def filter_records(self, records):
for record in records:
a = record.annotations
clip_right = a['clip_flow_right']
flows = a['flow_values']
flows = [float(i) / 100.0 for i in flows]
trim_flows = flows[:clip_right]
trim_flows = self.filter_record(trim_flows)
trimmed_reading = sff.flow_to_seq(trim_flows)
m = self.primer_re.match(trimmed_reading)
if (self.min_flows is None
or len(trim_flows) >= self.min_flows) and m:
sequence = m.group(1)
# Truncate the flow result to a maximum length
# Note that the FASTA result is unchanged
flow_result = trim_flows[:self.max_flows]
# AmpliconNoise reports flowgram lengths to the nearest power of 4
trim_len = int(math.ceil(len(flow_result) / 4.0)) * 4
self.passed += 1
yield (record.id, sequence, trim_len, flows[:self.max_flows])
else:
self.failed += 1
def filter_records(self, records):
for record in records:
a = record.annotations
clip_right = a['clip_flow_right']
flows = a['flow_values']
flows = [float(i) / 100.0 for i in flows]
trim_flows = flows[:clip_right]
trim_flows = self.filter_record(trim_flows)
trimmed_reading = sff.flow_to_seq(trim_flows)
m = self.primer_re.match(trimmed_reading)
if (self.min_flows is None or len(trim_flows) >= self.min_flows) and m:
sequence = m.group(1)
# Truncate the flow result to a maximum length
# Note that the FASTA result is unchanged
flow_result = trim_flows[:self.max_flows]
# AmpliconNoise reports flowgram lengths to the nearest power of 4
trim_len = int(math.ceil(len(flow_result) / 4.0)) * 4
self.passed += 1
yield (record.id, sequence, trim_len, flows[:self.max_flows])
else:
self.failed += 1
def __iter__(self):
while True:
header = next(self._fp)[1:]
split_line = next(self._fp).split()
flow_length = int(split_line[0])
flows = split_line[1:]
flows = map(float, flows)
bases = sff.flow_to_seq(flows)
sequence = Seq(bases, generic_dna)
record = SeqRecord(sequence, id=header)
# Add flows and clip as annotations
record.annotations["flow_values"] = [int(i * 100) for i in flows]
record.annotations["clip_flow_right"] = flow_length
yield record
def __iter__(self):
while True:
header = next(self._fp)[1:]
split_line = next(self._fp).split()
flow_length = int(split_line[0])
flows = split_line[1:]
flows = map(float, flows)
bases = sff.flow_to_seq(flows)
sequence = Seq(bases, generic_dna)
record = SeqRecord(sequence, id=header)
# Add flows and clip as annotations
record.annotations['flow_values'] = [int(i * 100) for i in flows]
record.annotations['clip_flow_right'] = flow_length
yield record
def setUp(self):
flows = (101, 1, 99, 2, 0, 103, 2, 100, 0, 111, 110, 1, 3, 108, 0, 2,
107, 0, 0, 103, 101, 1, 13, 102, 0, 8, 204, 12, 0, 105, 1, 290,
2, 92, 7, 98, 9, 6, 98, 4, 101, 10, 0, 199, 5, 299, 3, 101, 4,
99)
bases = sff.flow_to_seq(flows)
sequence = Seq(bases, generic_dna)
self.record = SeqRecord(sequence, id='FTWCYXX01BTPDQ')
self.record.annotations['clip_qual_right'] = 14
self.record.annotations['clip_qual_left'] = 4
self.record.annotations['flow_values'] = flows
self.record.annotations['flow_index'] = (1, 2, 3, 2, 2, 1, 3, 3, 3, 1,
3, 3, 0, 3, 2, 0, 0, 2, 2, 3, 2, 3, 0, 2, 0, 0, 2, 2, 3, 0, 2,
1, 3, 3, 0, 3, 0, 1, 0, 3, 2, 0, 2, 3, 0, 3, 0, 2, 0, 0)
def setUp(self):
flows = (101, 1, 99, 2, 0, 103, 2, 100, 0, 111, 110, 1, 3, 108, 0, 2,
107, 0, 0, 103, 101, 1, 13, 102, 0, 8, 204, 12, 0, 105, 1,
290, 2, 92, 7, 98, 9, 6, 98, 4, 101, 10, 0, 199, 5, 299, 3,
101, 4, 99)
bases = sff.flow_to_seq(flows)
sequence = Seq(bases, generic_dna)
self.record = SeqRecord(sequence, id='FTWCYXX01BTPDQ')
self.record.annotations['clip_qual_right'] = 14
self.record.annotations['clip_qual_left'] = 4
self.record.annotations['flow_values'] = flows
self.record.annotations['flow_index'] = (1, 2, 3, 2, 2, 1, 3, 3, 3, 1,
3, 3, 0, 3, 2, 0, 0, 2, 2, 3,
2, 3, 0, 2, 0, 0, 2, 2, 3, 0,
2, 1, 3, 3, 0, 3, 0, 1, 0, 3,
2, 0, 2, 3, 0, 3, 0, 2, 0, 0)
def test_flow_to_seq_int(self):
actual = sff.flow_to_seq(self.test_flow_int)
self.assertEqual(self.test_expected, actual)
def test_flow_to_seq_int(self):
actual = sff.flow_to_seq(self.test_flow_int)
self.assertEqual(self.test_expected, actual)
