A thin‐layer chromatography (TLC) experiment was used to find a new structural descriptor based on empirical data, which can be useful for prediction of high performance liquid chromatography (HPLC) retention of peptides. The optimization of TLC separation of a series of twenty naturally occurring amino acids was performed and, finally, the mobile phase comprising water and ethanol 95° (20:80 v/v) appeared to be an optimal one. The designed TLC experiment enabled obtaining different values of retardation factor, R f , and to further calculate R M values for individual amino acids. The sum of calculated R M values, corresponding to the individual amino acids in the appropriate peptide, and four other descriptors calculated from the peptides' structural formulas using molecular modeling methods, were used in quantitative structure retention relationships (QSRR) analysis to predict retention times of a series of structurally diversified peptides chromatographed in a reversed phase HPLC system.