LAUSR

As an indispensable component of various living organisms, the antioxidant proteins have been studied for anti-aging and prevention of various diseases, such as altitude sickness, coronary heart disease, and even cancer. However, the traditional experimental methods for identifying the antioxidant proteins are very expensive and time-consuming. Thus, to address the challenge, a new predictor, named ANOX, was developed in this study. Features of multi-source heterogeneous, such as Frequency matrix features (FRE), Amino acid and dipeptide composition (AADP), Evolutionary difference formula features (EEDP), K-separated bigrams (KSB), and PSI-PRED secondary structure (PRED), were extracted to generate the original feature space. To find the optimized feature subset, the Max-Relevance-Max-Distance (MRMD) algorithm was implemented for feature ranking and our model received the best performance with the top 1,170 features. Rigorous tests were performed to evaluate the performance of ANOX, and the results showed that ANOX achieved a major improvement in the accuracy of the prediction of the antioxidant proteins (AUC:0.930 and 0.935 using 5-fold cross-validation or the jackknife test) compared to the state-of-the-art computational approaches AOPs-SVM (AUC:0.869 and 0.885). The dataset used in this study and the source code of ANOX is all available at https://github.com/NWAFU-LiuLab/ANOX.