Prediction of Anticancer / Non-anticancer Drugs Based on Comparative Molecular Moment Descriptors Using Artificial Neural Network and Support Vector Machine

Abstract

The structure-activity relationship (QSAR) model developed discriminate anticancer / non-anticancer drugs using machine learning techniques: artificial neural network (ANN) and support vector machine (SVM). The ANN used here is a feed-forward neural network with a standard back-propagation training algorithm. The performance was compared using 13 shape and electrostatic (Molecular Moments) descriptors. For the complete set of 13 molecular moment descriptors, ANN reveal a superior model (accuracy = 86.7%, Qpred = 76.7%, sensitivity = 0.958, specificity = 0.805 Matthews correlation coefficient (MCC) = 0.74) in comparison to the SVM model (accuracy = 84.28%, Qpred = 74.28%, sensitivity = 0.9285, specificity = 0.7857, MCC = 0.6998). These methods were trained and tested on a non redundant data set of 180 drugs (90 anticancer and 90 non-anticancer). The proposed model can be used for the prediction of the anti-cancer activity of novel classes of compounds enabling a virtual screening of large databases.