Enables the accurate prediction of residue burial states, which should greatly facilitate protein structure prediction and evaluation. ACRF is a high-order conditional random field model that considers burial states of all residues in a protein simultaneously. It exploits not only the correlation among adjacent residues but also the correlation among long-range residues. ACRF also outperforms the logistic regression model, suggesting the importance of incorporating correlations into the prediction model.
Key Lab of Intelligent Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China; School of Computer Science, University of Chinese Academy of Sciences, Beijing, China; Institute of Theoretical Physics, Chinese Academy of Sciences, Beijing, China
ACRF funding source(s)
This work was supported by the National Basic Research Program of China (2012CB316502) and the National Natural Science Foundation of China under grants 11175224, 11121403, 31270834, 61272318, and 31671369.