def count_approx_pattern(text, pattern, d):
k = len(pattern)
count = 0
for i in range(len(text) - k + 1):
if hamming_dist(text[i:i + k], pattern) <= d:
count += 1
return count
def distance(pattern, text):
k = len(pattern)
min_dist = float("Inf")
for i in range(len(text) - k + 1):
dist = hamming_dist(text[i:i + k], pattern)
if dist < min_dist:
min_dist = dist
return min_dist
def neighbors(pattern, d):
if d == 0:
return pattern
if len(pattern) == 1:
return ['A', 'C', 'G', 'T']
neighborhood = set()
suffix_neighbors = neighbors(pattern[1:], d)
for suffix in suffix_neighbors:
if hamming_dist(pattern[1:], suffix) < d:
for nuc in ['A', 'C', 'G', 'T']:
neighborhood.add(nuc + suffix)
else:
neighborhood.add(pattern[0] + suffix)
return neighborhood
def main(k, d, data):
variants = get_all_kmers(k)
start = 0
data_len = len(data)
while start + k <= data_len:
sub = data[start:start + k]
for item in variants.keys():
if hamming_dist(item, sub) <= d:
variants[item] += 1
if hamming_dist(rev_complement(item), sub) <= d:
variants[item] += 1
start += 1
values = variants.values()
maximum = max(values)
answer = []
for key in variants.keys():
if variants[key] == maximum:
answer.append(key)
return answer
def main(k, d, data):
variants = get_all_kmers(k)
start = 0
data_len = len(data)
while start + k <= data_len:
sub = data[start:start + k]
for item in variants.keys():
if hamming_dist(item, sub) <= d:
variants[item] += 1
if hamming_dist(rev_complement(item), sub) <= d:
variants[item] += 1
start += 1
values = variants.values()
maximum = max(values)
answer = []
for key in variants.keys():
if variants[key] == maximum:
answer.append(key)
return answer
def hamming_dist_approx(pattern, string, d):
""" returns all approximate occurances (up to d mismatches) of pattern inside the string """
start = 0
pat_len = len(pattern)
str_len = len(string)
answer = []
while start + pat_len < str_len:
sub = string[start:start + pat_len]
if (hamming_dist(pattern, sub) <= d):
answer.append(start)
start += 1
return answer
def gen_d_neighb(d, fileName, data):
""" returns and write to file_name d-neighborhood of a string """
variants = get_all_kmers(len(data))
var_len = len(variants)
answers = []
for i in xrange(var_len):
if hamming_dist(data, variants[i]) <= d:
answers.append(variants[i])
file = open(fileName, 'w+')
for item in answers:
file.writelines(str(item) + "\n")
return answers
def CalculateScore(Motifs):
k = len(Motifs[0])
profile = FormProfile(Motifs)
consensus = ''
for i in range(k):
most_freq = 0
for nuc in ['A', 'C', 'G', 'T']:
if profile[nuc][i] > most_freq:
most_freq = profile[nuc][i]
to_add = nuc
consensus += to_add
score = 0
for motif in Motifs:
score += hamming_dist(consensus, motif)
return score
def hamming_dist_approx(pattern, string, d):
""" returns all approximate occurances (up to d mismatches) of pattern inside the string """
start = 0
pat_len = len(pattern)
str_len = len(string)
answer = []
while start + pat_len < str_len:
sub = string[start:start+pat_len]
if (hamming_dist(pattern, sub) <= d):
answer.append(start)
start += 1
return answer