def get_model_RFE_top_features(self,expression_file,ic50_file,target_features,drug):
expression_frame,ic50_series = dfm.get_expression_frame_and_ic50_series_for_drug(expression_file, ic50_file,drug,normalized=True,trimmed=True,threshold=None)
scikit_data,scikit_target = dfm.get_scikit_data_and_target(expression_frame,ic50_series)
step_length = int(len(scikit_data.tolist()[0]) / 100) + 1
selector = RFE(self.model,int(target_features),step=step_length)
selector.fit(scikit_data,scikit_target)
return [expression_frame.index[i] for i in xrange(0,len(expression_frame.index)) if selector.support_[i]]
def get_model_coefficients_threshold(self,expression_file,ic50_file,threshold,drug):
if(self.model_type == 'svm' and self.kernel == 'linear'):
expression_frame,ic50_series = dfm.get_expression_frame_and_ic50_series_for_drug(expression_file, ic50_file,drug,normalized=True,trimmed=True,threshold=threshold)
scikit_data,scikit_target = dfm.get_scikit_data_and_target(expression_frame,ic50_series)
self.model.fit(scikit_data,scikit_target)
return expression_frame.index, self.model.coef_[0]
else:
raise Exception("Method only defined for the SVM linear model")
def get_predictions_full_CCLE_dataset_threshold(self,expression_file,ic50_file,threshold,drug):
training_frame,training_series = dfm.get_expression_frame_and_ic50_series_for_drug(expression_file,ic50_file,drug,normalized=True,trimmed=True,threshold=threshold)
training_data,training_target = dfm.get_scikit_data_and_target(training_frame,training_series)
cell_lines, testing_data = dfm.get_normalized_full_expression_identifiers_and_data(expression_file,training_frame.index)
self.model.fit(training_data,training_target)
predictions = self.model.predict(testing_data)
return cell_lines, predictions
def get_predictions_full_CCLE_dataset_top_features(self,expression_file,ic50_file,num_features,drug):
expression_frame,ic50_series = dfm.get_expression_frame_and_ic50_series_for_drug(expression_file,ic50_file,drug,normalized=True,trimmed=True)
top_features = dfm.get_pval_top_n_features(expression_frame,ic50_series,num_features)
expression_frame = expression_frame.ix[top_features]
scikit_data,scikit_target = dfm.get_scikit_data_and_target(expression_frame,ic50_series)
cell_lines, testing_data = dfm.get_normalized_full_expression_identifiers_and_data(expression_file,expression_frame.index)
self.model.fit(scikit_data,scikit_target)
predictions = self.model.predict(testing_data)
return cell_lines,predictions,list(top_features)
