PLS (Partial Least Square) Study for GSK-3 (Glycogen synthase kinase-3) Inhibition by Indirubin Derivatives

GSK-3 (Glycogen synthase kinase-3) is a serine/threonine protein kinase involved in various physiological processes and its inhibitors have been evaluated as promising drug candidates for severe pathologies. In this paper a PLS regression analysis was used, to explore the relationship between field of descriptors (as independent variable) and biological activities (pIC50 as dependent variables). The main purpose of this work is to develop a robust QSAR model for predicting inhibitory activity of the 109 indirubin derivatives and better understanding of structural features of these compounds and their relation with the inhibitory activity using the Dragon descriptors. The statistical qualities of the final model have been assessed by several parameters such as: the cumulative sum of squares of correlation coefficient R-gamma(2)(CUM)=0.872, the cumulative fraction of the total variation of the Y values that can be predicted ford the extracted principal components by cross validation Q(2)(CUM) = 0.804,R-2 supplied by the Golbraikh-Tropsha external validation method and Y-randomization test.