nf-core · jfy133 · Sep 25, 2024 · Sep 19, 2024 · Sep 19, 2024 · Sep 19, 2024
@@ -7,17 +7,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
-- [#417](https://github.com/nf-core/taxprofiler/pull/417) - Added reference-free metagenome complexity/coverage estimation with Nonpareil (added by @jfy133)
-- [#466](https://github.com/nf-core/taxprofiler/pull/466) - Input database sheets can specify a `db_type` column to distinguish between short- and long-read databases (added by @LilyAnderssonLee)
-- [#505](https://github.com/nf-core/taxprofiler/pull/505) - Add small files to the file `tower.yml` (added by @LilyAnderssonLee)
-- [#508](https://github.com/nf-core/taxprofiler/pull/508) - Add `nanoq` as a filtering tool for nanopore reads (added by @LilyAnderssonLee)
-- [#511](https://github.com/nf-core/taxprofiler/pull/511) - Add `porechop_abi` as an alternative adapter removal tool for long reads nanopore data (added by @LilyAnderssonLee)
-- [#512](https://github.com/nf-core/taxprofiler/pull/512) - Update all tools to the latest version and include nf-test (updated by @LilyAnderssonLee & @jfy133)
+- [#417](https://github.com/nf-core/taxprofiler/pull/417) Added reference-free metagenome complexity/coverage estimation with Nonpareil (added by @jfy133)
+- [#466](https://github.com/nf-core/taxprofiler/pull/466) Input database sheets can specify a `db_type` column to distinguish between short- and long-read databases (added by @LilyAnderssonLee)
+- [#505](https://github.com/nf-core/taxprofiler/pull/505) Add small files to the file `tower.yml` (added by @LilyAnderssonLee)
+- [#508](https://github.com/nf-core/taxprofiler/pull/508) Add `nanoq` as a filtering tool for nanopore reads (added by @LilyAnderssonLee)
+- [#511](https://github.com/nf-core/taxprofiler/pull/511) Add `porechop_abi` as an alternative adapter removal tool for long reads nanopore data (added by @LilyAnderssonLee)
+- [#512](https://github.com/nf-core/taxprofiler/pull/512) Update all tools to the latest version and include nf-test (updated by @LilyAnderssonLee & @jfy133)
+- [#512](https://github.com/nf-core/taxprofiler/pull/532) Configure MultiQC to collapse stats of paired-read files into one line (by @jfy133)
 
 ### `Fixed`
 
 - [#518](https://github.com/nf-core/taxprofiler/pull/518) Fixed a bug where Oxford Nanopore FASTA input files would not be processed (❤️ to @ikarls for reporting, fixed by @jfy133)
 - [#523](https://github.com/nf-core/taxprofiler/pull/523) Removed hardcoded `-m lca` from GANON_CLASSIFY due to more options in new version of ganon (fixed by @LilyAnderssonLee & @jfy133)
+- [#531](https://github.com/nf-core/taxprofiler/pull/531) Fix FASTA input validation in schema allowing FASTQ extension, expand allowed FASTA extensions (fixed by @jfy133)
+- [#512](https://github.com/nf-core/taxprofiler/pull/532) Minor formatting and ordering improvements in MultiQC report (by @jfy133)
 - [#532](https://github.com/nf-core/taxprofiler/pull/532) - Added missing documentation behind the 'ignore' BRACKEN_BRACKEN error strategy (❤️ to @Mavti for reporting, fixed by @jfy133)
 
 ### `Dependencies`
@@ -35,7 +38,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | metaphlan     | 4.0.6            | 4.1.1       |
 | minimap2      | 2.24             | 2.28        |
 | motus/profile | 3.0.3            | 3.1.0       |
-| multiqc       | 1.21             | 1.24.1      |
+| multiqc       | 1.21             | 1.25        |
 | samtools      | 1.17             | 1.20        |
 
 ### `Deprecated`

@@ -18,41 +18,41 @@ report_section_order:
   fastqc-1:
     order: 800
   fastp:
+    order: 750
+  adapterremoval:
     order: 700
-  adapterRemoval:
-    order: 600
   nonpareil:
+    order: 600
+  bbduk:
     order: 500
+  prinseqplusplus:
+    order: 550
   porechop:
-    order: 400
-  porechop_abi:
     order: 450
-  bbduk:
-    order: 300
-  prinseqplusplus:
-    order: 200
+  porechop_abi:
+    order: 400
   filtlong:
-    order: 100
+    order: 350
   nanoq:
-    order: 95
+    order: 300
   bowtie2:
-    order: 90
+    order: 200
   samtools:
-    order: 80
+    order: 100
   kraken:
-    order: 70
+    order: 90
   bracken:
-    order: 60
+    order: 80
   centrifuge:
-    order: 50
+    order: 70
   malt:
-    order: 40
+    order: 60
   diamond:
-    order: 30
+    order: 50
   kaiju:
-    order: 20
+    order: 40
   motus:
-    order: 10
+    order: 30
 
 export_plots: true
 
@@ -63,7 +63,7 @@ custom_logo_title: "nf-core/taxprofiler"
 
 run_modules:
   - fastqc
-  - adapterRemoval
+  - adapterremoval
   - fastp
   - nonpareil
   - bbduk
@@ -72,7 +72,6 @@ run_modules:
   - filtlong
   - nanoq
   - bowtie2
-  - minimap2
   - samtools
   - kraken
   - kaiju
@@ -83,7 +82,7 @@ run_modules:
 
 sp:
   diamond:
-    fn_re: ".*.diamond.log$"
+    fn: "*.diamond.log"
   fastqc/data:
     fn_re: ".*(fastqc|falco)_data.txt$"
   fastqc/zip:
@@ -210,7 +209,8 @@ table_columns_placement:
   Filtlong:
     Target bases: 600
   nanoq:
-    Read N50: 700
+    Reads: 700
+    Read N50: 710
   BBDuk:
     Input reads: 800
     Total Removed bases percent: 810
@@ -312,6 +312,7 @@ table_columns_visible:
     Target bases: True
   nanoq:
     ReadN50: True
+    Reads: True
   BBDuk:
     Input reads: False
     Total Removed bases Percent: False
@@ -356,6 +357,17 @@ table_columns_name:
     reads_mapped: "Nr. Mapped Reads"
     reads_mapped_percent: "% Mapped Reads"
 
