
     krakenuniq_batch_size               = 20
 
     // Bracken
-    run_bracken = false
+    run_bracken                      = false
+    bracken_save_intermediatekraken2 = false
 
     // centrifuge
     run_centrifuge             = false

nextflow_schema.json

@@ -466,6 +466,11 @@
                     "description": "Turn on Bracken (and the required Kraken2 prerequisite step).",
                     "fa_icon": "fas fa-toggle-on"
                 },
+                "bracken_save_intermediatekraken2": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-save",
+                    "description": "Turn on the saving of the intermediate Kraken2 files used as input to Bracken itself into Kraken2 results folder"
+                },
                 "run_malt": {
                     "type": "boolean",
                     "fa_icon": "fas fa-toggle-on",