Quantitative Structure–Retention Relationship Modeling of Morphine and Its Derivatives on OV-1 Column in Gas–Liquid Chromatography Using Genetic Algorithm

In this paper, a back propagation artificial neural network (BP-ANN) was used for quantitative structure–retention relationship (QSRR) modeling of retention time ( t R ) of 57 morphine and its derivatives. The molecular descriptors were calculated for each compound. By applying a genetic algorithm, the most relevant descriptors were selected to build the QSRR model. The selected descriptors were: Hosoya Index, kappa1, and most negative potential. The prediction results from the BP-ANN were in good agreement with the experimental values. The optimal QSRR model was developed based on a 3-3-1 artificial neural network architecture using molecular descriptors calculated from molecular structure alone. The root-mean-square error (RMSE) and squared correlation coefficient ( R 2 ) for the ANN model were 0.3996 and 0.9559 for the training set (42 molecules) and 0.6052 and 0.9540 for the prediction set (15 molecules), respectively.