A COMPARATIVE 2D QSAR ANALYSIS OF LEVETIRACETAM& ITS ANALOGS:-THE INHIBITOR OF GLIOBLASTOMA, BY DIFFERENT STATISTICAL TECHNIQUES: MLR, PLS, SVM, ANN

Abstract

Levetiracetam is a Antiepileptic drugs (AEDs) that act as an inhibitor of Glioblastoma. AEDs may have an impact in modulating O(6)-methylguanine-DNA methyltransferase (MGMT), a DNA repair protein that has an important role in tumour cell resistance to alkylating agents. Levetiracetam (LEV) is the most potent MGMT inhibitor among several AEDs with diverse MGMT regulatory actions. A QSAR study has been performed by taking 64 analogs of Levetiracetam. Various 2D Constitutional, Geometrical and Chemical Feature Distance Matrix (CFDM) descriptors were generated by using Molegro Data Modeller V2.5.0 tool. The consequence was calculated for each type of descriptors by taking the Andrews coefficient as dependent variable. Multiple regression analysis was performed by Minitab 16 tool. Good correlation R-sq value 0.93 was obtained from the CFDM descriptors in comparison to 2D Constitutional, Geometrical descriptor calculation. The results were also further verified by using PLS (Partial Least Square), SVM (Support vector machines) and ANN (artificial neural networks) based calculation. The results obtained were consistent with ANN statistics and the ANN based method show R-sq value as 0.93 in case of CFDM descriptor which was observed to be the highest among above three methods of analysis. The results obtained with these models suggest, for this particular drug CFDM descriptors modulates strongly the activity rather than 2D Constitutional & Geometrical Descriptor.