Application of Monte Carlo and QSAR Techniques of Several Methotrexate Derivatives as Anticancer Drugs

This research presents quantitative structure-activity relationship (QSAR) of half maximal inhibitory concentration (IC50 ) values of 31 different Methotrxate derivatives by employing Multiple linear regression (MLR) and artificial neural networks (ANN), simulated annealing algorithm (SA) and genetic algorithm(GA). Furthermore, CORAL software was used for multiple probability simulation of the studied derivatives. The obtained results from MLR-MLR, MLR-SA, SA-ANN, MLR-GA and GA-ANN approaches were compared and GA-ANN combination showed the best performance according to its correlation coefficient (R2) and mean sum square errors (RMSE). From Monte Carlo simulations, it was found that the presence of double bond, the presence of nitrogen and oxygen, the absence of sulphur and phosphorus and connected sp2 carbon to the ring, are the most important molecular features that affect the biological activity of the drug. It was concluded that the simultaneous application of GA-ANN and Monte Carlo methods can provide a more comprehensive understanding of the relationship between a drug's physicochemical, structural, or theoretical molecular descriptors and its biological activity, leading to accelerate the development of new drugs.