Merge pull request #377 from bbglab/dev

New release: v1.0.0 Ter

Author: FerriolCalvet

.gitignore

@@ -11,3 +11,5 @@ nf-*-reports.tsv
 *.sif
 ste_notes.txt
 assets/HDP_files*
+scratch/
+scratchhhh/

CITATIONS.md

@@ -8,16 +8,42 @@
 
 > Di Tommaso P, Chatzou M, Floden EW, Barja PP, Palumbo E, Notredame C. Nextflow enables reproducible computational workflows. Nat Biotechnol. 2017 Apr 11;35(4):316-319. doi: 10.1038/nbt.3820. PubMed PMID: 28398311.
 
-## Pipeline tools
+## Sources of data and tools
 
-- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+- Nanoseq masks
 
-  > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
+  > Abascal, F., Harvey, L.M.R., Mitchell, E. et al. Somatic mutation landscapes at single-molecule resolution. Nature 593, 405–410 (2021). https://doi.org/10.1038/s41586-021-03477-4
+
+- **CADD scores**
+
+  > Schubach M, Maass T, Nazaretyan L, Röner S, Kircher M. CADD v1.7: Using protein language models, regulatory CNNs and other nucleotide-level scores to improve genome-wide variant predictions. Nucleic Acids Res. 2024 Jan 5. doi: 10.1093/nar/gkad989. PubMed PMID: 38183205.
+
+- COSMIC signatures
+
+  > https://cancer.sanger.ac.uk/signatures/sbs
+
+- **dNdScv covariates**
+
+  > Martincorena I, et al. (2017) Universal Patterns of Selection in Cancer and Somatic Tissues. Cell. http://www.cell.com/cell/fulltext/S0092-8674(17)31136-4
+
+- Pfam 
+
+  > Jaina Mistry, Sara Chuguransky, Lowri Williams, Matloob Qureshi, Gustavo A Salazar, Erik L L Sonnhammer, Silvio C E Tosatto, Lisanna Paladin, Shriya Raj, Lorna J Richardson, Robert D Finn, Alex Bateman, Pfam: The protein families database in 2021, Nucleic Acids Research, Volume 49, Issue D1, 8 January 2021, Pages D412–D419, https://doi.org/10.1093/nar/gkaa913
+
+- **Oncodrive3D & Oncodrive3D datasets.**
+
+  > Stefano Pellegrini, Olivia Dove-Estrella, Ferran Muiños, Nuria Lopez-Bigas, Abel Gonzalez-Perez, Oncodrive3D: fast and accurate detection of structural clusters of somatic mutations under positive selection, Nucleic Acids Research, Volume 53, Issue 15, 28 August 2025, gkaf776, https://doi.org/10.1093/nar/gkaf776
 
 - [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.
 
+- Python
+- SigProfilerAssignment, MatrixGenerator
+- HDP
+- OncodriveFML
+- OncodriveCLUSTL
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

LICENSE

@@ -1,7 +1,17 @@
-Placeholder License - Temporary Notice
+Copyright (C) 2025 Institute for Research in Biomedicine (IRB Barcelona)
 
-This repository is temporarily published without a definitive open-source license.
+deepCSA is the property of the Institute for Research in Biomedicine 
+(IRB Barcelona), which hold the copyright thereto.
 
-The final license (GPLv3, AGPLv3, or other) will be confirmed and updated as soon as possible, and no later than the manuscript's publication.
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as
+published by the Free Software Foundation, either version 3 of the
+License, or (at your option) any later version.
 
-Until the final license is in place, this code is provided for **review purposes only**, it can be run, but it must not be used, modified, or redistributed without explicit permission from the authors.
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>

README.md

@@ -6,15 +6,10 @@
 
 ![deepCSA workflow overview](docs/images/deepCSA.png)
 
-<!-- TODO nf-core: Include a figure that guides the user through the major workflow steps. Many nf-core
-     workflows use the "tube map" design for that. See https://nf-co.re/docs/contributing/design_guidelines#examples for examples.   -->
-<!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->
-
-<!-- 1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
-2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)) -->
-
 ## Usage
 
+You can find a detailed documentation in the [docs section](docs/README.md), but here there is a minimal summary on how to prepare the inputs. Still for your first runs if you need to make the complete set up you have to check the deeper documentation.
+
 First, prepare a samplesheet with your input data that looks as follows:
 
 `samplesheet.csv`:
@@ -43,12 +38,6 @@ nextflow run main.nf --outdir <OUTDIR> -profile singularity,<DESIRED PROFILE> -p
 
 The input can be provided by the `--input` option but it is more recommended to define this and all the other parameters in a parameter file (i.e. `pipeline_params.yml`), that can be provided to the pipeline for running the analysis with the specified configuration. This will also allow the definition of the remaining required parameters.
 
-### Warning
-
-Please provide pipeline parameters via the Nextflow `-params-file` option or CLI. Custom config files including those
-provided by the `-c` Nextflow option can be used to provide any configuration **except for parameters**_;
-see [docs](https://nf-co.re/usage/configuration#custom-configuration-files).
-
 ## Credits
 
 bbglab/deepCSA was originally written by Ferriol Calvet.
@@ -62,20 +51,11 @@ We thank the following people for their extensive assistance in the development
 * @AxelRosendahlHuber
 * @andrianovam
 * @migrau
-
-<!-- TODO 
-## Contributions and Support
-
-If you would like to contribute to this pipeline, please see the [contributing guidelines](.github/CONTRIBUTING.md).
- -->
+* @rochamorro1
+* @m-huertasp
 
 ## Citations
 
-<!-- TODO nf-core: Add citation for pipeline after first release. Uncomment lines below and update Zenodo doi and badge at the top of this file. -->
-<!-- If you use  bbglab/deepCSA for your analysis, please cite it using the following doi: [10.5281/zenodo.XXXXXX](https://doi.org/10.5281/zenodo.XXXXXX) -->
-
-<!-- TODO nf-core: Add bibliography of tools and data used in your pipeline -->
-
 An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.
 
 This pipeline uses code and infrastructure developed and maintained by the [nf-core](https://nf-co.re) community, reused here under the [MIT license](https://github.com/nf-core/tools/blob/master/LICENSE).
@@ -89,3 +69,9 @@ This pipeline uses code and infrastructure developed and maintained by the [nf-c
 ## Documentation
 
 Find the documentation ([link to docs](https://github.com/bbglab/deepCSA/tree/main/docs)).
+
+We are working to provide the biggest possible detail on the [usage](docs/usage.md) and explanation of the rationale and [tools](docs/tools.md), but this is still in progress.
+
+## Publications
+
+> [Sex and smoking bias in the selection of somatic mutations in human bladder](https://www.nature.com/articles/s41586-025-09521-x)

assets/useful_scripts/deepcsa_maf2samplevcfs.py

@@ -674,9 +674,7 @@ def generate_plot(gene,
                                                                                          gene_pos)
 
     # Domain
-    domain_gene = o3d_annot_df[(o3d_annot_df["Gene"] == gene) &
-                               (o3d_annot_df["Type"] == "DOMAIN") &
-                               (o3d_annot_df["Evidence"] == "Pfam")].reset_index(drop=True)
+    domain_gene = o3d_annot_df[(o3d_annot_df["Gene"] == gene)].reset_index(drop=True)
 
     # Transcripts and Uniprot ID
     canonical_tr, o3d_tr = get_transcript_ids(gene, maf_df_f, o3d_seq_df)