def _get_mh_obj(genotype_row):
ret_mh_obj = Microhaplotype()
ret_mh_obj.name = str(genotype_row['Locus'])
ret_mh_obj.number_of_alleles = int(genotype_row['Allele Count'])
ret_mh_obj.number_of_contributors = int(
genotype_row['Min Contributors'])
return ret_mh_obj
def _get_mh_obj(self, single_microhap_dict):
ret_mh_obj = Microhaplotype()
ret_mh_obj.name = single_microhap_dict['locus']
ret_mh_obj.ae = float(single_microhap_dict['avgAe'])
ret_mh_obj.prob_det_mix = float(single_microhap_dict['probOfDetMix'])
ret_mh_obj.number_of_alleles = int(
single_microhap_dict['numOfAlleles'])
ret_mh_obj.number_of_contributors = int(
single_microhap_dict['numOfCont'])
ret_mh_obj.analytical_threshold = int(
single_microhap_dict['minCoverage'])
ret_mh_obj.snps_rsid_list = '/'.join(single_microhap_dict['snps'])
ret_mh_obj.alleles = self._get_alleles(single_microhap_dict['profile'])
return ret_mh_obj
def _get_mh_obj(self, mh_single_line_dict):
""" Get an object of class Microhaplotype populated with its attributes.
:param mh_single_line_dict: A csv.DictReader dict of a single mh txt file line
:return: An object of class Microhaplotype
"""
ret_mh_obj = Microhaplotype()
ret_mh_obj.name = mh_single_line_dict['MarkerId']
ret_mh_obj.ae = float(mh_single_line_dict['AvgAe'])
ret_mh_obj.prob_det_mix = float(mh_single_line_dict['ProbOfDetMix'])
ret_mh_obj.number_of_alleles = int(mh_single_line_dict['NumOfAlleles'])
ret_mh_obj.number_of_contributors = int(
mh_single_line_dict['NumOfContributors'])
ret_mh_obj.analytical_threshold = int(
mh_single_line_dict['MinimumCoverage'])
ret_mh_obj.snps_rsid_list = mh_single_line_dict['SNPs']
ret_mh_obj.alleles = self._get_alleles(
mh_single_line_dict['AlleleCoverageDetail(-strand:+strand:avgMQ)'])
return ret_mh_obj
def _get_mh_count(self):
bam_file_obj = pysam.AlignmentFile(self.bam, 'rb')
for mh_name in self.bed_obj.bed_dict.keys():
self.mh_dict.setdefault(mh_name, Microhaplotype(name=mh_name))
mh_number_of_bases_targeted = len(self.bed_obj.bed_dict[mh_name])
for chromosome, start_position in self.bed_obj.bed_dict[mh_name]:
self.mh_dict[mh_name].process_overlapping_reads(chromosome, start_position, bam_file_obj)
reads_processed, short_reads = self.mh_dict[mh_name].get_alleles(mh_number_of_bases_targeted)
self.total_reads_count += reads_processed
self.short_reads_count += short_reads
self.mh_dict[mh_name].calculate_avg_mapping_quality()
self.mh_dict[mh_name].calculate_total_coverage()
self.mh_dict[mh_name].filter_alleles(self.filters_obj)
if self.info:
self.info_obj.add_info(self.mh_dict[mh_name])
def microhap_obj():
from microhaplotype import Microhaplotype
return Microhaplotype(name='mitotrial-001')