E-state modeling of HIV-1 protease inhibitor binding independent of 3D information.

Data for HIV-1 protease inhibitors (in vitro enzyme binding) were used as a training set to develop a QSAR model based on topological descriptors, including two hydrogen E-state indices, along with a molecular connectivity chi and a kappa shape index. A statistically satisfactory four-variable model was obtained for the 32 compounds in the training set, r2 = 0.86, s = 0.60, and q2 = 0.79, without the use of information from 3D geometries or detailed interaction energy calculations. The model was validated through the prediction of 15 compounds in the external test set, yielding a mean absolute error, MAE, = 0.82. Structure interpretation is given for each variable to assist in the design of new compounds. Structure features emphasized in the model include hydrogen bond donating ability, nonpolar groups, skeletal branching, and molecular globularity. On the basis of these statistical criteria, this E-state model may be considered useful for prediction of pIC50 values for new HIV-1 protease inhibitors.