Scribd
Upload
469 views2 pages

01 07 FrequentWordsWithMismatchesSolution

www.rosalind.info and/or stepic frequent words with mismatches problem. This is a solution for the problem in Python.

Uploaded by

crl_ca
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
469 views2 pages

01 07 FrequentWordsWithMismatchesSolution

www.rosalind.info and/or stepic frequent words with mismatches problem. This is a solution for the problem in Python.

Uploaded by

crl_ca
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

import itertools # Calculate all mutations within the specified distance of word # WARNING: The same mutation can

be listed multiple times!! def mutations(word, hamming_distance, charset='ATCG'): for indices in itertools.combinations(range(len(word)), hamming_distance): for replacements in itertools.product(charset, repeat=hamming_distance): mutation = list(word) for index, replacement in zip(indices, replacements): mutation[index] = replacement yield "".join(mutation) # Count the number of occurrences of sub in string def occurrences(string, sub): count = start = 0 while True: start = string.find(sub, start) + 1 if start > 0: count+=1 else: return count # Count all kmers in Genome and add to kmerDict kmerDict = {} # For each kmer in kmerDict, add kmer plus count to tmpDict. Then find all # mutations of kmer within d and add them to tmpDict. tmpDict = {} # Open the input file and read in Genome, k, and d. f = open('frequent_words_mismatch_data.txt', 'r') Genome = f.readline().rstrip('\n') # header in sample data Genome = f.readline().rstrip('\n') k = int(f.readline().rstrip('\n')) d = int(f.readline().rstrip('\n')) print 'parameters' print k print d f.close() # Step through genome 1 character at a time and add all kmers to kmerDict numChars = len(Genome) for i in range (0, numChars - k + 1): kmer = Genome[i:i+k] if kmer in kmerDict: kmerDict[kmer] += 1 else: kmerDict[kmer] = 1 print 'kmerDict completed' # Take kmer from kmerDict and add it to tmpDict # Find each mutation of kmer and record occurrences in tmpDict # Repeat for each entry in kmerDict # Result is count of all kmers and count of all d mutations. for key in kmerDict: count = kmerDict[key] if key in tmpDict: tmpDict[key] += count

else: tmpDict[key] = count # kmerDict[key] tmpList = mutations(key, d) tmpList = set(tmpList) tmpList = list(tmpList) for tmpMutation in tmpList: if tmpMutation != key: if tmpMutation in tmpDict: tmpDict[tmpMutation] += count # kmerDict[key] else: tmpDict[tmpMutation] = count print 'tmpDict completed' # Display the answers maxNum = 0 for key in sorted(tmpDict, key=tmpDict.get, reverse=True): if tmpDict[key] >= maxNum: maxNum = tmpDict[key] print key + ' ' + str(tmpDict[key])

You might also like