def __call__(self, read1, read2):
len1 = len(read1.sequence)
len2 = len(read2.sequence)
min_overlap = self.min_overlap
if min_overlap <= 1:
min_overlap = max(2, round(self.min_overlap * min(len1, len2)))
if len1 < min_overlap or len2 < min_overlap:
return (read1, read2)
insert_matched = read1.insert_overlap and read2.insert_overlap
if insert_matched:
# If we've already determined that there is an insert overlap
# with a 3' overhang, we can constrain our alignment
aflags = START_WITHIN_SEQ1 | STOP_WITHIN_SEQ2
else:
aflags = SEMIGLOBAL
# align read1 to read2 reverse-complement to be compatible with
# InsertAligner
read2_rc = reverse_complement(read2.sequence)
aligner = Aligner(read2_rc, self.error_rate, aflags)
alignment = aligner.locate(read1.sequence)
if alignment:
r2_start, r2_stop, r1_start, r1_stop, matches, errors = alignment
if matches >= min_overlap:
# Only correct errors if we haven't already done correction in
# the InsertAligner
if (self.mismatch_action and errors > 0 and not insert_matched
and read1.corrected == 0 and read2.corrected == 0):
self.correct_errors(read1, read2, alignment)
if r2_start == 0 and r2_stop == len2:
# r2 is fully contained in r1
pass
elif r1_start == 0 and r1_stop == len1:
# r1 is fully contained in r2
read1.sequence = read2_rc
read1.qualities = "".join(reversed(read2.qualities))
elif r1_start > 0:
read1.sequence += read2_rc[r2_stop:]
if read1.qualities and read2.qualities:
read1.qualities += "".join(reversed(
read2.qualities))[r2_stop:]
elif r2_start > 0:
read1.sequence = read2_rc + read1.sequence[r1_stop:]
if read1.qualities and read2.qualities:
read1.qualities = ("".join(reversed(read2.qualities)) +
read1.qualities[r1_stop:])
else:
raise AtroposError(
"Invalid alignment while trying to merge read "
"{}: {}".format(read1.name,
",".join(str(i) for i in alignment)))
read1.merged = True
read2 = None
return (read1, read2)
def align(seq1, seq2, min_overlap_frac=0.9):
aligner = Aligner(seq1, 0.0, SEMIGLOBAL, False, False)
aligner.min_overlap = math.ceil(
min(len(seq1), len(seq2)) * min_overlap_frac)
aligner.indel_cost = 100000
match = aligner.locate(seq2)
if match:
return seq1[match[0]:match[1]]
else:
return None
def align(seq1, seq2, min_overlap_frac=0.9):
"""Align two sequences.
Args:
seq1: The second sequence to align.
seq2: The first sequence to align.
min_overlap_frac: Minimum fraction of overlapping bases required for a
match.
Returns:
The matching portion of the sequence.
"""
aligner = Aligner(seq1, 0.0, SEMIGLOBAL, False, False)
aligner.min_overlap = math.ceil(
min(len(seq1), len(seq2)) * min_overlap_frac)
aligner.indel_cost = 100000
match = aligner.locate(seq2)
if match:
return seq1[match[0]:match[1]]
else:
return None
def test_100_percent_error_rate(self):
reference = 'GCTTAGACATATC'
aligner = Aligner(reference, 1.0, flags=BACK)
aligner.locate('CAA')
def test(self):
reference = 'CTCCAGCTTAGACATATC'
aligner = Aligner(reference, 0.1, flags=BACK)
aligner.locate('CC')
