QSAR study of anthranilic acid sulfonamides as inhibitors of methionine aminopeptidase-2 using LS-SVM and GRNN based on principal components

Quantitative relationships between molecular structure and methionine aminopeptidase-2 inhibitory activity of a series of cytotoxic anthranilic acid sulfonamide derivatives were discovered. We have demonstrated the detailed application of two efficient nonlinear methods for evaluation of quantitative structure–activity relationships of the studied compounds. Components produced by principal component analysis as input of developed nonlinear models were used. The performance of the developed models namely PC-GRNN and PC-LS-SVM were tested by several validation methods. The resulted PC-LS-SVM model had a high statistical quality ( R 2 = 0.91 and R CV 2 = 0.81 ) for predicting the cytotoxic activity of the compounds. Comparison between predictability of PC-GRNN and PC-LS-SVM indicates that later method has higher ability to predict the activity of the studied molecules. PC-GRNN and PC-LS-SVM as regression methods were investigated for building quantitative structure–activity relationships for the prediction of inhibitory activity of methionine aminopeptidase-2 antagonists. [Display omitted]