Merge pull request #253 from nf-core/futher-further-prerelease-updates

Futher further prerelease updates: FALCO display in MultiQC

assets/multiqc_config.yml

@@ -39,6 +39,10 @@ sp:
   diamond:
     contents: "diamond v"
     num_lines: 10
+  fastqc/data:
+    fn_re: ".*(fastqc|falco)_data.txt$"
+  fastqc/zip:
+    fn: "*_fastqc.zip"
 
 #extra_fn_clean_exts:
 #    - '_fastp'
@@ -47,25 +51,23 @@ sp:
 
 top_modules:
   - "fastqc":
-      name: "FastQC (pre-Trimming)"
+      name: "FastQC / Falco (pre-Trimming)"
       path_filters:
-        - "*raw_*fastqc.zip"
+        - "*raw*"
+      path_filters_exclude:
+        - "*processed*"
+      extra: "If used in this run, Falco is a drop-in replacement for FastQC producing the same output, written by Guilherme de Sena Brandine and Andrew D. Smith."
   - "fastqc":
-      name: "Falco (pre-Trimming)"
+      name: "FastQC / Falco (post-Trimming)"
       path_filters:
-        - "*_raw_falco_*_report.html"
+        - "*processed*"
+      path_filters_exclude:
+        - "*raw*"
+      extra: "If used in this run, Falco is a drop-in replacement for FastQC producing the same output, written by Guilherme de Sena Brandine and Andrew D. Smith."
   - "fastp"
   - "adapterRemoval"
   - "porechop":
       extra: "ℹ️: if you get the error message 'Error - was not able to plot data.' this means that porechop did not detect any adapters and therefore no statistics generated."
-  - "fastqc":
-      name: "FastQC (post-Trimming)"
-      path_filters:
-        - "*_processed_*fastqc.zip"
-  - "fastqc":
-      name: "Falco (post-Trimming)"
-      path_filters:
-        - "*_processed_falco_*_report.html"
   - "bbduk"
   - "prinseqplusplus"
   - "filtlong"
@@ -105,19 +107,20 @@ top_modules:
 #It is not possible to set placement for custom kraken and centrifuge columns.
 
 table_columns_placement:
-  FastQC (pre-Trimming):
+  FastQC / Falco (pre-Trimming):
     total_sequences: 100
     avg_sequence_length: 110
     median_sequence_length: 120
     percent_duplicates: 130
     percent_gc: 140
     percent_fails: 150
-  Falco (pre-Trimming):
+  FastQC / Falco (post-Trimming):
     total_sequences: 200
     avg_sequence_length: 210
-    percent_duplicates: 220
+    median_sequence_length: 220
-    percent_gc: 230
+    percent_duplicates: 230
-    percent_fails: 240
+    percent_gc: 240
+    percent_fails: 250
   fastp:
     pct_adapter: 300
     pct_surviving: 310
@@ -141,19 +144,6 @@ table_columns_placement:
     Middle Split Percent: 460
   Filtlong:
     Target bases: 500
-  FastQC (post-Trimming):
-    total_sequences: 600
-    avg_sequence_length: 610
-    median_sequence_length: 620
-    percent_duplicates: 630
-    percent_gc: 640
-    percent_fails: 650
-  Falco (post-Trimming):
-    total_sequences: 700
-    avg_sequence_length: 710
-    percent_duplicates: 720
-    percent_gc: 730
-    percent_fails: 740
   BBDuk:
     Input reads: 800
     Total Removed bases percent: 810
@@ -205,25 +195,18 @@ table_columns_placement:
     "Number of ext-mOTUs": 1880
 
