def test_writeFastaFile(self):
"""Test method to test the correct writing of a fasta file."""
if os.path.exists("testWriteFasta.fas"):
os.remove("testWriteFasta.fas")
sequence = [["ACGT", "ACGTAATTA"]]
expectedReadSequence = [
">Alignment 0 sequence 0", "ACGT", ">Alignment 0 sequence 1",
"ACGTAATTA"
]
readInputSequence = []
# first test case, filename with extension
io().writeFastaFile(sequence, "testWriteFasta.fas")
testInputFile = open("testWriteFasta.fas")
for line in testInputFile.readlines():
readInputSequence.append(line.strip("\n"))
self.assertEqual(expectedReadSequence, readInputSequence)
testInputFile.close()
os.remove("testWriteFasta.fas")
# second test case, filename without extension
readInputSequence = []
io().writeFastaFile(sequence, "testWriteFasta")
testInputFile = open("testWriteFasta.fas")
for line in testInputFile.readlines():
readInputSequence.append(line.strip("\n"))
self.assertEqual(expectedReadSequence, readInputSequence)
testInputFile.close()
os.remove("testWriteFasta.fas")
def test_writeFastaFile(self):
"""Test method to test the correct writing of a fasta file."""
if os.path.exists("testWriteFasta.fas"):
os.remove("testWriteFasta.fas")
sequence = [["ACGT", "ACGTAATTA"]]
expectedReadSequence = [">Alignment 0 sequence 0", "ACGT", ">Alignment 0 sequence 1", "ACGTAATTA"]
readInputSequence = []
# first test case, filename with extension
io().writeFastaFile(sequence, "testWriteFasta.fas")
testInputFile = open("testWriteFasta.fas")
for line in testInputFile.readlines():
readInputSequence.append(line.strip("\n"))
self.assertEqual(expectedReadSequence, readInputSequence)
testInputFile.close()
os.remove("testWriteFasta.fas")
# second test case, filename without extension
readInputSequence = []
io().writeFastaFile(sequence, "testWriteFasta")
testInputFile = open("testWriteFasta.fas")
for line in testInputFile.readlines():
readInputSequence.append(line.strip("\n"))
self.assertEqual(expectedReadSequence, readInputSequence)
testInputFile.close()
os.remove("testWriteFasta.fas")
def nussinov(sequence, outputFile):
"""Executes the RNA-folding algorithm from Nussinov.
sequence: The RNA-sequnce as a list.
outputFile: The name of the output file."""
print "\nThe following sequence is given:"
print sequence[0]
print "\n"
nussinov = Nussinov(sequence[0])
nussinov.execute()
print "\nDot-bracket: "
io().writeRnaDotBracketNotation(sequence[0], nussinov.pairedBases, outputFile)
print "The result was also written to: ", os.path.abspath(outputFile)
def needlemanWunschN3(sequences, weightFunction="weightFunctionDifference", outputFile="nw3.fas"):
"""Executes the Needleman-Wunsch algorithm with three sequences"""
print "\nThe following sequences are given:"
for i in sequences:
print i
print "\nComputing solution...\n\n"
nw3 = NW3(sequences[0], sequences[1], sequences[2], weightFunction)
result = nw3.execute()
io().writeFastaFile(result, outputFile)
print "\nScore: ", nw3.computation_matrix[-1][-1][-1]
print "Number of optimal solutions: ", len(result)
print "\nOne solution is:\n", result[0][0], "\n", result[0][1], "\n", result[0][2]
print "\nFor more solutions look in the file \"nw3.fas\" in the bin directory.\n"
def needlemanWunsch(sequences, scoreFunction, outputFile, numberOfSolutions):
"""Executes the Needleman-Wunsch algorithm with a default score function defined as: a == b -> 0 and a !=b --> 1.\n
Stores the alignments per default in file needlemanWunsch.fas.
To change the score function define a function in class PairwiseAligmentHelper and define the name as an input paramter.
scoreFunction: The name of the weigh function which is defined in class PairwiseAligmentHelper.
outputFile: The path to the output file.
numberOfSolutions: Maximal number of optimal solutions which should be computed."""
print "\nThe following sequences are given:"
for i in sequences:
print i
print "\nComputing solution...\n\n"
result = nw().compute(sequences, scoreFunction, int(numberOfSolutions), scoringValue=True)
print "\nScore: ", result[1]
print "Number of optimal solutions: ", len(result[0])
print "\nOne solution is:\n", result[0][0][0], "\n", result[0][0][1]
print "\nFor more solutions look in the file \"needlemanWunsch.fas\" in the bin directory.\n"
io().writeFastaFile(result[0], outputFile)
def test_readFastaFile(self):
"""Test method to test the correct reading of a fasta file."""
if os.path.exists("testReadFasta.fas"):
os.remove("testReadFasta.fas")
# first test case: two sequences
sequenceToWrite = [["ACGT", "ACGTAATTA"]]
expectedSequence = ["ACGT", "ACGTAATTA"]
io().writeFastaFile(sequenceToWrite, "testReadFasta.fas")
readSequence = io().readFastaFile("testReadFasta.fas",
multipleSequenceAlignment=False)
self.assertEqual(expectedSequence, readSequence)
# second test case: two sequences but there are multilpe ones
sequenceToWrite = [["ACGT", "ACGTAATTA", "AGTTG"]]
expectedSequence = ["ACGT", "ACGTAATTA", "AGTTG"]
io().writeFastaFile(sequenceToWrite, "testReadFasta.fas")
readSequence = io().readFastaFile("testReadFasta.fas",
multipleSequenceAlignment=False)
self.assertNotEqual(expectedSequence, readSequence)
# third test case: multiple sequences
readSequence = io().readFastaFile("testReadFasta.fas",
multipleSequenceAlignment=True)
self.assertEqual(expectedSequence, readSequence)
os.remove("testReadFasta.fas")
def fengDoolittle(sequences, weightFunction, similarityScore, outputFile):
"""Executes the heuristic multiple sequence alignment by Feng and Doolittle.
