report.py 文件源码

def mark_dupes_group_cb(self, gene_id, umis, dupe_type):
        total_counts = sum(umis.values())
        total_umis = len(umis)
        if any([count > 1 for count in umis.itervalues()]):
            umi_hamming_distance = 0
        else:
            umi_hamming_distance = cr_utils.get_kmers_hamming_distance(umis.keys())

        for reference in [cr_utils.get_genome_from_str(gene_id, self.genomes), cr_constants.MULTI_REFS_PREFIX]:
            if total_counts > 0:
                reads_per_dupe_group_histogram = self._get_metric_attr(
                    'reads_per_dupe_group_histogram', reference, dupe_type)
                reads_per_dupe_group_histogram.add(total_counts)

            if total_umis > 0:
                umis_per_dupe_group_histogram = self._get_metric_attr(
                    'umis_per_dupe_group_histogram', reference, dupe_type)
                umis_per_dupe_group_histogram.add(total_umis)

            reads_per_molecule_histogram = self._get_metric_attr(
                'reads_per_molecule_histogram', reference, dupe_type)
            for count in umis.itervalues():
                reads_per_molecule_histogram.add(count)

            if umi_hamming_distance is not None:
                umi_hamming_distance_per_dupe_group_histogram = self._get_metric_attr(
                    'umi_hamming_distance_per_dupe_group_histogram', reference, dupe_type)
                umi_hamming_distance_per_dupe_group_histogram.add(umi_hamming_distance)