Application of genetic algorithm-kernel partial least square as a novel nonlinear feature selection method: Activity of carbonic anhydrase II inhibitors

This paper introduces the genetic algorithm-kernel partial least square (GA-KPLS), as a novel nonlinear feature selection method. This technique combines genetic algorithms (GAs) as powerful optimization methods with KPLS as a robust nonlinear statistical method for variable selection. This feature selection method is combined with artificial neural network to develop a nonlinear QSAR model for predicting activities of a series of substituted aromatic sulfonamides as carbonic anhydrase II (CA II) inhibitors. Eight simple one- and two-dimensional descriptors were selected by GA-KPLS and considered as inputs for developing artificial neural networks (ANNs). These parameters represent the role of acceptor-donor pair, hydrogen bonding, hydrosolubility and lipophilicity of the active sites and also the size of the inhibitors on inhibitor–isozyme interaction. The accuracy of 8-4-1 networks was illustrated by validation techniques of leave-one-out (LOO) and leave-multiple-out (LMO) cross-validations and Y-randomization. Superiority of this method (GA-KPLS-ANN) over the linear one (MLR) in a previous work and also the GA-PLS-ANN in which a linear feature selection method has been used indicates that the GA-KPLS approach is a powerful method for the variable selection in nonlinear systems.

The sulfonamides represent an important class of biologically active compounds. The aromatic sulfonamides act as carbionic anhydrase inhibitors. A novel nonlinear feature selection method, genetic algorithm-kernel partial least square, was combined with ANN to develop a nonlinear QSAR model for the prediction of activity of a series of substituted aromatic sulfonamides as carbionic anhydrase II inhibitors.Figure optionsDownload as PowerPoint slide