Quantitative Structure-Retention Relationship Analysis of Polyphenols in Carob Fibre

2 Abstract: Genetic algorithm and partial least square (GA-PLS) technique was used to investigate the correlation between retention time (RT) and descriptors for 24 polyphenols in carob fibre which obtained by high performance liquid chromatography (HPLC). The applied internal (leave-group-out cross validation (LGO-CV)) and external (test set) validation methods were used for the predictive power of model. It is easy to notice that there was a good prospect for the GA-PLS application in the quantitative structure-retention relationship (QSRR) modeling. This indicates that RT of essential oils possesses some linear characteristics. It can also be used successfully to estimate the RT for new compounds or for other compounds whose experimental values are unknown.