Merge pull request #440 from bbglab/dev

release v1.1.0

Author: FerriolCalvet

.gitignore

@@ -13,3 +13,5 @@ ste_notes.txt
 assets/HDP_files*
 scratch/
 scratchhhh/
+tests/test_data/all_samples.somatic.mutations.maf
+tests/test_data/all_samples_indv.depths.tsv.gz

README.md

@@ -16,8 +16,8 @@ First, prepare a samplesheet with your input data that looks as follows:
 
 ```csv
 sample,vcf,bam
-sample1,sample1.high.filtered.vcf,sample1.sorted.bam
-sample2,sample2.high.filtered.vcf,sample2.sorted.bam
+sample1,sample1.filtered.vcf,sample1.sorted.bam
+sample2,sample2.filtered.vcf,sample2.sorted.bam
 ```
 
 Each row represents a single sample with a single-sample VCF containing the mutations called in that sample and the BAM file that was used for getting those variant calls. The mutations will be obtained from the VCF and the BAM file will be used for computing the sequencing depth at each position and using this for the downstream analysis.
@@ -28,8 +28,6 @@ Each row represents a single sample with a single-sample VCF containing the muta
 
 After making sure that these files are ready, you can now run the pipeline using:
 
-<!-- TODO nf-core: update the following command to include all required parameters for a minimal example -->
-
 ```bash
 git clone https://github.com/bbglab/deepCSA.git
 cd deepCSA
@@ -74,4 +72,16 @@ We are working to provide the biggest possible detail on the [usage](docs/usage.
 
 ## Publications
 
-> [Sex and smoking bias in the selection of somatic mutations in human bladder](https://www.nature.com/articles/s41586-025-09521-x)
+> **Sex and smoking bias in the selection of somatic mutations in human bladder**
+>
+> Ferriol Calvet*, Raquel Blanco Martinez-Illescas*, Ferran Muiños, Maria Tretiakova, Elena S. Latorre-Esteves, Jeanne Fredrickson, Maria Andrianova, Stefano Pellegrini, Axel Rosendahl Huber, Joan Enric Ramis-Zaldivar, Shuyi Charlotte An, Elana Thieme, Brendan F. Kohrn, Miguel L. Grau, Abel Gonzalez-Perez, Nuria Lopez-Bigas & Rosa Ana Risques
+>
+>_Nature_ (2025) doi:[10.1038/s41586-025-09521-x](https://doi.org/10.1038/s41586-025-09521-x)
+>
+> *these authors contributed equally and the order was decided randomly
+
+> **DeepClone, an end-to-end protocol to study somatic mutagenesis and selection at high resolution**
+>
+> Ferriol Calvet, Morena Pinheiro-Santin, Erika Lopez, Raquel Blanco Martinez-Illescas, Núria Samper, Miguel L. Grau, Ferran Muiños, Rocío Chamorro González, Maria Andrianova, Federica Brando, Stefano Pellegrini, Marta Huertas, Elisabet Figuerola-Bou, Coohleen Coombes, Brendan F. Kohrn, Jeanne Fredrickson, Rosa Ana Risques, Nuria Lopez-Bigas, Abel Gonzalez-Perez
+>
+> _protocols.io_ (2026) doi:[10.17504/protocols.io.dm6gp1jodgzp/v2](https://dx.doi.org/10.17504/protocols.io.dm6gp1jodgzp/v2)

assets/regressions/configs/mutdensity.yml

@@ -0,0 +1,31 @@
+general:
+  correct_pvals: true
+  elements: null
+  handle_na: ignore
+  model: linear
+  multi: true
+  output_dir: ./
+  predictor_random_effect: null
+  predictors: null
+  predictors_file: null
+  predictors_intercept_0: null
+  predictors_multi_force: null
+  sample_column: null
+  samples: null
+  significance_threshold: 0.2
+metrics:
+  metric_1:
+    adjust: false
+    elements_total_by: included
+    file: all_mutdensities.tsv
+    metric_name: mutdensity
+    muttype:
+    - snv
+    - snv_indel
+    region:
+    - protein_affecting
+    - non_protein_affecting
+    samples_total_by: included
+plot:
+  predictors_colors: null
+  predictors_names: null

assets/regressions/configs/omega.yml

@@ -0,0 +1,31 @@
+general:
+  correct_pvals: true
+  elements: null
+  handle_na: ignore
+  model: linear
+  multi: true
+  output_dir: ./
+  predictor_random_effect: null
+  predictors: null
+  predictors_file: null
+  predictors_intercept_0: null
+  predictors_multi_force: null
+  sample_column: null
+  samples: null
+  significance_threshold: 0.2
+metrics:
+  metric_1:
+    elements_total_by: included
+    file: all_omegas.tsv
+    global_loc: false
+    impact:
+    - missense
+    - truncating
+    - nonsynonymous_splice
+    metric_name: omega
+    multi: false
+    samples_total_by: included
+    significance_threshold: 1
+plot:
+  predictors_colors: null
+  predictors_names: null

assets/regressions/configs/omegaglobal.yml

@@ -0,0 +1,31 @@
+general:
+  correct_pvals: true
+  elements: null
