def get_read_positions(self):
piece_CDSs, max_gene_length = self.get_CDSs()
gene_infos = positions.get_Transcript_position_counts(self.merged_file_names['combined_extended'],
piece_CDSs,
[],
left_buffer=500,
right_buffer=500,
)
self.read_positions = {}
for name, info in gene_infos.iteritems():
five_prime_counts = info['five_prime_positions']
three_prime_counts = info['three_prime_positions']
all_positions = {'all': five_prime_counts['all'],
'three_prime_genomic': three_prime_counts[0],
'three_prime_nongenomic': three_prime_counts['all'] - three_prime_counts[0],
'sequence': info['sequence'],
}
self.read_positions[name] = all_positions
self.write_file('read_positions', self.read_positions)
joint_position_counts = {}
for transcript in piece_CDSs:
counts = positions.get_joint_position_counts_sparse(self.merged_file_names['combined_extended'],
transcript,
left_buffer=500,
right_buffer=500,
)
joint_position_counts[transcript.name] = counts
self.write_file('joint_positions', joint_position_counts)
def get_joint_position_counts(self, gene_name):
CDSs, _ = self.get_CDSs()
CDS_dict = {t.name: t for t in CDSs}
transcript = CDS_dict[gene_name]
joint_position_counts = positions.get_joint_position_counts_sparse(self.file_names['combined_extended_sorted'],
transcript,
)
return joint_position_counts, transcript