By applying a three-dimensional holographic vector of the atomic interaction field (3D-HoVAIF) to express the structure of three classical peptide drugs, quantitative structure activity relationship (QSAR) models are built by the multiple linear regression. The accuracy of the proposed model is illustrated using Q LOO 2 (cross-validation) and r 2 (test set validation). Moreover, the r m 2 metrics is used to further refine the predictive ability of the developed QSAR models. The results show that 3D-HoVAIF, due to the high predictive ability, offers a useful alternative to the costly and time-consuming experiments determining the bioactivity of peptide drugs.