A machine learning approach for the prediction of protein surface loop flexibility

UMMS Affiliation

Department of Biochemistry and Molecular Pharmacology; Program in Bioinformatics and Integrative Biology

Publication Date


Document Type



*Artificial Intelligence; Protein Structure, Secondary; Proteins


Bioinformatics | Computational Biology | Systems Biology


Proteins often undergo conformational changes when binding to each other. A major fraction of backbone conformational changes involves motion on the protein surface, particularly in loops. Accounting for the motion of protein surface loops represents a challenge for protein-protein docking algorithms. A first step in addressing this challenge is to distinguish protein surface loops that are likely to undergo backbone conformational changes upon protein-protein binding (mobile loops) from those that are not (stationary loops). In this study, we developed a machine learning strategy based on support vector machines (SVMs). Our SVM uses three features of loop residues in the unbound protein structures-Ramachandran angles, crystallographic B-factors, and relative accessible surface area-to distinguish mobile loops from stationary ones. This method yields an average prediction accuracy of 75.3% compared with a random prediction accuracy of 50%, and an average of 0.79 area under the receiver operating characteristic (ROC) curve using cross-validation. Testing the method on an independent dataset, we obtained a prediction accuracy of 70.5%. Finally, we applied the method to 11 complexes that involve members from the Ras superfamily and achieved prediction accuracy of 92.8% for the Ras superfamily proteins and 74.4% for their binding partners.

DOI of Published Version



Proteins. 2011 Aug;79(8):2467-74. doi: 10.1002/prot.23070. Epub 2011 Jun 1. Link to article on publisher's site

Journal/Book/Conference Title


Related Resources

Link to Article in PubMed

PubMed ID