Predicting And Modeling Of Anti-Aggregation Activities For Some Piperazinyl-Glutamate-Pyridine/Primidin Derivatives P2Y12 Antagonists Through Multidimensional QSAR And Molecular Docking

Abstract

In this work hybrid molecular docking quantitative structure activity relationship (QSAR) methodology is used to modeling and predict the inhibitory activities of some piperazinyl-glutamate-pyridine/primidin derivatives toward P2Y12 protein. Data set consist of inhibitory activities (as IC₅₀ in µM^-1) of 52 piperazinyl-glutamate-pyridine/primidin derivatives, which can be used in treatment of thrombocythemia. After docking of these derivative’s to P2Y12 protein, the most stable structure of ligands is chosen and frozen, to calculate molecular descriptors. In the next step prescreening of descriptors are done and stepwise feature selection methods was used to select the most relevel descriptors. Then the selected descriptors are used to developing multiple linear regression (MLR) and support vector machine (SVM) models. The statistical parameters of these model are; the outperformed SVM r=0.84, 0.87; RMSE=0.42, 0.82 for training and test sets, respectively, compared to r=0.72, 0.82, RMSE=0.72, 0.77 for MLR). Comparison between these valves of and other statistics reveals the superiority of SVM over MLR models. In the next step virtual screening based on the lead derivatives is outperformed to identify new efficient candidate based on ADME properties and docking studies.