INNER CODE UNIT · Python

calculate_sequences_missing_data_percentage

nickjcroucher/gubbins · python/gubbins/PreProcessFasta.py:34

    def calculate_sequences_missing_data_percentage(self):
        sequences_to_missing_data = {}
        with open(self.input_filename) as input_handle:
            alignments = AlignIO.parse(input_handle, "fasta")
            for alignment in alignments:
                for record in alignment:
                    number_of_gaps = 0
                    number_of_gaps += record.seq.count('n')
                    number_of_gaps += record.seq.count('N')
                    number_of_gaps += record.seq.count('-')
                    sequence_length = len(record.seq)

                    if sequence_length == 0:
                        sequences_to_missing_data[record.id] = 100
                        if self.verbose:
                            print("Sample " + str(record.id) + " has no sequence ")
                    else:
                        per_missing_data = number_of_gaps*100/sequence_length

View source record →