Merge pull request #227 from jonasscheid/fix-bug-if-no-transcript-ava…

…ilable Prevent crash if no transcript is found (in splitted vcf)
nf-core · Feb 6, 2024 · a728456 · a728456
2 parents a0e248d + 6177dc3
commit a728456
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 7 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - [#228](https://github.com/nf-core/epitopeprediction/pull/228) - Update to nf-core template `2.12`
 - [#228](https://github.com/nf-core/epitopeprediction/pull/228) - Update to nf-core template `2.11`
+- [#227](https://github.com/nf-core/epitopeprediction/pull/227) Prevent crash if no transcript is found (in splitted vcf)
 - [#220](https://github.com/nf-core/epitopeprediction/pull/220) - Switch to nf-validation to parse samplesheet
 - [#213](https://github.com/nf-core/epitopeprediction/pull/203) - Update to nf-core template `2.10`
 - [#206](https://github.com/nf-core/epitopeprediction/issues/206) - Update the row checker class.

diff --git a/bin/epaa.py b/bin/epaa.py
@@ -280,7 +280,6 @@ def read_vcf(filename, pass_only=True):
                                 split_coding_c[0] if split_coding_c[0] else split_annotation[vep_fields["feature"]]
                             )
                             transcript_id = transcript_id.split(".")[0]
-
                             tpos = int(cds_pos.split("/")[0].split("-")[0]) - 1
                             if split_annotation[vep_fields["protein_position"]]:
                                 ppos = (
@@ -712,7 +711,6 @@ def make_predictions_from_variants(
 
     # list to hold dataframes for all predictions
     pred_dataframes = []
-
     prots = [
         p
         for p in generator.generate_proteins_from_transcripts(
@@ -1054,14 +1052,10 @@ def __main__():
         logger.info("Running epaa for variants...")
         if args.somatic_mutations.endswith(".vcf"):
             variant_list, transcripts, metadata = read_vcf(args.somatic_mutations)
+            transcripts = list(set(transcripts))
         else:
             raise ValueError("File is not in VCF format. Please provide a VCF file.")
 
-        transcripts = list(set(transcripts))
-
-        # use function provided by epytope to retrieve protein IDs (different systems) for transcript IDs
-        transcriptProteinTable = ma.get_protein_ids_from_transcripts(transcripts, type=ID_SYSTEM_USED)
-
     # get the alleles
     alleles = [Allele(a) for a in args.alleles.split(";")]
 
@@ -1123,7 +1117,15 @@ def __main__():
         pred_dataframes, statistics = make_predictions_from_peptides(
             peptides, methods, thresholds, args.use_affinity_thresholds, alleles, up_db, args.identifier, metadata
         )
+    elif len(transcripts) == 0:
+        logger.warning(f"No transcripts found for variants in {args.somatic_mutations}")
+        pred_dataframes = []
+        statistics = {}
+        all_peptides_filtered = []
+        proteins = []
     else:
+        # use function provided by epytope to retrieve protein IDs (different systems) for transcript IDs
+        transcriptProteinTable = ma.get_protein_ids_from_transcripts(transcripts, type=EIdentifierTypes.ENSEMBL)
         pred_dataframes, statistics, all_peptides_filtered, proteins = make_predictions_from_variants(
             variant_list,
             methods,