Prediction of basicity constants of various pyridines in aqueous solution using a principal component-genetic algorithm-artificial neural network

摘要

Principal component-genetic algorifhm-multiparameter linear regression(PC-GA-MLR)and principal component-genetic algorithm-artificial neural network(PC-GA-ANN)models were applied for prediction of the basicity constant(pK_b)for various pyridines(91 compounds)dissolved in water at 25°C.A large number of theoretical descriptors were calculated for each compound.The first 54 principal components(PCs)were found to explain more than 99.9% of variances in the original data matrix.From the pool of these PCs,the genetic algorithm was employed for selection of the best set of extracted PCs for PC-MLR and PC-ANN models.The models were generated using eight principal components as variables.For evaluation of the predictive power of the models,pK_b values of 18 compounds in the prediction set were calculated.Mean percentage deviation(MPD)for PC-GA-MLR and PC-GA-ANN models are 21.096 and 3.541.Comparison of the results obtained by the models reveals superiority of the PC-GA-ANN model relative to the PC-GA-MLR model.The improvements are due to the fact that the pK_b of the pyridines demonstrate non-linear correlations with the principal components.