+  handle_na: ignore
+  model: linear
+  multi: true
+  output_dir: ./
+  predictor_random_effect: null
+  predictors: null
+  predictors_file: null
+  predictors_intercept_0: null
+  predictors_multi_force: null
+  sample_column: null
+  samples: null
+  significance_threshold: 0.2
+metrics:
+  metric_1:
+    elements_total_by: included
+    file: all_omegas_global_loc.tsv
+    global_loc: true
+    impact:
+    - missense
+    - truncating
+    - nonsynonymous_splice
+    metric_name: omega
+    multi: false
+    samples_total_by: included
+    significance_threshold: 1
+plot:
+  predictors_colors: null
+  predictors_names: null

assets/schema_input.json

@@ -25,14 +25,14 @@
             "pileup_bam": {
                 "type": "string",
                 "pattern": "^\\S+\\.bam$",
-                "errorMessage": "pileup BAM file for sample must be provided, cannot contain spaces and must have extension '.bam'"
+                "errorMessage": "BAM file for computing a pileup per sample, it must have extension '.bam'"
             },
             "pileup_ind": {
                 "type": "string",
                 "pattern": "^\\S+\\.bam.csi$",
-                "errorMessage": "BAM index pilup file for sample must be provided, cannot contain spaces and must have extension '.bam.csi'"
+                "errorMessage": "BAM index file for computing a pileup per sample, it must have extension '.bam.csi'"
             }
         },
-        "required": ["sample", "vcf", "bam"]
+        "required": ["sample", "vcf"]
     }
 }

assets/useful_scripts/deepcsa_maf2samplevcfs.py

@@ -43,6 +43,8 @@ def build_vcf_like_dataframe(mutations_dataframe, samplee):
     Build a VCF-like dataframe from the mutations dataframe.
     input needs to have:
         ['CHROM', 'POS', 'REF', 'ALT', 'DEPTH', 'ALT_DEPTH']
+        can optionally have:
+            ['FILTER', 'INFO'] and ['ALT_DEPTH_AM', 'DEPTH_AM']
     output needs to have:
         ['CHROM', 'POS', 'REF', 'ALT', 'FILTER', 'INFO', 'FORMAT', 'SAMPLE']
     """
@@ -58,10 +60,16 @@ def build_vcf_like_dataframe(mutations_dataframe, samplee):
         print(f"WARNING: INFO column is missing from the mutations dataframe. Setting it to 'SAMPLE={samplee};'")
         mutations_dataframe["INFO"] = f"SAMPLE={samplee};"
 
+    if 'ALT_DEPTH_AM' not in mutations_dataframe.columns or 'DEPTH_AM' not in mutations_dataframe.columns:
+        print("WARNING: Optional columns: ALT_DEPTH_AM and DEPTH_AM are missing from the mutations dataframe.")
+        print("         These are being initialized as its duplex values.")
+        mutations_dataframe['ALT_DEPTH_AM'] = mutations_dataframe['ALT_DEPTH']
+        mutations_dataframe['DEPTH_AM'] = mutations_dataframe['DEPTH']
+
     # Create a new dataframe with the required columns
-    vcf_like_df = mutations_dataframe[['CHROM', 'POS', 'REF', 'ALT', 'FILTER', 'INFO', 'DEPTH', 'ALT_DEPTH']].copy()
+    vcf_like_df = mutations_dataframe[['CHROM', 'POS', 'REF', 'ALT', 'FILTER', 'INFO', 'DEPTH', 'ALT_DEPTH', 'ALT_DEPTH_AM', 'DEPTH_AM']].copy()    
     vcf_like_df["FORMAT"] = "GT:DP:VD:AD:AF:RD:ALD:CDP:CAD:NDP:CDPAM:CADAM:NDPAM"
-    vcf_like_df["SAMPLE"] = vcf_like_df[['DEPTH', 'ALT_DEPTH']].apply(
+    vcf_like_df["SAMPLE"] = vcf_like_df[['DEPTH', 'ALT_DEPTH', 'ALT_DEPTH_AM', 'DEPTH_AM']].apply(
         lambda x: "{GT}:{DP}:{VD}:{AD}:{AF}:{RD}:{ALD}:{CDP}:{CAD}:{NDP}:{CDPAM}:{CADAM}:{NDPAM}".format(
             GT="0/1",
             DP=x['DEPTH'],
@@ -73,8 +81,8 @@ def build_vcf_like_dataframe(mutations_dataframe, samplee):
             CDP=x['DEPTH'],
             CAD=f"{x['DEPTH'] - x['ALT_DEPTH']},{x['ALT_DEPTH']}",
             NDP="0",
-            CDPAM=x['DEPTH'],
-            CADAM=f"{x['DEPTH'] - x['ALT_DEPTH']},{x['ALT_DEPTH']}",
+            CDPAM=x['DEPTH_AM'],
+            CADAM=f"{x['DEPTH_AM'] - x['ALT_DEPTH_AM']},{x['ALT_DEPTH_AM']}",
             NDPAM="0" 
         ),
         axis=1
@@ -86,7 +94,7 @@ def remove_deepcsa_filters(old_filt, filters_to_removee):
     """
     Remove deepCSA filters from the FILTER field of the VCF file.
     """    
-    filter_result = sorted([ x for x in old_filt.split(";") if x not in filters_to_removee ])
+    filter_result = sorted([ x for x in str(old_filt).split(";") if x not in filters_to_removee ])
     return ";".join(filter_result) if filter_result != [] else "PASS"