Advances in computational methods to predict the biological activity of compounds.
The support vector machine (SVM) and partial least square (PLS) methods were used to develop quantitative structure activity relationship (QSAR) models to predict the inhibitory activity of non-peptide HIV-1 protease inhibitors. Genetic algorithm (GA) was employed to select variables that lead to the best-fitted models. A comparison between the obtained results using SVM with those of PLS revealed that the SVM model is much better than that of PLS. The root mean square errors of the training set and the test set for SVM model were calculated to be 0.2027, 0.2751, and the coefficients of determination (R(2)) are 0.9800, 0.9355 respectively. Furthermore, the obtained statistical parameter of leave-one-out cross-validation test (Q(2)) on SVM model was 0.9672, which proves the reliability of this model. The results suggest that TE2, Ui, GATS5e, Mor13e, ATS7m, Ss, Mor27e, and RDF035e are the main independent factors contributing to the inhibitory activities of the studied compounds.