def __init__(self, bindres_file, pssms_file, log_file, method, fold=5, undersampling=True, shuffle=True, maxEpochs_for_trainer=10, geneScale=(0, 10)):
if geneScale[0] != 0 or geneScale[1] <= geneScale[0]:
raise ValueError("Gene Scale in GA has to be (0, n). n is greater than 0.")
if method != "neuralNetwork" and method != "randomForest" and method != "SVM":
raise ValueError("method must be neuralNetwork or randomForest or SVM [{}]".format(method))
self.bindingResidueData, self.pssmData = feature.parse_record_files(bindres_file, pssms_file)
self.log_file = log_file
self.method = method
self.fold = fold
self.undersampling = undersampling
self.shuffle = shuffle
self.maxEpochs_for_trainer=maxEpochs_for_trainer
self.SVMParamScales = {"cost" : (-10, 10), "gamma" : (-10, 5)}
self.NNParamScales = {"node_num" : (5, 50), "learning_rate" : (0.01, 0.1)}
self.RFParamScales = {"n_estimators" : (101, 1001), "max_features" : (2, 30)}
self.windowSizeScales = (1, 19)
self.geneScale = geneScale
self.log = {}
def create_positive_and_negative_dataset(window_size, sequence_length):
bindres_file = "/tmp/bindingData.txt"
pssms_file = "/tmp/pssms.txt"
with open(bindres_file, "w") as fp:
fp.write("http://purl.uniprot.org/uniprot/AAAAAA 0 1 2\n")
fp.write("http://purl.uniprot.org/uniprot/BBBBBB 9\n")
fp.write("http://purl.uniprot.org/uniprot/CCCCCC 7 2\n")
with open(pssms_file, "w") as fp:
fp.write(">http://purl.uniprot.org/uniprot/AAAAAA\n")
pssm = '\n'.join(map('\t'.join, [['1' if i == j else '-1' for i in xrange(20)]+['5' for l in xrange(20)] for j in xrange(sequence_length)]))
fp.write(pssm+"\n")
fp.write(">http://purl.uniprot.org/uniprot/BBBBBB\n")
pssm = '\n'.join(map('\t'.join, [['2' if i == j else '-2' for i in xrange(20)]+['5' for l in xrange(20)] for j in xrange(sequence_length)]))
fp.write(pssm+"\n")
fp.write(">http://purl.uniprot.org/uniprot/CCCCCC\n")
pssm = '\n'.join(map('\t'.join, [['3' if i == j else '-3' for i in xrange(20)]+['5' for l in xrange(20)] for j in xrange(sequence_length)]))
fp.write(pssm+"\n")
bindingResidueData, pssmData = feature.parse_record_files(bindres_file, pssms_file)
positive_dataset, negative_dataset = feature.create_dataset(bindingResidueData, pssmData, window_size)
return positive_dataset, negative_dataset
def __init__(self,
bindres_file,
pssms_file,
log_file,
method,
fold=5,
undersampling=True,
shuffle=True,
maxEpochs_for_trainer=10,
geneScale=(0, 10)):
if geneScale[0] != 0 or geneScale[1] <= geneScale[0]:
raise ValueError(
"Gene Scale in GA has to be (0, n). n is greater than 0.")
if method != "neuralNetwork" and method != "randomForest" and method != "SVM":
raise ValueError(
"method must be neuralNetwork or randomForest or SVM [{}]".
format(method))
self.bindingResidueData, self.pssmData = feature.parse_record_files(
bindres_file, pssms_file)
self.log_file = log_file
self.method = method
self.fold = fold
self.undersampling = undersampling
self.shuffle = shuffle
self.maxEpochs_for_trainer = maxEpochs_for_trainer
self.SVMParamScales = {"cost": (-10, 10), "gamma": (-10, 5)}
self.NNParamScales = {
"node_num": (5, 50),
"learning_rate": (0.01, 0.1)
}
self.RFParamScales = {
"n_estimators": (101, 1001),
"max_features": (2, 30)
}
self.windowSizeScales = (1, 19)
self.geneScale = geneScale
self.log = {}
indim = 21 * (2 * window_size + 1)
clf = svm.SVC(C=cost, gamma=gamma, class_weight='auto')
clf.fit(train_dataset, train_labels)
return clf
def create_classifier(method_and_genes, positive_dataset, negative_dataset):
method, genes = method_and_genes[0], method_and_genes[1:]
if method == "neuralNetwork":
return create_NN_classifier(genes, positive_dataset, negative_dataset)
elif method == "randomForest":
return create_RF_classifier(genes, positive_dataset, negative_dataset)
elif method == "SVM":
return create_SVM_classifier(genes, positive_dataset, negative_dataset)
else:
raise ValueError("method must be neuralNetwork or randomForest or SVM [{}]".format(method))
if __name__ == "__main__":
arguments = docopt(__doc__)
best_chromosome_file = arguments['<best_chromosome_file>']
bindres_file = arguments['<binding_residue_file>']
pssms_file = arguments['<pssms_file>']
output_pickled_model_file = arguments['<output_pickled_model_file>']
method_and_genes = common.get_method_and_genes(best_chromosome_file)
bindingResidueData, pssmData = feature.parse_record_files(bindres_file, pssms_file)
positive_dataset, negative_dataset = feature.create_dataset(bindingResidueData, pssmData, int(method_and_genes[3]))
clf_or_net = create_classifier(method_and_genes, positive_dataset, negative_dataset)
with open(output_pickled_model_file, 'wb') as fp:
pickle.dump(clf_or_net, fp)
def create_classifier(method_and_genes, positive_dataset, negative_dataset):
method, genes = method_and_genes[0], method_and_genes[1:]
if method == "neuralNetwork":
return create_NN_classifier(genes, positive_dataset, negative_dataset)
elif method == "randomForest":
return create_RF_classifier(genes, positive_dataset, negative_dataset)
elif method == "SVM":
return create_SVM_classifier(genes, positive_dataset, negative_dataset)
else:
raise ValueError(
"method must be neuralNetwork or randomForest or SVM [{}]".format(
method))
if __name__ == "__main__":
arguments = docopt(__doc__)
best_chromosome_file = arguments['<best_chromosome_file>']
bindres_file = arguments['<binding_residue_file>']
pssms_file = arguments['<pssms_file>']
output_pickled_model_file = arguments['<output_pickled_model_file>']
method_and_genes = common.get_method_and_genes(best_chromosome_file)
bindingResidueData, pssmData = feature.parse_record_files(
bindres_file, pssms_file)
positive_dataset, negative_dataset = feature.create_dataset(
bindingResidueData, pssmData, int(method_and_genes[3]))
clf_or_net = create_classifier(method_and_genes, positive_dataset,
negative_dataset)
with open(output_pickled_model_file, 'wb') as fp:
pickle.dump(clf_or_net, fp)
