Quantitative Structure-Activity Relationship Model of Lenalidomide Analogues as TNF-Inhibitors

Abstract

Quantitative structure-activity relationship (QSAR) models between tumor necrosis factor a (TNF-a) inhibition activity of lenalidomide analogues and their chemical structures were established by stepwise multiple linear regression (MLR) and support vector machines (SVM) methods. The molecular descriptors of compounds were calculated based on DFT (density functional theory) method, with the basis set 6-311G. According to the correlation analysis, Kappa1_AM (alpha-modified Kappa shape index of order one), Shadow_XYfrac (area of the molecular shadow in the XY plane) and ELUMO (energy of lowest unoccupied molecular orbital) had positive impact on the inhibition activity. Compared with stepwise MLR model, the SVM model has more powerful predictive capacity with the correlation coefficient Rtest of 0.8000 for the test set.