 table_columns_visible:
-  FastQC (pre-Trimming):
+  FastQC / Falco (pre-Trimming):
     total_sequences: True
     avg_sequence_length: True
     percent_duplicates: True
     percent_gc: True
     percent_fails: False
-  Falco (pre-Trimming):
+  FastQC / Falco (post-Trimming):
     total_sequences: True
     avg_sequence_length: True
-    percent_duplicates: True
+    percent_duplicates: False
-    percent_gc: True
+    percent_gc: False
     percent_fails: False
-  fastp:
-    pct_adapter: True
-    pct_surviving: True
-    pct_duplication: False
-    after_filtering_gc_content: False
-    after_filtering_q30_rate: False
-    after_filtering_q30_bases: False
   porechop:
     Input reads: False
     Start Trimmed:
@@ -232,6 +215,13 @@ table_columns_visible:
     End Trimmed Percent: True
     Middle Split: False
     Middle Split Percent: True
+  fastp:
+    pct_adapter: True
+    pct_surviving: True
+    pct_duplication: False
+    after_filtering_gc_content: False
+    after_filtering_q30_rate: False
+    after_filtering_q30_bases: False
   Filtlong:
     Target bases: True
   Adapter Removal:
@@ -239,18 +229,6 @@ table_columns_visible:
     percent_aligned: True
     percent_collapsed: True
     percent_discarded: False
-  FastQC (post-Trimming):
-    total_sequences: True
-    avg_sequence_length: True
-    percent_duplicates: False
-    percent_gc: False
-    percent_fails: False
-  Falco (post-Trimming):
-    total_sequences: True
-    avg_sequence_length: True
-    percent_duplicates: False
-    percent_gc: False
-    percent_fails: False
   BBDuk:
     Input reads: False
     Total Removed bases Percent: False
@@ -278,25 +256,13 @@ table_columns_visible:
   motus: False
 
 table_columns_name:
-  FastQC (pre-Trimming):
+  FastQC / Falco (pre-Trimming):
     total_sequences: "Nr. Input Reads"
     avg_sequence_length: "Length Input Reads"
     percent_gc: "% GC Input Reads"
     percent_duplicates: "% Dups Input Reads"
     percent_fails: "% Failed Input Reads"
-  Falco (pre-Trimming):
+  FastQC / Falco (post-Trimming):
-    total_sequences: "Nr. Input Reads"
-    avg_sequence_length: "Length Input Reads"
-    percent_gc: "% GC Input Reads"
-    percent_duplicates: "% Dups Input Reads"
-    percent_fails: "% Failed Input Reads"
-  FastQC (post-Trimming):
-    total_sequences: "Nr. Processed Reads"
-    avg_sequence_length: "Length Processed Reads"
-    percent_gc: "% GC Processed Reads"
-    percent_duplicates: "% Dups Processed Reads"
-    percent_fails: "% Failed Processed Reads"
-  Falco (post-Trimming):
     total_sequences: "Nr. Processed Reads"
     avg_sequence_length: "Length Processed Reads"
     percent_gc: "% GC Processed Reads"
@@ -314,7 +280,8 @@ extra_fn_clean_exts:
   - ".bbduk"
   - ".unmapped"
   - "_filtered"
-  - "_processed"
+  - type: remove
+    pattern: "_falco"
 
 section_comments:
   general_stats: "By default, all read count columns are displayed as millions (M) of reads."

conf/modules.config

@@ -486,7 +486,7 @@ process {
         ext.args = { "${meta.db_params}" }
     }
 
-    withName: '.*PROFILING:KAIJU_KAIJU2TABLE' {
+    withName: 'KAIJU_KAIJU2TABLE_SINGLE' {
         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}/" },
@@ -495,7 +495,7 @@ process {
         ]
     }
 
-    withName: '.*STANDARDISATION_PROFILES:KAIJU_KAIJU2TABLE' {
+    withName: 'KAIJU_KAIJU2TABLE_COMBINED' {
         ext.prefix = { "kaiju_${meta.id}_combined_reports" }
         publishDir = [
             path: { "${params.outdir}/kaiju/" },

docs/output.md

@@ -35,19 +35,21 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
-### FastQC or falco
+### FastQC or Falco
 
 <details markdown="1">
 <summary>Output files</summary>
 
 - `fastqc/`
-  - `*_fastqc.html`: FastQC report containing quality metrics.
+  - `*_fastqc.html`: FastQC or Falco report containing quality metrics.
-  - `*_fastqc.zip`: Zip archive containing the FastQC report, tab-delimited data file and plot images.
+  - `*_fastqc.zip`: Zip archive containing the FastQC report, tab-delimited data file and plot images (FastQC only).
 
 </details>
 
 [FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your sequenced reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. For further reading and documentation see the [FastQC help pages](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/).
 
