Structural Characterization and Retention Time Prediction for Essential Oil

The composition of the essential oil from leaves of Cryptocarya mandioccana has been determined by chromatographic fractionation and GC-FID and GC-MS. Genetic algorithm and kernel partial least square (GA-KPLS) technique was used to investigate the correlation between retention time (RT) of essential oil. The applied internal (leave-group-out cross validation (LGO-CV)) and external (test set) validation methods were used for the predictive power of model. Finally a model with a low prediction error and a good correlation coefficient was obtained GA-KPLS. This model was used for the prediction of the RT values of some of compounds which were not used in the modeling procedure.