INNER CODE UNIT · Python

are_sequence_names_unique

nickjcroucher/gubbins · python/gubbins/ValidateFastaAlignment.py:69

    def are_sequence_names_unique(self):
        any_modified_names = False
        with open(self.input_filename) as input_handle:
            alignment = AlignIO.read(input_handle, "fasta")
            sequence_names = []
            for record in alignment:
                # Remove disallowed characters
                if '#' in record.name or ':' in record.name:
                    record.name = process_sequence_names(record.name)
                    record.id = process_sequence_names(record.id)
                    record.description = process_sequence_names(record.description)
                    any_modified_names = True
                # Store modified names
                sequence_names.append(record.name)
        duplicate_sequence_list = [k for k,v in list(Counter(sequence_names).items()) if v>1]
        if duplicate_sequence_list != []:
            print("Duplicate sequences found after name processing:")
            for dup in duplicate_sequence_list:

View source record →