+If preprocessing is turned on, nf-core/taxprofiler runs FastQC/Falco twice -once before and once after adapter removal/read merging, to allow evaluation of the performance of these preprocessing steps. Note in the General Stats table, the columns of these two instances of FastQC/Falco are placed next to each other to make it easier to evaluate. However, the columns of the actual preprocessing steps (i.e, fastp, AdapterRemoval, and Porechop) will be displayed _after_ the two FastQC/Falco columns, even if they were run 'between' the two FastQC/Falco jobs in the pipeline itself.
+
 > ℹ️ Falco produces identical output to FastQC but in the `falco/` directory.
 
 ![MultiQC - FastQC sequence counts plot](images/mqc_fastqc_counts.png)
@@ -56,8 +58,6 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 ![MultiQC - FastQC adapter content plot](images/mqc_fastqc_adapter.png)
 
-> **NB:** The FastQC plots displayed in the MultiQC report shows _untrimmed_ reads. They may contain adapter sequence and potentially regions with low quality.
-
 ### fastp
 
 [fastp](https://github.com/OpenGene/fastp) is a FASTQ pre-processing tool for quality control, trimmming of adapters, quality filtering and other features.

subworkflows/local/profiling.nf

@@ -11,7 +11,7 @@ include { CENTRIFUGE_CENTRIFUGE                 } from '../../modules/nf-core/ce
 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 { KAIJU_KAIJU2TABLE as KAIJU_KAIJU2TABLE_SINGLE } 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'
@@ -272,10 +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)
+        KAIJU_KAIJU2TABLE_SINGLE ( KAIJU_KAIJU.out.results, ch_input_for_kaiju.db, params.kaiju_taxon_rank)
-        ch_versions = ch_versions.mix( KAIJU_KAIJU2TABLE.out.versions )
+        ch_versions = ch_versions.mix( KAIJU_KAIJU2TABLE_SINGLE.out.versions )
-        ch_multiqc_files = ch_multiqc_files.mix( KAIJU_KAIJU2TABLE.out.summary )
+        ch_multiqc_files = ch_multiqc_files.mix( KAIJU_KAIJU2TABLE_SINGLE.out.summary )
-        ch_raw_profiles    = ch_raw_profiles.mix( KAIJU_KAIJU2TABLE.out.summary )
+        ch_raw_profiles    = ch_raw_profiles.mix( KAIJU_KAIJU2TABLE_SINGLE.out.summary )
     }
 
     if ( params.run_diamond ) {

subworkflows/local/standardisation_profiles.nf

@@ -3,7 +3,7 @@
 //
 
 include { BRACKEN_COMBINEBRACKENOUTPUTS                                         } from '../../modules/nf-core/bracken/combinebrackenoutputs/main'
-include { KAIJU_KAIJU2TABLE                                                     } from '../../modules/nf-core/kaiju/kaiju2table/main'
+include { KAIJU_KAIJU2TABLE as KAIJU_KAIJU2TABLE_COMBINED                       } 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'
 include { METAPHLAN3_MERGEMETAPHLANTABLES                                       } from '../../modules/nf-core/metaphlan3/mergemetaphlantables/main'
@@ -103,9 +103,9 @@ workflow STANDARDISATION_PROFILES {
                                     [[id:it[0]], it[1]]
                                 }
 
-    KAIJU_KAIJU2TABLE ( ch_profiles_for_kaiju, ch_input_databases.kaiju.map{it[1]}, params.kaiju_taxon_rank)
+    KAIJU_KAIJU2TABLE_COMBINED ( ch_profiles_for_kaiju, ch_input_databases.kaiju.map{it[1]}, params.kaiju_taxon_rank)
-    ch_multiqc_files = ch_multiqc_files.mix( KAIJU_KAIJU2TABLE.out.summary )
+    ch_multiqc_files = ch_multiqc_files.mix( KAIJU_KAIJU2TABLE_COMBINED.out.summary )
-    ch_versions = ch_versions.mix( KAIJU_KAIJU2TABLE.out.versions )
+    ch_versions = ch_versions.mix( KAIJU_KAIJU2TABLE_COMBINED.out.versions )
 
     // Kraken2