Prediction of retention time of a variety of volatile organic compounds based on the heuristic method and support vector machine Original Research Article

The support vector machine (SVM) and the heuristic method (HM) were used to develop the non-linear and linear models between the retention time (RT) and five molecular descriptors of 149 volatile organic compounds (VOCs). Descriptors calculated from the molecular structures alone were used to represent the characteristics of compounds. The five molecular descriptors selected by the heuristic method in CODESSA were used as inputs for SVM. The results obtained by SVM were compared with those obtained by the heuristic method. The mean squared errors (MSE) in RT predictions for the whole data set given by HM and SVM were 1.270 and 0.844, respectively, which shows the performance of SVM model is better than that of the HM model. The prediction results are in very good agreement with the experimental values. This paper provided a new and effective method for predicting the chromatography retention index.