def _remove_rec_sites(seq, enzymes=None):
'''It modifies all rec sites in the sequence to be able to use with
goldenbraid pipeline'''
if enzymes is None:
enzymes = MANDATORY_DOMEST_ENZYMES
rec_sites = get_ret_sites(enzymes)
# regex with the sites to domesticate
rec_sites_regex = '(' + '|'.join(rec_sites) + ')'
rec_sites_regex = re.compile(rec_sites_regex, flags=re.IGNORECASE)
rec_sites_in_seq = []
fragments = []
for splitted_part in rec_sites_regex.split(str(seq)):
if rec_sites_regex.match(splitted_part):
rec_sites_in_seq.append(splitted_part)
else:
fragments.append(splitted_part)
new_seq = Seq('', alphabet=generic_dna)
# we can not convert a rec site in another rec site
_cumulative_patch = '' # it is only used to know the frame
rec_site_pairs = []
for fragment, rec_site_in_seq in izip_longest(fragments, rec_sites_in_seq):
new_seq += fragment
if rec_site_in_seq is not None:
_cumulative_patch += fragment + rec_site_in_seq
new_rec_site = _domesticate_rec_site(rec_site_in_seq,
_cumulative_patch,
rec_sites_regex)
rec_site_pairs.append({'original': rec_site_in_seq,
'modified': new_rec_site})
new_seq += new_rec_site
coding_seq = Seq(_get_upper_nucls(seq))
new_coding_seq = Seq(_get_upper_nucls(new_seq))
if str(coding_seq.translate()) != str(new_coding_seq.translate()):
msg = 'The generated sequence does not produce the same peptide'
raise ValueError(msg)
if rec_sites_regex.search(str(new_seq)):
msg = 'Not all rec_sites modified'
raise ValueError(msg)
return new_seq, rec_site_pairs, fragments
def num_rec_sites(self):
rec_sites = get_ret_sites(ENZYMES_USED_IN_GOLDENBRAID)
# regex with the sites to domesticate
rec_sites_regex = '(' + '|'.join(rec_sites) + ')'
rec_sites_regex = re.compile(rec_sites_regex)
return len(re.findall(rec_sites_regex, self.residues))
