Address review comments

.gitignore

@@ -9,3 +9,5 @@ testing*
 null/
 .nf-test
 .nf-test.log
+modules/nf-core/**/tests/
+subworkflows/nf-core/**/tests/

.nf-core.yml

@@ -4,14 +4,14 @@ lint:
     - tests/default.nf.test
   files_unchanged:
     - .github/CONTRIBUTING.md
+    - assets/nf-core-seqinspector_logo_light.png
     - docs/images/nf-core-seqinspector_logo_dark.png
     - docs/images/nf-core-seqinspector_logo_light.png
-    - assets/nf-core-seqinspector_logo_light.png
   nextflow_config:
     - config_defaults:
         - params.fastq_screen_references
   nf_test_content: false
-nf_core_version: 3.5.1
+nf_core_version: 3.5.2
 repository_type: pipeline
 template:
   author: Adrien Coulier

CHANGELOG.md

@@ -23,8 +23,8 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#100](https://github.com/nf-core/seqinspector/pull/100) Added official logos
 - [#103](https://github.com/nf-core/seqinspector/pull/103) Configure full-tests
 - [#106](https://github.com/nf-core/seqinspector/pull/106) Parse rundir metadata
-- [#108](https://github.com/nf-core/seqinspector/pull/108) Update lists of default steps in the pipeline (#86)
 - [#108](https://github.com/nf-core/seqinspector/pull/108) Test data validation (#94)
+- [#108](https://github.com/nf-core/seqinspector/pull/108) Update lists of default steps in the pipeline (#86)
 - [#110](https://github.com/nf-core/seqinspector/pull/110) Update input schema to accept either tar file or directory as rundir, and fastq messages and patterns
 - [#111](https://github.com/nf-core/seqinspector/pull/111) Short summary of seqinspector in README.md (#84)
 - [#127](https://github.com/nf-core/seqinspector/pull/127) Added alignment tools - bwamem2 - index and mem
@@ -36,6 +36,8 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#156](https://github.com/nf-core/seqinspector/pull/156) Added relative sample_size and warning when a sample has less reads than desired sample_size
 - [#159](https://github.com/nf-core/seqinspector/pull/159) Added a subworkflow QC_BAM including picard_collecthsmetrics for alignment QC of hybrid-selection data
 - [#162](https://github.com/nf-core/seqinspector/pull/162) Add tests for prepare_genome subworkflow
+- [#168](https://github.com/nf-core/seqinspector/pull/168) Add contributors list
+- [#168](https://github.com/nf-core/seqinspector/pull/168) Add logo to the pipeline logo
 
 ### `Fixed`
 
@@ -64,6 +66,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#148](https://github.com/nf-core/seqinspector/pull/148), [#152](https://github.com/nf-core/seqinspector/pull/152), [#153](https://github.com/nf-core/seqinspector/pull/153) Update documentation
 - [#158](https://github.com/nf-core/seqinspector/pull/158) Moved picard_collectmultiplemetrics to the subworkflow QC_BAM
 - [#164](https://github.com/nf-core/seqinspector/pull/164) Refactor local subworkflow and pipeline tests
+- [#168](https://github.com/nf-core/seqinspector/pull/168) Adhere to strict syntax
 
 ### `Dependencies`
 

CITATIONS.md

@@ -10,35 +10,39 @@
 
 ## Pipeline tools
 
-- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+- [Bowtie2](https://www.nature.com/articles/nmeth.1923)
 
-> Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
+  > Langmead B, Salzberg SL. Fast gapped-read alignment with Bowtie 2. Nat Methods. 2012 Apr;9(4):357-9. doi: 10.1038/nmeth.1923. PubMed PMID: 22388286.
 
-- [SeqFu](https://telatin.github.io/seqfu2/)
+- [BWAMEM2](https://ieeexplore.ieee.org/abstract/document/8820962)
 
-> Telatin A, Fariselli P, Birolo G. SeqFu: A Suite of Utilities for the Robust and Reproducible Manipulation of Sequence Files. Bioengineering 2021, 8, 59. doi.org/10.3390/bioengineering8050059
+  > Vasimuddin Md, Misra S, Li H, Aluru S. Efficient Architecture-Aware Acceleration of BWA-MEM for Multicore Systems. In: 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE; 2019:314-324. doi:10.1109/IPDPS.2019.00041
+
+- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+
+  > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
 
 - [FastQ Screen](https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/)
 
