About
Protein thermostability is essential for both research and industrial applications. Up until now, most protein stability prediction tools considered 3D structure information. However, a large number of proteins possess only primary structure. Therefore, this study proposed an effective prediction system, KStable, based on protein sequence. KStable was the first to adopt KStar algorithms with regular-mRMR feature selection. The prediction accuracy of KStable was 0.83 on the Protherm database using 10-fold cross validation. In addition, we also compared KStable with present prediction tools (AUTO-MUTE, i-Mutant, Mupro, PopMuSiC and CUPSAT) and the prediction accuracy and the Matthew's correlation coefficient of KStable were better than others. Therefore, KStable was shown to reduce prediction time while keeping the prediction performance comparable to those that used 3D structure information.