The major economic alternative way for prediction of anti oxidation activity of tripeptide analogue is the use of quantitative structure-activity relationships (QSARs). In this work, a group of 23 tripeptides was modeled for their antioxidation activity using interpretable structural descriptors three-dimensional (3D) and two-dimensional (2D) descriptors. Quantitative relationships between structural descriptors and antioxidation activities (QSARs) were constructed by incorporating the multivariate regression analysis with Genetic algorithm. Among models developed using different chemometric tools, the best model based on both internal and external validation. The important molecular descriptors xch6, xvch5, SaaN, SdO, Hother, Dipole, SpcPolarizability and Volume were selected by the forward and backward technique with the genetic algorithm. The best 4-variable model QSARlinear including SaaN, Hother, SdO and Dipole was derived from those techniques. The quality of this model QSARlinear was exhibited by values R2fibless of 97.8524, R2tesl of 92.784, standard error of estimation SE of 0.0355 and F-stat of 148.0816. For nonlinear model QSAR.,eurah the architecture type I(4)-HL(4)-O(1) with R2fibless of 99.4293 was conStructed by the present predictors in linear model QSARlinear. The antioxidation activities of tripeptides resulting from models QSARlinear and QSARneural were depicted in values MARE, percent of31.0854 and 27.9484, respectively.