-> Wingett SW and Andrews S. FastQ Screen: A tool for multi-genome mapping and quality control [version 2; referees: 4 approved]. F1000Research 2018, 7:1338 (https://doi.org/10.12688/f1000research.15931.2)
+  > Wingett SW and Andrews S. FastQ Screen: A tool for multi-genome mapping and quality control [version 2; referees: 4 approved]. F1000Research 2018, 7:1338 (https://doi.org/10.12688/f1000research.15931.2)
 
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
 
-> Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
-
-- [Seqtk](https://github.com/lh3/seqtk)
+  > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
 
-- [BWAMEM2](https://ieeexplore.ieee.org/abstract/document/8820962)
+- [Picard Tools](https://broadinstitute.github.io/picard/)
 
-> Vasimuddin Md, Misra S, Li H, Aluru S. Efficient Architecture-Aware Acceleration of BWA-MEM for Multicore Systems. In: 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE; 2019:314-324. doi:10.1109/IPDPS.2019.00041
+  > Broad Institute, “Picard Toolkit.” 2019. GitHub Repository. https://broadinstitute.github.io/picard/
 
 - [SAMTOOLS](https://academic.oup.com/bioinformatics/article/25/16/2078/204688)
 
-> Danecek P, Bonfield JK, Liddle J, et al. Twelve years of SAMtools and BCFtools. GigaScience. 2021;10(2):giab008. doi:10.1093/gigascience/giab008
+  > Danecek P, Bonfield JK, Liddle J, et al. Twelve years of SAMtools and BCFtools. GigaScience. 2021;10(2):giab008. doi:10.1093/gigascience/giab008
 
-- [Picard Tools](https://broadinstitute.github.io/picard/)
+- [SeqFu](https://telatin.github.io/seqfu2/)
+
+  > Telatin A, Fariselli P, Birolo G. SeqFu: A Suite of Utilities for the Robust and Reproducible Manipulation of Sequence Files. Bioengineering 2021, 8, 59. doi.org/10.3390/bioengineering8050059
 
-> Broad Institute, “Picard Toolkit.” 2019. GitHub Repository. https://broadinstitute.github.io/picard/
+- [Seqtk](https://github.com/lh3/seqtk)
 
 ## Software packaging/containerisation tools
 

README.md

@@ -21,19 +21,10 @@
 
 ## Introduction
 
-<picture>
-  <source media="(prefers-color-scheme: dark)" srcset="docs/images/nf-core-seqinspector_logo_dark.png">
-  <source media="(prefers-color-scheme: light)" srcset="docs/images/nf-core-seqinspector_logo_light.png">
-  <img alt="Fallback image description" src="docs/images/nf-core-seqinspector_logo_light.png">
-</picture>
-
-<picture>
-  <source media="(prefers-color-scheme: dark)" srcset="docs/images/nfcore-seqinspector-logo-hex-dark.png">
-  <source media="(prefers-color-scheme: light)" srcset="docs/images/nfcore-seqinspector-logo-hex-light.png">
-  <img alt="Fallback image description" src="docs/images/nfcore-seqinspector-logo-hex-light.png">
-</picture>
-
-**nf-core/seqinspector** is a bioinformatics pipeline that that processes raw sequence data (FASTQ) to provide comprehensive quality control. It can perform subsampling, quality assessment, duplication level analysis, and complexity evaluation on a per-sample basis, while also detecting adapter content, technical artifacts, and common biological contaminants. The pipeline generates detailed MultiQC reports with flexible output options, ranging from individual sample reports to project-wide summaries, making it particularly useful for sequencing core facilities and research groups with access to sequencing instruments. If provided, nf-core/seqinspector can also parse statistics from an Illumina run folder directory into the final MultiQC reports.
+**nf-core/seqinspector** is a bioinformatics pipeline that processes raw sequence data (FASTQ) to provide comprehensive quality control.
+It can perform subsampling, quality assessment, duplication level analysis, and complexity evaluation on a per-sample basis, while also detecting adapter content, technical artifacts, and common biological contaminants.
+The pipeline generates detailed MultiQC reports with flexible output options, ranging from individual sample reports to project-wide summaries, making it particularly useful for sequencing core facilities and research groups with access to sequencing instruments.
+If provided, nf-core/seqinspector can also parse statistics from an Illumina run folder directory into the final MultiQC reports.
 
