Ab initio and QSAR study of several etoposides as anticancer drugs: Solvent effect

Abstract

Quantitative structure-activity relationship (QSAR) of twenty-five different Etoposides derivatives was estimated by means of multiple linear regression (MLR), artificial neural network (ANN), simulated annealing (SA) and genetic algorithm (GA) techniques. The geometric compounds were selected as optimized samples using Gaussian 09W at B3LYP/6-31g. A high predictive ability was observed for the MLR-MLR, MLR-ANN, SA-ANN, MLR-GA and GA-ANN models, with the root mean sum square errors (RMSE) of 0.6265, 0.223, 0.195, 0.161 and 0.061 in gas phase and 0.5864, 0.226, 0.061, 0.106, and 0.0320 in the solvent phase, respectively (N = 25). The results obtained using the GA-ANN method indicated that the activity of derivatives of Etoposide depends on several parameters including Mor 14u, EEig12d, VEA1 and ICR descriptors in gas phase and RDF065p, Qxxe, ISH, RDF 050v and GATS6p descriptors in the solvent phase. Finally, the comparison of the quality of ANN with different MLR methods showed that ANN has a better predictive ability.