AIM: To develop an artificial neural network (ANN) model for predicting the resistance index (RI) of taxoids. METHODS: A dataset of 63 experimental data points were compiled from literatures and subdivided into traini...AIM: To develop an artificial neural network (ANN) model for predicting the resistance index (RI) of taxoids. METHODS: A dataset of 63 experimental data points were compiled from literatures and subdivided into training and external test sets randomly. Electrotopological state (E-state) indices were calculated to characterize molecular structure, together with a principle component analysis to reduce the variable space and analyze the relative importance of E-state indices. Back propagation neural network (BPNN) technique was used to build the models. Five-fold cross validation was performed and five models with different compounds composition in training and validation sets were built. The independent external test set was used to evaluate the predictive ability of models. RESULTS: The final model was proved to be good with the cross validation Qcv2 0.62, external testing R2 0.84 and the slope of the regression line through the origin for testing set is 0.9933. CONCLUSION: The QSAR model can predict the RI to a relative nicety, which will aid in the development of new anti-MDR taxoids.展开更多
文摘AIM: To develop an artificial neural network (ANN) model for predicting the resistance index (RI) of taxoids. METHODS: A dataset of 63 experimental data points were compiled from literatures and subdivided into training and external test sets randomly. Electrotopological state (E-state) indices were calculated to characterize molecular structure, together with a principle component analysis to reduce the variable space and analyze the relative importance of E-state indices. Back propagation neural network (BPNN) technique was used to build the models. Five-fold cross validation was performed and five models with different compounds composition in training and validation sets were built. The independent external test set was used to evaluate the predictive ability of models. RESULTS: The final model was proved to be good with the cross validation Qcv2 0.62, external testing R2 0.84 and the slope of the regression line through the origin for testing set is 0.9933. CONCLUSION: The QSAR model can predict the RI to a relative nicety, which will aid in the development of new anti-MDR taxoids.
