Merge pull request #1155 from griffithlab/insertion_fasta

Add additional trailing amino acids for frameshift insertions when creating fasta
griffithlab · Dec 12, 2024 · 370ce3f · 370ce3f
2 parents 346b0db + bab7164
commit 370ce3f
Show file tree

Hide file tree

Showing 42 changed files with 162,168 additions and 162,081 deletions.
diff --git a/pvactools/lib/fasta_generator.py b/pvactools/lib/fasta_generator.py
@@ -246,7 +246,10 @@ def execute(self):
                 #we would need to recalculate the downstream protein sequence taking all downstream variants into account.
                 mutant_subsequence = re.sub('^%s' % left_flanking_subsequence, left_flanking_subsequence_with_proximal_variants, mutant_subsequence)
             else:
-                mutation_start_position, wildtype_subsequence = self.get_wildtype_subsequence(position, full_wildtype_sequence, wildtype_amino_acid_length, line)
+                if variant_type == 'inframe_ins':
+                    mutation_start_position, wildtype_subsequence = self.get_wildtype_subsequence(position, full_wildtype_sequence, len(mutant_amino_acid), line)
+                else:
+                    mutation_start_position, wildtype_subsequence = self.get_wildtype_subsequence(position, full_wildtype_sequence, wildtype_amino_acid_length, line)
                 mutation_end_position = mutation_start_position + wildtype_amino_acid_length
                 if wildtype_amino_acid != '-' and wildtype_amino_acid != wildtype_subsequence[mutation_start_position:mutation_end_position]:
                     if line['amino_acid_change'].split('/')[0].count('*') > 1: