INNER CODE UNIT · Python

taxa_of_duplicate_sequences

nickjcroucher/gubbins · python/gubbins/PreProcessFasta.py:70

    def taxa_of_duplicate_sequences(self):
        taxa_to_remove = []
        for sequence_hash, taxa in sorted(self.hash_sequences().items()):
            if len(taxa) > 1:
                taxon_to_keep = taxa.pop()
                for taxon in taxa:
                    print("Sequences in " + taxon + " and " + taxon_to_keep + " are identical, removing " + taxon +
                          " from analysis")
                    taxa_to_remove.append(taxon)

        return taxa_to_remove

    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:

View source record →