def check_barcode(fastadict, barcodedict, barcodelength, maxdistance):
"check for barcode and update sample data"
samplematch = None
barcodedata = None
spacermismatch = False
barcode_distance = 0
halfbarcode = int(barcodelength / 2)
fseq = fastadict['forward_sequence']
rseq = fastadict['reverse_sequence']
barcode = fseq[:halfbarcode] + rseq[:halfbarcode]
#check for perfect match first:
for sample, samplebarcodedict in barcodedict.items():
if samplebarcodedict['barcode'] == barcode:
samplematch = sample
barcodedata = samplebarcodedict
#if not choose closest
if not samplematch:
for sample, samplebarcodedict in barcodedict.items():
hdist = hamdist(samplebarcodedict['barcode'], barcode)
if hdist <= maxdistance:
barcode_distance = hdist
samplematch = sample
barcodedata = samplebarcodedict
# trim the sequences after checking the spacer sequence between the barcode and the primer
fseq = fseq[halfbarcode:]
rseq = rseq[halfbarcode:]
if barcodedata is not None:
forward_spacer = barcodedata['forward_spacer']
reverse_spacer = barcodedata['reverse_spacer']
if fseq.startswith(forward_spacer):
fseq = fseq[len(forward_spacer):]
else:
fseq = fseq[len(forward_spacer):]
spacermismatch = True
if rseq.startswith(reverse_spacer):
rseq = rseq[len(reverse_spacer):]
else:
rseq = rseq[len(reverse_spacer):]
spacermismatch = True
# return updated values
return thread_first(fastadict, (assoc, "sample", samplematch),
(assoc, "spacermismatch", spacermismatch),
(assoc, "barcode", barcode),
(assoc, "barcode_distance", barcode_distance),
(assoc, "forward_sequence", fseq),
(assoc, "reverse_sequence", rseq))
def truncate_by_size(fastadict, trimsize_forward, trimsize_reverse):
"subset sequence and indicate if short"
fseq = fastadict['forward_sequence']
rseq = fastadict['reverse_sequence']
tooshort = False
if len(fseq) < trimsize_forward:
tooshort = True
if len(rseq) < trimsize_reverse:
tooshort = True
return thread_first(fastadict, (assoc, "tooshort", tooshort),
(assoc, "forward_sequence", fseq[:trimsize_forward]),
(assoc, "reverse_sequence", rseq[:trimsize_reverse]))
def from_yaml(cls, yaml_f):
with open(yaml_f) as fh:
y = yaml.load(fh)
if y['surveys']:
y['surveys']['meta'] = pd.DataFrame(
y['surveys']['meta']['rows'],
columns=y['surveys']['meta']['cols']
)
logger.info('loading cfg')
cfg = thread_first(
y,
(assoc, 'facet_levels', None if 'facet_levels' not in y else y['facet_levels']),
(assoc, 'questions', None if 'questions' not in y else y['questions']),
(assoc, 'national', None if not y['national'] else ColumnFilter(**y['national'])),
(assoc, 'socrata', None if not y['socrata'] else SocrataConfig(**y['socrata'])),
(assoc, 'surveys', None if not y['surveys'] else SurveyConfig(**y['surveys']))
)
return cls(**cfg)
def test_thread_first():
assert thread_first(2) == 2
assert thread_first(2, inc) == 3
assert thread_first(2, inc, inc) == 4
assert thread_first(2, double, inc) == 5
assert thread_first(2, (add, 5), double) == 14
def test_thread_first():
assert thread_first(2) == 2
assert thread_first(2, inc) == 3
assert thread_first(2, inc, inc) == 4
assert thread_first(2, double, inc) == 5
assert thread_first(2, (add, 5), double) == 14