CNS Drug Discovery & Therapy (Track)

Application of Support Vector Machine for Prediction of the CaMKIId Inhibitor of aryl Derivatives

Eslam Pourbasheer
Center of Excellence in Electrochemistry, Faculty of Chemistry, University of Tehran, P. O. Box 14155-6455, Tehran, Iran

Abstract:

The multiple linear regressions (MLR) and support vector machine (SVM) were used to develop the quantitative structure activity relationship (QSAR) models of aryl derivatives as inhibitors of CaMKIIδ. Various kinds of molecular descriptors were calculated to represent the molecular structures of compounds, such as: constitutional, topological, geometrical, electrostatic and quantum-chemical descriptors. Principal component analysis (PCA) was used to select the training set. The models were validated using Leave-One-Out (LOO) cross-validation, external test set and Y- randomization test. Comparison of results of the two methods showed that SVM was a very accurate approach in predicting the CaMKIIδ inhibitory of aryl derivatives. This indicates that SVM can be used as an alternative modeling tool for quantitative structure activity relationship studies. Moreover, it should facilitate the design of new drugs and development of new CaMKIIδ inhibitors.