sequences: All input sequnces to align.
weightFunction: The weight function defined in class PairwiseAlignmentHelper for the Needleman-Wunsch algorithm to compute the optimal local alignment.
similarityScore: Name of a similarity score defined in class PairwiseAligmentHelper.
outputFile: The output file name."""
fd = FengDoolittle(sequences, weightFunction, similarityScore)
alignmentDict = fd.computeMultipleAlignment()
alignment = [[]]
for i in alignmentDict:
alignment[0].append(alignmentDict[i])
io().writeFastaFile(alignment, outputFile)
print "Input sequences:\n"
for i in sequences:
print i
print "\nAlignment:"
for i in alignmentDict:
print alignmentDict[i]
print sumOfPairs(alignment[0], weightFunction)
def gotoh(sequences, scoreFunction="weightFunctionDifference", costFunction="gapCost", outputFile="gotoh.fas"):
"""Executes the Gotoh algorithm with a default score function defined as: a == b -> 0 and a !=b --> 1 and a cost function defined as: g(x) = 2 + k.\n
Stores the alignments per default in file gotoh.fas.
To change the score or cost function define a function in class PairwiseAligmentHelper and define the name as an input paramter.
scoreFunction: The name of the weigh function which is defined in class PairwiseAligmentHelper.
costFunction: The name of the gap cost function which is defined in class PairwiseAligmentHelper.
outputFile: The path to the output file.
"""
print "The following sequences are given:"
for i in sequences:
print i
print "Computing solution..."
gotoh = Gotoh(sequences[0], sequences[1], scoreFunction, costFunction)
result = gotoh.compute()
io().writeFastaFile(result, outputFile)
print "Number of solutions: ", len(result)
print "Score:", max(gotoh.computationMatrix[0][-1][-1], max(gotoh.computationMatrix[1][-1][-1], gotoh.computationMatrix[2][-1][-1]))
print "One solution is:\n", result[0][0], "\n", result[0][1]
print "For more solutions look in the file \"gotoh.fas\" in the bin directory."
def upgmaWpgma(upgmaWpgma, sequences, outputFile, fileFormat):
"""Executes the a phylogenetic clustering with a upgm or wpgm weighting.
sequences: All defined input sequences as a list.
outputFile: The name of the output file
fileFormat: The file format of the output file"""
#create
print "The following sequences are given:"
for i in sequences:
print i
print "Computing clustering..."
data = mah().createDataForUpgmaWpgma(sequences)
if upgmaWpgma:
upgma = UpgmaWpgma(data[0], len(data[1]))
upgma.compute_clustering()
if not fileFormat:
outputFile += ".graphML"
io().writeGraphMLFile(upgma.mapping, outputFile)
print "Clustering written as graphML file: ", os.path.abspath(outputFile)
else:
outputFile += ".newickTree"
cluster = upgma.get_newick_tree(with_edge_weights=True)
io().writeNewickTree(cluster, outputFile)
print "Computed upgma cluster: ", cluster
print "The clustering was also written to: ", os.path.abspath(outputFile)
else:
wpgma = UpgmaWpgma(data[0], len(data[1]), False, data[2])
wpgma.compute_clustering()
if not fileFormat:
outputFile += ".graphML"
io().writeGraphMLFile(wpgma.mapping, outputFile)
print "Clustering written as graphML file: ", os.path.abspath(outputFile)
else:
outputFile += ".newickTree"
cluster = wpgma.get_newick_tree(with_edge_weights=True)
io().writeNewickTree(cluster, outputFile)
print "Computed wpgma cluster: ", cluster
print "The clustering was also written to: ", os.path.abspath(outputFile)
def test_readFastaFile(self):
"""Test method to test the correct reading of a fasta file."""
if os.path.exists("testReadFasta.fas"):
os.remove("testReadFasta.fas")
# first test case: two sequences
sequenceToWrite = [["ACGT", "ACGTAATTA"]]
expectedSequence = ["ACGT", "ACGTAATTA"]
io().writeFastaFile(sequenceToWrite, "testReadFasta.fas")
readSequence = io().readFastaFile("testReadFasta.fas", multipleSequenceAlignment=False)
self.assertEqual(expectedSequence, readSequence)
# second test case: two sequences but there are multilpe ones
sequenceToWrite = [["ACGT", "ACGTAATTA", "AGTTG"]]
expectedSequence = ["ACGT", "ACGTAATTA", "AGTTG"]
io().writeFastaFile(sequenceToWrite, "testReadFasta.fas")
readSequence = io().readFastaFile("testReadFasta.fas", multipleSequenceAlignment=False)
self.assertNotEqual(expectedSequence, readSequence)
# third test case: multiple sequences
readSequence = io().readFastaFile("testReadFasta.fas", multipleSequenceAlignment=True)
self.assertEqual(expectedSequence, readSequence)
os.remove("testReadFasta.fas")
def getSequencesFromFile(inputFile):
"""Parse the input file to get the sequences. Returns the sequences as an array.
inputFile: A fasta format file with the input sequences."""
sequences = io().readFastaFile(inputFile)
return sequences