 <!-- TODO: add a search tool that accepts a tree for `Compatibility with Data`. -->
 
@@ -69,7 +60,9 @@ sample,fastq_1,fastq_2,rundir,tags
 CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX,lane1:project5:group2
 ```
 
-Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
+Each row represents a fastq file (single-end with only `fastq_1`) or a pair of fastq files (paired end with `fastq_1` and `fastq_2`).
+`rundir` is the path to the runfolder.
+`tags` is a colon-separated list of tags that will be added to the MultiQC report for this `sample`.
 
 Now, you can run the pipeline using:
 
@@ -93,11 +86,29 @@ For more details about the output files and reports, please refer to the
 
 ## Credits
 
-nf-core/seqinspector was originally written by the Swedish [@NationalGenomicsInfrastructure](https://github.com/NationalGenomicsInfrastructure/) and [Clinical Genomics Stockholm](https://clinical.scilifelab.se/).
+nf-core/seqinspector was originally written by [@agrima2010](https://github.com/agrima2010), [@Aratz](https://github.com/Aratz), [@FranBonath](https://github.com/FranBonath), [@kedhammar](https://github.com/kedhammar), and [@MatthiasZepper](https://github.com/MatthiasZepper) from the Swedish [@NationalGenomicsInfrastructure](https://github.com/NationalGenomicsInfrastructure/) and [Clinical Genomics Stockholm](https://clinical.scilifelab.se/).
 
 We thank the following people for their extensive assistance in the development of this pipeline:
 
+- [@adamrtalbot](https://github.com/adamrtalbot)
+- [@alneberg](https://github.com/alneberg)
+- [@beatrizsavinhas](https://github.com/beatrizsavinhas)
+- [@ctuni](https://github.com/ctuni)
+- [@edmundmiller](https://github.com/edmundmiller)
+- [@EliottBo](https://github.com/EliottBo)
+- [@KarNair](https://github.com/KarNair)
+- [@kjellinjonas](https://github.com/kjellinjonas)
 - [@mahesh-panchal](https://github.com/mahesh-panchal)
+- [@matrulda](https://github.com/matrulda)
+- [@maxulysse](https://github.com/maxulysse)
+- [@mirpedrol](https://github.com/mirpedrol)
+- [@nggvs](https://github.com/nggvs)
+- [@nkongenelly](https://github.com/nkongenelly)
+- [@Patricie34](https://github.com/Patricie34)
+- [@pontushojer](https://github.com/pontushojer)
+- [@ramprasadn](https://github.com/ramprasadn)
+- [@rannick](https://github.com/rannick)
+- [@torigiffin](https://github.com/torigiffin)
 
 ## Contributions and Support
 

conf/base.config

@@ -9,8 +9,6 @@
 */
 
 process {
-
-    // TODO nf-core: Check the defaults for all processes
     cpus   = { 1      * task.attempt }
     memory = { 6.GB   * task.attempt }
     time   = { 4.h    * task.attempt }
@@ -24,7 +22,6 @@ process {
     //        These labels are used and recognised by default in DSL2 files hosted on nf-core/modules.
     //        If possible, it would be nice to keep the same label naming convention when
     //        adding in your local modules too.
-    // TODO nf-core: Customise requirements for specific processes.
     // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
     withLabel:process_single {
         cpus   = { 1                   }

conf/modules.config

@@ -117,22 +117,18 @@ process {
         publishDir = [
             path: { "${params.outdir}/multiqc/group_reports" },
             mode: params.publish_dir_mode,
-            saveAs: {
-                filename ->
-                    switch (filename) {
-                        case 'versions.yml':
-                            null
-                            break
-                        case ~/\[TAG:.+\]_multiqc_(report\.html|plots|data)/:
-                            def tag = (filename =~ /\[TAG:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
-                            def new_filename = filename.replaceFirst(
-                                "(?<prefix>.*)\\[TAG:${tag}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
-                                '${prefix}${suffix}')
-                            "${tag}/${new_filename}"
-                            break
-                        default:
-                            filename
-                    }
+            saveAs: { filename ->
+                if (filename == 'versions.yml') {
+                    return null
+                } else if (filename  =~/\[TAG:.+\]_multiqc_(report\.html|plots|data)/) {
+                        def tag = (filename =~ /\[TAG:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
+                        def new_filename = filename.replaceFirst(
+                            "(?<prefix>.*)\\[TAG:${tag}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
+                            '${prefix}${suffix}')
+                    return "${tag}/${new_filename}"
+                } else {
+                    return filename
+                }
             }
         ]
     }