INNER CODE UNIT · Python

remove_duplicate_sequences_and_sequences_missing_too_much_data

nickjcroucher/gubbins · python/gubbins/PreProcessFasta.py:82

    def remove_duplicate_sequences_and_sequences_missing_too_much_data(self, output_filename,
                                                                       remove_identical_sequences=None):

        if not remove_identical_sequences:
            taxa_to_remove = self.taxa_missing_too_much_data()
        else:
            taxa_to_remove = self.taxa_of_duplicate_sequences() + self.taxa_missing_too_much_data()

        with open(self.input_filename) as input_handle:
            alignments = AlignIO.parse(input_handle, "fasta")
            output_alignments = []
            number_of_included_alignments = 0
            for alignment in alignments:
                for record in alignment:
                    if record.id not in taxa_to_remove:
                        output_alignments.append(record)
                        number_of_included_alignments += 1
            if number_of_included_alignments <= 1:

View source record →