+## Allow collapsing of file names with _R1/_R2 or _1/_2 at the end
+table_sample_merge:
+  "Read 1":
+    - "_R1"
+    - type: regex
+      pattern: "[_.-][rR]?1$"
+  "Read 2":
+    - "_R2"
+    - type: regex
+      pattern: "[_.-][rR]?2$"
+
 extra_fn_clean_exts:
   - "kraken2.report.txt"
   - ".txt"
@@ -366,6 +378,7 @@ extra_fn_clean_exts:
   - "porechop"
   - "porechop_abi"
   - "_processed"
+  - ".diamond"
   - type: remove
     pattern: "_falco"
 

@@ -39,21 +39,21 @@
                 "format": "file-path",
                 "pattern": "^\\S+\\.f(ast)?q\\.gz$",
                 "unique": true,
-                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+                "errorMessage": "Gzipped FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
             },
             "fastq_2": {
                 "type": "string",
                 "format": "file-path",
                 "pattern": "^\\S+\\.f(ast)?q\\.gz$",
                 "unique": true,
-                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'. If not applicable, leave it empty."
+                "errorMessage": "Gzipped FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'. If not applicable, leave it empty."
             },
             "fasta": {
                 "type": "string",
                 "format": "file-path",
-                "pattern": "^\\S+\\.(f(ast)?q|fa(sta)?)\\.gz$",
+                "pattern": "^\\S+\\.(fasta|fas|fna|fa)\\.gz?$",
                 "unique": true,
-                "errorMessage": "FastA file must be provided, cannot contain spaces and must have extension '.fa.gz' or '.fasta.gz'. If not applicable, leave it empty."
+                "errorMessage": "Gzipped FastA file must be provided, cannot contain spaces and must have extension '.fa.gz', 'fna.gz', 'fas.gz', or '.fasta.gz'. If not applicable, leave it empty."
             }
         },
         "required": ["sample", "run_accession", "instrument_platform"]

@@ -723,7 +723,17 @@ You can expect in the MultiQC reports either sections and/or general stats colum
 - motus
 
 :::info
-The 'General Stats' table by default will only show statistics referring to pre-processing steps, and will not display possible values from each classifier/profiler, unless turned on by the user within the 'Configure Columns' menu or via a custom MultiQC config file (`--multiqc_config`)
+The 'General Stats' table by default will only show statistics referring to pre-processing steps, and will not display possible values from each classifier/profiler, unless turned on by the user within the 'Configure Columns' menu or via a custom MultiQC config file (`--multiqc_config`).
+
+For example, DIAMOND output does not have a dedicated section in the MultiQC HTML, only in the general stats table. To turn this on, copy the nf-core/taxprofiler [MultiQC config](https://github.com/nf-core/taxprofiler/blob/master/assets/multiqc_config.yml) and change the DIAMOND entry in `table_columns_visible:` to True.
+:::
+
+:::info
+In the 'General Stats' table, files that end with `_R1/_R2` or `_1/_2` prior the file format extension will be collapsed into single rows.
+
+It is assumed that file names only differening by these characters are associated paired-end reads and stats should be reported together.
+
+For example `sample1_R1.fastq.gz` and `sample1_R2.fastq.gz` will be reported together as `sample1`, with R1/R2 specific stats included inside the collapsed row.
 :::
 
 ### Pipeline information

@@ -101,6 +101,11 @@ An [example samplesheet](../assets/samplesheet.csv) has been provided with the p
 FASTA input will not go through any preprocessing steps, and will go directly to profiling.
 :::
 
+:::warning
+Files names prior the file format extension that include `_R1`/`_R2`, or `_1`/`_2` will be automatically be collapsed in the MultiQC report's General Stats table.
+Please see output documentation for more information.
+:::
+
 ### Full database sheet
 
 nf-core/taxprofiler supports multiple databases being classified/profiled against in parallel for each tool.

@@ -192,7 +192,7 @@
                     },
                     "multiqc": {
                         "branch": "master",
-                        "git_sha": "06c8865e36741e05ad32ef70ab3fac127486af48",
+                        "git_sha": "7c316cae26baf55e0add993bed2b0c9f7105c653",
                         "installed_by": ["modules"]
                     },
                     "nanoq": {

@@ -15,8 +15,9 @@ workflow NONPAREIL {
                                 .map {
                                     meta, reads ->
                                         def reads_new = meta.single_end ? reads : reads[0]
+                                        // taxprofiler only accepts gzipped input files,
+                                        // so don't need to account for getBaseName removing all extensions
                                         def format = reads_new[0].getBaseName().split('\\.').last() in ['fasta', 'fna', 'fa', 'fas'] ? 'fasta' : 'fastq'
-
                                     [meta, reads_new, format]
                                 }
                                 .multiMap {