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

Published

Journal Article

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.

Full Text

Duke Authors

Cited Authors

  • Hwang, H; Vreven, T; Whitfield, TW; Wiehe, K; Weng, Z

Published Date

  • August 2011

Published In

Volume / Issue

  • 79 / 8

Start / End Page

  • 2467 - 2474

PubMed ID

  • 21633973

Pubmed Central ID

  • 21633973

Electronic International Standard Serial Number (EISSN)

  • 1097-0134

Digital Object Identifier (DOI)

  • 10.1002/prot.23070

Language

  • eng

Conference Location

  • United States