def get_inferred_sequences(pairs, genome_dict, add_softclipped_bases=False):
inferred_sequences = []
for read1, read2 in pairs:
if read1.query_name.count('_') == 2:
context_width = int(read1.query_name.split('_')[-2])
name = read1.reference_name + ':' + str(
read1.reference_start +
context_width) + '-' + str(read2.reference_end - context_width)
inferred_sequence = genome_dict[read1.reference_name][
read1.reference_start:read2.reference_end]
if add_softclipped_bases:
inferred_sequence = sctools.left_softclipped_sequence_strict(
read1
) + inferred_sequence + sctools.right_softclipped_sequence_strict(
read2)
inferred_sequence = inferred_sequence[context_width:-context_width]
if read1.query_name.split('_')[-1] == '2':
inferred_sequence = misc.revcomp(inferred_sequence)
contig_edge = False
if sctools.is_left_softclipped_strict(read1) and \
sctools.left_softclipped_position(read1) < 0:
contig_edge = True
elif sctools.is_right_softclipped_strict(read2) and \
sctools.right_softclipped_position(read2) >= len(genome_dict[read2.reference_name]):
contig_edge = True
else:
name = read1.reference_name + ':' + str(
read1.reference_start) + '-' + str(read2.reference_end)
inferred_sequence = genome_dict[read1.reference_name][
read1.reference_start:read2.reference_end]
if add_softclipped_bases:
inferred_sequence = sctools.left_softclipped_sequence_strict(
read1
) + inferred_sequence + sctools.right_softclipped_sequence_strict(
read2)
if read1.query_name.split('_')[-1] == '2':
inferred_sequence = misc.revcomp(inferred_sequence)
contig_edge = False
if sctools.is_left_softclipped_strict(read1) and \
sctools.left_softclipped_position(read1) < 0:
contig_edge = True
elif sctools.is_right_softclipped_strict(read2) and \
sctools.right_softclipped_position(read2) >= len(genome_dict[read2.reference_name]):
contig_edge = True
inferred_sequences.append(
(name, len(inferred_sequence), contig_edge, inferred_sequence))
return inferred_sequences
def get_inferred_sequence(self, forward_read, reverse_read, is_reverse):
contig = forward_read.reference_name
start = forward_read.reference_start
end = reverse_read.reference_end
inferred_sequence = ''.join(self.genome_dict[contig][start:end])
inferred_sequence = sctools.left_softclipped_sequence_strict(forward_read) + \
inferred_sequence + \
sctools.right_softclipped_sequence_strict(reverse_read)
inferred_sequence = inferred_sequence[self.context_width:-self.context_width]
if is_reverse:
inferred_sequence = misc.revcomp(inferred_sequence)
contig_edge = False
if sctools.is_left_softclipped_strict(forward_read) and \
sctools.left_softclipped_position(forward_read) < 0:
contig_edge = True
elif sctools.is_right_softclipped_strict(reverse_read) and \
sctools.right_softclipped_position(reverse_read) >= len(self.genome_dict[contig]):
contig_edge = True
return inferred_sequence, contig_edge
def get_inferred_sequence(self, forward_read, reverse_read, is_reverse):
contig, start, end = forward_read.reference_name, forward_read.reference_start, reverse_read.reference_end
inferred_sequence = ''.join(self.genome_dict[contig][start:end])
inferred_sequence = sctools.left_softclipped_sequence_strict(forward_read) + \
inferred_sequence + \
sctools.right_softclipped_sequence_strict(reverse_read)
if is_reverse:
inferred_sequence = misc.revcomp(inferred_sequence)
return inferred_sequence
def get_inferred_sequences(pairs, genome_dict, add_softclipped_bases=False):
inferred_sequences = []
for read1, read2 in pairs:
name = read1.reference_name + ':' + str(
read1.reference_start) + '-' + str(read2.reference_end)
inferred_sequence = genome_dict[
read1.reference_name][read1.reference_start:read2.reference_end]
if add_softclipped_bases:
inferred_sequence = sctools.left_softclipped_sequence_strict(
read1
) + inferred_sequence + sctools.right_softclipped_sequence_strict(
read2)
if read1.is_read2:
inferred_sequence = misc.revcomp(inferred_sequence)
inferred_sequences.append(
(name, len(inferred_sequence), inferred_sequence))
return inferred_sequences