QSAR Study of 17β-HSD3 Inhibitors by Genetic Algorithm-Support Vector Machine as a Target Receptor for the Treatment of Prostate Cancer

The 17β-HSD3 enzyme plays a key role in treatment of prostate cancer and small inhibitorscan be used to efficiently target it. In the present study, the multiple linear regression (MLR),and support vector machine (SVM) methods were used to interpret the chemical structuralfunctionality against the inhibition activity of some 17β-HSD3inhibitors. Chemical structuralinformation were described through various types of molecular descriptors and genetic algorithm(GA) was applied to decrease the complexity of inhibition pathway to a few relevant moleculardescriptors. Non-linear method (GA-SVM) showed to be better than the linear (GA-MLR)method in terms of the internal and the external prediction accuracy. The SVM model, withhigh statistical significance (R2train = 0.938; R2test = 0.870), was found to be useful for estimatingthe inhibition activity of 17β-HSD3 inhibitors. The models were validated rigorously throughleave-one-out cross-validation and several compounds as external test set. Furthermore, theexternal predictive power of the proposed model was examined by considering modified R2 andconcordance correlation coefficient values, Golbraikh and Tropsha acceptable model criteriaʹs,and an extra evaluation set from an external data set. Applicability domain of the linear modelwas carefully defined using Williams plot. Moreover, Euclidean based applicability domainwas applied to define the chemical structural diversity of the evaluation set and training set.