Aim:To discriminate 32 phenethyl-amines between antagonists and agonists,and predict the activities of these compounds.Methods:The support vectormachine (SVM) is employed to investigate the structure-activity relationship(SAR)/quantitative structure-activity relationship (QSAR) of phenethyl-aminesbased on molecular descriptors.Results:By using the leave-one-out cross-vali-dation (LOOCV) test,1 optimal SAR and 2 optimal QSAR models for agonists andantagonists were attained.The accuracy of prediction for the classification ofphenethyl-amines by using the LOOCV test is 91.67%,and the accuracy of predic-tion for the classification of phenethyl-amines by using the independent test is100%;the results are better than those of the Fisher,the artificial neural network(ANN),and the K-nearest neighbor models for this real world data.The RMSE(root mean square error)of antagonists’ QSAR model is 0.5881,and the RMSE ofagonists’ QSAR model is 0.4779,which are better than those of the multiple linearregression,partial least squares,and ANN models for this real world data.Conclusion:The SVM can be used to investigate the SAR and QSAR of phenethyl-amines and could be a promising tool in the field of SAR/QSAR research. Aim: To discriminate 32 phenethyl-amines between antagonists and agonists, and predict the activities of these compounds. Methods: The support vector machinery (SVM) is employed to investigate the structure-activity relationship (SAR) / quantitative structure-activity relationship (QSAR) of phenethyl-aminesbased on molecular descriptors. Results: By using the leave-one-out cross-vali-dation (LOOCV) test, 1 optimal SAR and 2 optimal QSAR models for agonists and antagonists were attained.The accuracy of prediction for the classification ofphenethyl -amines by using the LOOCV test is 91.67%, and the accuracy of predic-tion for the classification of phenethyl-amines by using the independent test is 100%; the results are better than those of the Fisher, the artificial neural network (ANN) , and the K-nearest neighbor models for this real world data. RMSE (root mean square error) of antagonists ’QSAR model is 0.5881, and the RMSE ofagonists’ QSAR model is 0.4779, which are better than those of the multiple linearr egression, partial least squares, and ANN models for this real world data. Conlusion: The SVM can be used to investigate the SAR and QSAR of phenethyl-amines and could be a promising tool in the field of SAR / QSAR research.