def main():
sequences = readfasta('transversionVsTransitionTest.fasta')
rates = calcTransitionTransversionRates(sequences)
print('The percentage of transitions is {}%'.format(rates[0]))
print('The percentage of transversions is {}%'.format(rates[1]))
def main(geneFileName, outputFileName):
geneList = []
geneList = readfasta(geneFileName)
outputFile = open(outputFileName, 'w')
for gene in geneList:
AASequence = translateGeneDNAToAASequence(gene[2])
AASequence = AASequence[1:(len(AASequence) - 1)]
transmemDomainsHH = calcTransmemDomainsHH(AASequence)
transmemDomainsKD = calcTransmemDomainsKD(AASequence)
outputFile.write(gene[1] + '\n')
outputFile.write(AASequence + '\n\n')
outputFile.write(
'According to hydrophobicity and helicity there are ' +
str(len(transmemDomainsHH)) +
' that identify as transmembrane domains. They are:\n')
for TDregion in transmemDomainsHH:
outputFile.write(AASequence[TDregion[0]:TDregion[1]] + ', ')
outputFile.write(
'\n\nAccording to the Kyte Dolittle scale there are ' +
str(len(transmemDomainsKD)) +
' that identify as transmembrane domains. They are:\n')
for TDregion in transmemDomainsKD:
outputFile.write(AASequence[TDregion[0]:TDregion[1]] + ', ')
outputFile.write('\n\n')
def main(DNAFileName):
sys.setrecursionlimit(100000)
params = [5, -4, -11]
DNAList = readfasta(DNAFileName)
TempDNAList = DNAList[:]
for i in range(len(DNAList) - 1):
currentBest = bestCombination(TempDNAList, params)
TempDNAList.remove(currentBest[0])
TempDNAList.remove(currentBest[1])
TempDNAList.append([
str(i),
str(i),
backtraceMatchOnly(currentBest[2], currentBest[0][2],
currentBest[1][2], params)
])
bestAlignment = TempDNAList[0][2]
for DNA in DNAList:
memo = buildBlankMemo(len(DNA[2]), len(bestAlignment), params)
val = calcMemo(len(DNA[2]), len(bestAlignment), DNA[2], bestAlignment,
memo, params)
print('Alignment Score for ' + DNA[0] + ': ' + str(val))
print(str(backtrace(memo, DNA[2], bestAlignment, params)[0]) + '\n')
def main():
sequences = readfasta('FinalProblemCS4.txt')
consensusTrees = []
resampleMatrices = []
bootstrapReplicates = int(input('How many bootstrap replicates should be made?: '))
for rep in range(bootstrapReplicates):
treeSubsitutions = {'Alpha' : 0,
'Beta' : 0,
'Gamma' : 0}
resampleMatrix = []
for site in range(len(sequences[0][2])):
siteValues = []
randomSite = random.randrange(0, len(sequences[0][2]))
for seq in sequences:
siteValues.append(seq[2][randomSite])
resampleMatrix.append(siteValues)
if isInformative(siteValues):
currentScores = getParsimonyScores(siteValues)
treeSubsitutions['Alpha'] += currentScores[0]
treeSubsitutions['Beta'] += currentScores[1]
treeSubsitutions['Gamma'] += currentScores[2]
currentConsensusTree = max(treeSubsitutions, key=treeSubsitutions.get)
consensusTrees.append(currentConsensusTree)
resampleMatrices.append(resampleMatrix)
consensusTreeCount = Counter(consensusTrees)
consensusTree = max(consensusTreeCount, key=consensusTreeCount.get)
#Output
for sample in range(3):
replicates = makeBootstrapReplicatesPrintable(resampleMatrices[sample])
print('Bootstrap number {}'.format(sample))
for rep in range(len(replicates)):
print('Replicate number {}'.format(rep))
print(replicates[rep] + '\n')
print('Supported Topology: ')
printConsensusTree(consensusTrees[sample], sequences)
print('\n')
print('The Final Consensus Tree Topology:')
printConsensusTree(consensusTree, sequences)
print('Bootstrap Value: {}%'.format(
consensusTreeCount[consensusTree]/bootstrapReplicates * 100))
def main():
sequences = readfasta('originalSequences.fasta')
mutationRates = [0.00241, 0.00139]
transiTransvRates = [0.77, 0.23]
yamaAntigenicSites = [[116, 137], [141, 150], [162, 167], [195, 203]]
victAntigenicSites = [[116, 137], [141, 150], [162, 167], [197, 205]]
totalPopulation = 100
simulationYears = 10
data = influenzaBSimulation(totalPopulation, simulationYears, sequences[0],
sequences[1], mutationRates, transiTransvRates,
yamaAntigenicSites, victAntigenicSites)
#generates output file for use in a phylogenetic tree
outputFile = open('dataForTree.fasta', 'w')
yearlySampleSize = 5
yearCounter = 0
for year in data:
for sample in range(yearlySampleSize):
randomSeq = random.choice(year)
outputFile.write(str(randomSeq[1]) + '\n')
outputFile.write(str(randomSeq[2]) + '\n')
outputFile.write('\n')
yearCounter += 1
def main(DNAFileName):
sys.setrecursionlimit(100000)
#sys.tracebacklimit = 0
hoxD55Scoring = {
'A': {
'A': 91,
'C': -90,
'G': -25,
'T': -100
},
'C': {
'A': -90,
'C': 100,
'G': -100,
'T': -25
},
'G': {
'A': -25,
'C': -100,
'G': 100,
'T': -90
},
'T': {
'A': -100,
'C': -25,
'G': -90,
'T': 91
}
}
hoxD70Scoring = {
'A': {
'A': 91,
'C': -114,
'G': -31,
'T': -123
},
'C': {
'A': -114,
'C': 100,
'G': -125,
'T': -31
},
'G': {
'A': -31,
'C': -125,
'G': 100,
'T': -114
},
'T': {
'A': -123,
'C': -31,
'G': -114,
'T': 91
}
}
gapPenalties = [-120, -140]
hiScoreCords = []
DNAList = readfasta(DNAFileName)
tempDNAList = DNAList[:]
for i in range(len(DNAList) - 1):
bestCombo = bestLocalCombination(tempDNAList, hoxD70Scoring,
gapPenalties[1])
hiScoreCords = calcHighScoreCord(bestCombo[2])
alignedSeqs = localBacktrace(bestCombo[2], bestCombo[0][2],
bestCombo[1][2], gapPenalties[1],
hiScoreCords)
assembledSeq = assembleContigs(bestCombo[0][2], bestCombo[1][2],
alignedSeqs[0], alignedSeqs[1])
if assembledSeq == 'flag':
raise NameError(bestCombo[0][0] + ' and ' + bestCombo[1][0] +
' do not fit into defined assemblies')
tempDNAList.remove(bestCombo[0])
tempDNAList.remove(bestCombo[1])
tempDNAList.append([
bestCombo[0][0] + bestCombo[1][0],
bestCombo[0][1] + bestCombo[1][1], assembledSeq
])
print(tempDNAList[-1][0])
print(tempDNAList[-1][2] + '\n')
averageCoverage = calcCoverage(tempDNAList[0][2], DNAList, hoxD70Scoring,
gapPenalties[1])
print('The fully assembled sequence:\n' + tempDNAList[0][2])
print('Coverage: ' + str(averageCoverage))
'''
def main():
sequence = readfasta()
while not alphaHelixFound and count < len(sequence[0][2]):