QSAR study of isonicotinamides derivatives as Alzheimr's disease inhibitors using PLS-R and ANN methods

Abstract

The field of artificial intelligence such as artificial neural networks (ANNs) and partial least squares regression (PLS-R) are the methods of choice for quantitative structure activity relationship (QSAR) correlation. Here, we have applied 2D-QSAR approach on a series of isonicotinamides derivatives as Glycogen synthase kinase-3 beta (GSK-3β) inhibitors using PLS-R and ANN methods. The models were generated and validated using a data set of 35 molecules. The best predictive models by PLS-R and ANN gave highly significant square correlation coefficient (r2) values of 0.84 and 0.90 respectively. Based on the results of 2D-QSAR models, GCUT_PEOE_2, h_emd_C, PEOE_VSA_FPPOS, and SlogP_VSA6 are the main descriptors in controlling the activity of the molecules. The developed models could be used to design the new isonicotinamides derivatives with high inhibitory activity against GSK-3β enzyme.