def frequent_words_with_mismatches_by_sorting(text, k, d):
frequent_patterns = []
neighborhoods = []
index = []
count = []
for i in range(0,len(text)-k +1):
neighborhoods.append(neighbors(text[i:i+k],d))
neighborhoods = [item for sublist in neighborhoods for item in sublist]
neighborhood_array = neighborhoods
for i in range(0, len(neighborhoods)):
index.append(0)
count.append(0)
for i in range(0,len(neighborhoods)):
pattern = neighborhood_array[i]
index[i] = p_to_n_modify(pattern)
count[i] = 1
sorted_index = sorted(index)
for i in range(0, neighborhoods.__len__()-1):
if sorted_index[i] == sorted_index[i+1]:
count[i+1] = count[i] +1
maxcount = max(count)
for i in range(0, len(neighborhoods)):
if count[i] == maxcount:
pattern = n_to_p_modify(sorted_index[i], k)
frequent_patterns.append(pattern)
return frequent_patterns
def motif_enumeration(dna, k, d):
patterns = []
for slice in dna:
for i in range(0,len(slice)-k +1):
neighborhood = set(neighbors(slice[i:i+k],d))
for pattern in neighborhood:
count = 0
for slice_II in dna:
if patterncount_with_mismatchs(slice_II,pattern,d) > 0:
count += 1
if count >= len(dna):
patterns.append(pattern)
patterns = set(patterns)
return patterns
def frequent_words_with_mismatches(text, k, d):
frequent_patterns = []
close = []
frequent_array = []
for i in range(0, pow(4,k)):
close.append(0)
frequent_array.append(0)
for i in range(0,len(text)-k+1):
neighborhood = neighbors(text[i:i+k],d)
for pattern in neighborhood:
index = p_to_n_modify(pattern)
close[index] = 1
for i in range(0, pow(4,k)):
if close[i] == 1:
pattern = n_to_p_modify(i,k)
frequent_array[i] = len(approximate_pattern_matching(pattern,text,d))
max_count = max(frequent_array)
for i in range(0,pow(4,k)):
if frequent_array[i] == max_count:
pattern = n_to_p_modify(i,k)
frequent_patterns.append(pattern)
return frequent_patterns