Nonlinear QSAR Study of Xanthone and Curcuminoid Derivatives as α-Glucosidase Inhibitors

Department of Chemistry, Faculty of Sciences, University of Djelfa, 17000, AlgeriaReceived November 26, 2012, Accepted March 6, 2013A non linear QSAR model was constructed on a series of 57 xanthone and curcuminoide derivatives as α-glucosidase inhibitors by back-propagation neural network method. The neural network architecture wasoptimized to obtain a three-layer neural network, composed of five descriptors, nine hidden neurons and oneoutput neuron. A good predictive determination coefficient was obtained (R