Identifying Antioxidant Proteins by Using Optimal Dipeptide Compositions.

Antioxidant proteins are a kind of molecules that can terminate cellular and DNA damages caused by free radical intermediates. The use of antioxidant proteins for prevention of diseases has been intensively studied in recent years. Thus, accurate identification of antioxidant proteins is essential for understanding their roles in pharmacology. In this study, a support vector machine-based predictor called AodPred was developed for identifying antioxidant proteins. In this predictor, the sequence was formulated by using the optimal 3-gap dipeptides obtained by using feature selection method. It was observed by jackknife cross-validation test that AodPred can achieve an overall accuracy of 74.79 % in identifying antioxidant proteins. As a user-friendly tool, AodPred is freely accessible at http://lin.uestc.edu.cn/server/AntioxiPred . To maximize the convenience of the vast majority of experimental scientists, a step-by-step guide is provided on how to use the web server to obtain the desired results.