ANN Based Virtual Classification Model for Discriminating Active and Inactive Withanolide E Analogs against Human Breast Cancer Cell Line MCF-7

Abstract

AbstractWithanolides are a group of natural C-28 steroids built on an ergostane skeleton and classified into two major groups according to their structural skeleton: (a) compounds with a beta-oriented side chain and (b) compounds with an alpha-oriented side chain. Withanolide E represents one of the members of the latter group. Classification of active compounds on the basis of pharmacophore against specific cancer cell line poses a serious concern at the primary stage of virtual screening. To overcome this problem we have developed an artificial neural network based virtual screening model for discriminating active and non-active Withanolide-E-like derivatives or analogs against human breast cancer cell line MCF-7. In the present work, a 2D chemical descriptors ensemble pharmacophore has been modelled on the basis of withanolide E structural featured molecules. The ANN structure activity based classification model could be useful for identification of active withanolide analogs as anticancer leads against MCF-7. This model can be used for predicting possible growth inhibitory concentration (logGI50) against breast cancer cell line MCF-7. The virtual screening tool “CanWithaANN” can be accessed at local network of CIMAP.