Quantitative structure-retardation factor relationship of protein amino acids in different solvent mixtures for normal-phase thin-layer chromatography

A quantitative predictive/descriptive model was proposed for the retardation factors of protein amino acids in normal-phase thin-layer chromatography. The experimental retardation factors of 126 chromatographic mixtures (21 protein amino acids in different mobile phases) were used as the independent variable. The matrix of dependent variables of the model was built using structural descriptors of amino acids and empirical parameters of solvents of the applied mobile phases. After variable selection, a five-parametr model was proposed for the retardation factor of amino acids, which covered about 84 and 77% variance of data in training and cross-validation, respectively. The correlation coefficient of the external test set was 0.80, which shows the prediction potential of proposed model as well as its good applicability domain that was checked using a standardized residual-leverage plot.