Prediction of chalcone derivative cytotoxicity activity against MCF-7 human breast cancer cell by Monte Carlo method

The anticancer activity of chalcones and their analogs is the most important biological activity of them among their broad spectrum of their biological activity. In this investigation, we performed quantitative structure-activity relationship (QSAR) modeling of the anticancer activity of 134 chalcones and their analogs against MCF-7 human breast cancer cell lines using Monte Carlo method. QSAR models were calculated by CORAL software and optimal descriptors were calculated with SMILES and hydrogen suppressed molecular graph (HSG). The total dataset split into training, invisible training, calibration, and validation set randomly. Analysis of three probes of the Monte Carlo optimization with three random splits was done. Results from three random splits displayed robust, very simple, predictable, and reliable models for training, invisible training, calibration, and validation set with the correlation coefficient (R-2) of 0.8142-0.8244, 0.8244-0.8699, 0.8125-0.8627 and 0.8290-0.8686 respectively. As a result, the obtained models help to identify the hybrid descriptors for the increase and the decrease of anticancer activity of chalcones against MCF-7 human breast cancer cell lines. This simple QSAR model can be used for prediction of log IC50 of numerous chalcone derivatives against breast cancer cell. (C) 2019 Elsevier B.V. All rights reserved.