diff --git a/downloads-generation/data_mass_spec_benchmark/run_mhcflurry.py b/downloads-generation/data_mass_spec_benchmark/run_mhcflurry.py index 8eeb45f208721a1a55267f8279a38b0f3e203e4f..435a6046ff96a115974f0065d8860d2464c04e86 100644 --- a/downloads-generation/data_mass_spec_benchmark/run_mhcflurry.py +++ b/downloads-generation/data_mass_spec_benchmark/run_mhcflurry.py @@ -108,7 +108,7 @@ def run(argv=sys.argv[1:]): peptides = pandas.read_csv(args.input_peptides).peptide.drop_duplicates() print("Filtering to valid peptides. Starting at: ", len(peptides)) - peptides = peptides[peptides.str.match("[ACDEFGHIKLMNPQRSTVWY]+")] + peptides = peptides[peptides.str.match("^[ACDEFGHIKLMNPQRSTVWY]+$")] print("Filtered to: ", len(peptides)) peptides = peptides.unique() num_peptides = len(peptides)