Allows users to forecast O-G1cNAcylation sites. O-GlcNAcPRED-II compiles four approaches including: (i) a K-means principal component analysis oversampling technique (KPCA) and fuzzy undersampling method (FUS); (ii) eight types of feature to encode each protein peptide; (iii) four types of classifiers, random forest (RF), k-nearest neighbor (KNN), naive Bayesian (NB) and support vector machine (SVM) used as the sub-classifiers of rotation forest and (iv) majority voting.
Department of Mathematics, Dalian Maritime University, Dalian, China; School of Computer Science and Technology, Tianjin University, China
O-GlcNAcPRED funding source(s)
Supported by the Fundamental Research Funds for the Central Universities (number 3132016306, 3132017048 and 3132017085); The National Social Science Foundation of China (Grant No.15CGL031); and the Program for Dalian High Level Talent Innovation Support (Grant No.2015R063).