def create_folded_dataset(self, window_size):
positive_dataset, negative_dataset = feature.create_dataset(
self.bindingResidueData, self.pssmData, window_size)
folded_dataset = dataset.FoldedDataset(
positive_dataset,
negative_dataset,
fold=self.fold,
undersampling=self.undersampling,
shuffle=self.shuffle)
return folded_dataset
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 create_folded_dataset(self, window_size):
positive_dataset, negative_dataset = feature.create_dataset(self.bindingResidueData, self.pssmData, window_size)
folded_dataset = dataset.FoldedDataset(positive_dataset, negative_dataset, fold=self.fold,
undersampling=self.undersampling, shuffle=self.shuffle)
return folded_dataset
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)
