Application of radial basis function neural network and DFT quantum mechanical calculations for the prediction of the activity of 2-biarylethylimidazole derivatives as bombesin receptor subtype-3 (BRS-3) agonists

Abstract

Two quantitative structure–activity relationship (QSAR) models, multiple linear regression (MLR) and radial basis function neural network (RBFNN), have been developed for predicting agonist activity of a series of potent and selective bombesin receptor subtype-3 (BRS-3) containing a biarylethylimidazole pharmacophore by performing density functional theory calculations at the B3LYP/6-311G(d,p) level. The investigated results have demonstrated that the excitation activity of investigated compounds can be reflected by quantum descriptors such as hardness, the total dipole moment, electrophilicity, the highest occupied molecular orbital energy (E HOMO), and the lowest unoccupied molecular orbital energy (E LUMO). The results showed that the pEC50 values calculated by RBFNN model are in good agreement with the experimental data, and the performance of the RBFNN regression model is superior to the MLR-based model. The developed RBFNN model was applied for the prediction of the biological activities of biarylethylimidazole derivatives, which were not in the modeling procedure. The resulted model showed high prediction ability with root mean square error of prediction of 0.224 for RBFNN. Therefore, the QSAR models based on quantum descriptors are reliable in predicting BRS-3 agonist activity for unknown biarylethylimidazole derivatives.