def distanceBetweenPatternAndStrings(pattern, DNA):
"""
Finds total distance between a pattern a set of sequences.
Input: A string pattern and collection of strings DNA.
Output: The total distance between DNA and pattern.
"""
k = len(pattern)
distance = 0
# finds minimum distance by checking all kmers in each string
for sequence in DNA:
hammingDistance = float("inf")
for i in range(len(sequence) - k + 1):
kmer = sequence[i:i + k]
d = f1.hammingDistance(pattern, kmer)
# found minimum distance; save
if hammingDistance > d:
hammingDistance = d
# distance keeps track of sum of distances
distance += hammingDistance
return distance
def motifEnumeration(DNA, k, d):
"""
Find all k-mer motifs with at most d mismatches given a collection of
strings.
Input: A collection of strings Dna, and integers k and d.
Output: All (k, d)-motifs in Dna.
"""
k = int(k)
d = int(d)
patterns = []
DNAkmers = [[] for seq in DNA] # 2d array of all sequence kmers
candidateMotifs = [] # contains set of generated kmer neighborhoods
# create list of all kmers as well as kmer neighborhoods
for dnaIndex in range(len(DNA)):
sequence = DNA[dnaIndex]
for seqIndex in range(len(sequence) - k + 1):
kmer = sequence[seqIndex:seqIndex + k]
DNAkmers[dnaIndex].append(kmer)
candidateMotifs.extend(f1.neighbors(kmer, d))
candidateMotifs = set(candidateMotifs)
# exhaustive search candidates for true motifs
for candidate in candidateMotifs:
found = [False] * len(DNAkmers)
for listIndex in range(len(DNAkmers)):
for kmer in DNAkmers[listIndex]:
if f1.hammingDistance(candidate, kmer) <= d:
found[listIndex] = True
break
if False not in found:
patterns.append(candidate)
return set(patterns)