def sites_outside_snp(target_seq, snp_pos, allele_pos_end):
sites_outside = []
pe_len = len(pe.clean_recognition_sequence)
pe_seq = expand_sequence(pe.clean_recognition_sequence.lower())
# seq_before_snp = snp.ex_wt_sequence[:snp.snp_pos - pe_len]
# seq_after_snp = snp.ex_wt_sequence[snp.snp_pos + snp.wt_allele_len:]
for i in range(0, len(target_seq) - pe_len):
try:
if i in range(snp_pos - pe_len, allele_pos_end):
raise fexceps.DigestError
for ii in range(0, pe_len):
if not can_recognize(target_seq[i+ii], pe_seq[ii]):
raise fexceps.DigestError
sites_outside.append(i)
except fexceps.DigestError:
pass
if not pe.clean_recognition_sequence == \
reverse_complement(pe.clean_recognition_sequence):
pe_seq_rc = expand_sequence(reverse_complement(pe.clean_recognition_sequence.lower()))
for i in range(0, len(target_seq) - pe_len):
try:
if i in range(snp_pos - pe_len, allele_pos_end):
raise fexceps.DigestError
for ii in range(0, pe_len):
if not can_recognize(target_seq[i+ii], pe_seq_rc[ii]):
raise fexceps.DigestError
sites_outside.append(i)
except fexceps.DigestError:
pass
return sites_outside
def pe_can_determine_snp(pe:PrototypeEnzyme,
snp:Snp,
max_num_of_mismatches):
pe_len = len(pe.clean_recognition_sequence)
pe_seq = expand_sequence(pe.clean_recognition_sequence.lower())
wt_sites = gen_mask(pe_len,
pe_seq,
snp.ex_wt_sequence,
snp.snp_pos,
snp.wt_pos_end,
snp.wt_allele_len,
)
mut_sites = gen_mask(pe_len,
pe_seq,
snp.ex_mut_sequence,
snp.snp_pos,
snp.mut_pos_end,
snp.mut_allele_len,
)
if not pe.clean_recognition_sequence == \
reverse_complement(pe.clean_recognition_sequence):
pe_seq_rc = expand_sequence(reverse_complement(pe.clean_recognition_sequence.lower()))
wt_sites = wt_sites + gen_mask(pe_len,
pe_seq_rc,
snp.ex_wt_sequence,
snp.snp_pos,
snp.wt_pos_end,
snp.wt_allele_len,
)
mut_sites = mut_sites + gen_mask(pe_len,
pe_seq_rc,
snp.ex_mut_sequence,
snp.snp_pos,
snp.mut_pos_end,
snp.mut_allele_len,
)
wt_filtered = []
for wt_site in wt_sites:
try:
for mut_site in mut_sites:
wt_site = test_intercept(wt_site, mut_site)
wt_filtered.append(wt_site)
except fexceps.SitesCollisionError:
pass
mut_filtered = []
for mut_site in mut_sites:
try:
for wt_site in wt_sites:
mut_site = test_intercept(mut_site, wt_site)
mut_filtered.append(mut_site)
except fexceps.SitesCollisionError:
pass
return (wt_filtered, mut_filtered)
def test_init_from_IUPAC(self):
"""
Snp("aaaaaaaaaaaaaaaaaaaaaaYaaaaaaaaaaaaaaaaaaaaaaa" ok
"""
snp = Snp("aaaaaaaaaaaaaaaaaaaaaaYaaaaaaaaaaaaaaaaaaaaaaa")
self.assertEqual(snp.snp_pos, 23)
self.assertEqual(snp.wt_allele, 'c')
self.assertEqual(snp.ex_wt_sequence,
expand_sequence('aaaaaaaaaaaaaaaaaaaaaacaaaaaaaaaaaaaaaaaaaaaaa'))
self.assertEqual(snp.mut_allele, 't')
self.assertEqual(snp.ex_mut_sequence,
expand_sequence('aaaaaaaaaaaaaaaaaaaaaataaaaaaaaaaaaaaaaaaaaaaa'))
def __init__(self, sequence: str, name=None):
def from_IUPAC(sequence: str):
snp_positions = []
for char in "rymksw":
if sequence.count(char) == 1:
position = sequence.find(char)
snp_positions.append((char, position, tuple(ambiguity_dict[char])))# IUPACdict[char]))
if len(snp_positions) == 1:
return snp_positions[0]
return None
def from_wt_slash_mut(sequence: str):
snps = re.findall('\[[atgc]*/[atgc]*]', sequence)
if len(snps) == 1:
return snps[0], sequence.find(snps[0]), \
tuple(snps[0]
.replace('[','')
.replace(']','')
.split('/'))
return None
self.name = name if name is not None else str(uuid.uuid1())
sequence = re.sub('[^{}]'.format('atgcrymkswbdhvnATGCRYMKSWBDHVN\[\]\/'),
'',
sequence.lower())
info_from_seq = from_wt_slash_mut(sequence)
if info_from_seq is None:
info_from_seq = from_IUPAC(sequence)
if info_from_seq is not None:
self.original_snp_sign, self.snp_pos, \
(self.wt_allele, self.mut_allele) = info_from_seq
self.snp_pos += 1 # from 0 based to real positions
self.wt_allele_len = len(self.wt_allele)
self.wt_pos_end = self.snp_pos + self.wt_allele_len - 1
self.mut_allele_len = len(self.mut_allele)
self.mut_pos_end = self.snp_pos + self.mut_allele_len - 1
self.wt_sequence = sequence.replace(self.original_snp_sign,
self.wt_allele, 1)
self.mut_sequence = sequence.replace(self.original_snp_sign,
self.mut_allele, 1)
self.ex_wt_sequence = expand_sequence(self.wt_sequence)
self.ex_mut_sequence = expand_sequence(sequence.replace(self.original_snp_sign,
self.mut_allele, 1))
self.digest_penzymes = []
if self.snp_pos < 50 or (len(self.wt_sequence) - self.wt_pos_end < 50 \
or len(self.mut_sequence) - self.mut_pos_end < 50):
raise fexceps.GetSNPFromSequenceError('Flanking sequence is to short')
else:
raise fexceps.GetSNPFromSequenceError('No valid SNP info in seq: %r' % sequence)
