Prediction of chiral chromatographic separations using combined multivariate regression and neural networks

A new method for the prediction and description of enantioselective separations on HPLC chiral stationary phases (CSPs) is described. Based on the combination of multivariate regression and neural networks, the method was successfully applied to the separation of a series of 29 aromatic acids and amides, chromatographed on three amylosic CSPs. Combinations of charge transfer, electrostatic, lipophilic, and dipole interactions, identified by multivariate regression, were found to describe retention and enantioselectivity, with highly predictive models being generated by the training of back-propagation neural networks.