Quantitative structure activity relationship for the computational prediction of α-glucosidase inhibitory

Abstract Quantitative structure–activity relationship (QSAR) models are useful in understanding how chemical structure relates to the biological activity of natural and synthetic chemicals and for design of newer and better therapeutics. In the present study, 57 xanthone and curcuminoid derivatives were evaluated as α-glucosidase inhibitors, expressed by the cytotoxicity of these compounds (IC 50 ). Based on these data, different molecular descriptors were used to solve this problem. A linear QSAR model was developed using Multiple Linear Regression technique, while Genetic Algorithm was adopted for selecting the most appropriate descriptors. The predictive activity of the model was evaluated by means of external validation set and the Y -randomization technique, and its structural chemical domain has been verified by the leverage approach. It was able to describe more than 85.7% of the variance in the experimental activity.