def betterClumpFinding(Genome, k, t, L):
genomeList = list(Genome)
frequentPatterns = []
clump = []
for i in range(4**k - 1 + 1):
clump.insert(i, 0)
text = Genome[0:L]
frequencyArray = computingFreqs(text,k)
for i in range(4**k-1+1):
if frequencyArray[i] >= t:
clump[i] = 1
for i in range(len(genomeList) - L + 1):
firstPattern = Genome[i-1:i-1+k]
index = patternToNumber(firstPattern)
frequencyArray[index] = frequencyArray[index]-1
lastPattern = Genome[i+L-k:i+L-k+k]
index = patternToNumber(lastPattern)
frequencyArray[index] = frequencyArray[index]+1
if frequencyArray[index] >= t:
clump[index] = 1
for i in range(4**k):
if clump[i] == 1:
pattern = numberToPattern(i,k)
frequentPatterns.append(pattern)
return frequentPatterns
def betterClumpFinding(Genome, k, t, L):
genomeList = list(Genome)
frequentPatterns = []
clump = []
for i in range(4**k - 1 + 1):
clump.insert(i, 0)
text = Genome[0:L]
frequencyArray = computingFreqs(text, k)
for i in range(4**k - 1 + 1):
if frequencyArray[i] >= t:
clump[i] = 1
for i in range(len(genomeList) - L + 1):
firstPattern = Genome[i - 1:i - 1 + k]
index = patternToNumber(firstPattern)
frequencyArray[index] = frequencyArray[index] - 1
lastPattern = Genome[i + L - k:i + L - k + k]
index = patternToNumber(lastPattern)
frequencyArray[index] = frequencyArray[index] + 1
if frequencyArray[index] >= t:
clump[index] = 1
for i in range(4**k):
if clump[i] == 1:
pattern = numberToPattern(i, k)
frequentPatterns.append(pattern)
return frequentPatterns
def frequencyArray(Close, Text, k, d): patternsCount = pow(4,k) fArray = [0] * patternsCount for i in xrange(0, patternsCount): if Close[i] == 1: Pattern = nTp.numberToPattern(i, k) fArray[i] = aM.approximate_count(Pattern, Text, d) return fArray
def computingFreqs(Text, k):
frequentPatterns = []
frequencyArray = computingFreqs(Text,k)
maxCount = max(frequencyArray)
for i in range(4**k-1+1):
if frequencyArray[i] == maxCount:
pattern = numberToPattern(i,k)
frequentPatterns.append(pattern)
return frequentPatterns
def computingFreqs(Text, k):
frequentPatterns = []
frequencyArray = computingFreqs(Text, k)
maxCount = max(frequencyArray)
for i in range(4**k - 1 + 1):
if frequencyArray[i] == maxCount:
pattern = numberToPattern(i, k)
frequentPatterns.append(pattern)
return frequentPatterns
def numberToPattern(index, k):
if k == 1:
return numberToSymbol(index)
prefixIndex = index // 4
r = index % 4
if index == 0:
symbol = 'A'
else:
symbol = numberToSymbol(r)
prefixPattern = numberToPattern(prefixIndex, k - 1)
return prefixPattern + symbol
def frequencyArrayAndReverse(Close, Text, k, d): patternsCount = pow(4,k) fArray = [0] * patternsCount for i in xrange(0, patternsCount): if Close[i] == 1: if fArray[i] > 0: continue Pattern = nTp.numberToPattern(i, k) ReversePattern = rC.reverse_complement(Pattern) anotherIndex = nTp.patternToNumber(ReversePattern) totalSum = aM.approximate_count(Pattern, Text, d) + aM.approximate_count(ReversePattern, Text, d) fArray[i] = totalSum fArray[anotherIndex] = totalSum return fArray
def clumpFinding(Genome, k, t, L):
genomeList = list(Genome)
frequentPatterns = []
clump = []
for i in range(4**k - 1 + 1):
clump[i] = 0
for i in range(len(genomeList) - L + 1):
text = genomeList[i:i + L]
frequencyArray = computingFreqs(text, k)
for index in range(4**k - 1 + 1):
if frequencyArray[index] >= t:
clump[index] = 1
for i in range(4**k):
if clump[i] == 1:
pattern = numberToPattern(i, k)
frequentPatterns.append(pattern)
return frequentPatterns
def clumpFinding(Genome, k, t, L):
genomeList = list(Genome)
frequentPatterns = []
clump = []
for i in range(4**k - 1 + 1):
clump[i] = 0
for i in range(len(genomeList) - L + 1):
text = genomeList[i:i+L]
frequencyArray = computingFreqs(text,k)
for index in range(4**k-1+1):
if frequencyArray[index] >= t:
clump[index] = 1
for i in range(4**k):
if clump[i] == 1:
pattern = numberToPattern(i,k)
frequentPatterns.append(pattern)
return frequentPatterns
def maxPatterns(fArray, k): maxCount = max(fArray) indexes = [i for i, x in enumerate(fArray) if x == maxCount] return set([nTp.numberToPattern(x, k) for x in indexes])
def closeNeighborsLines(Text, k, d): fArray = closeNeighbors(Text, k, d) indexes = [i for i, x in enumerate(fArray) if x != 0] return set([nTp.numberToPattern(x, k) for x in indexes])