Improved Prediction of Protein Ligand-Binding Sites Using Random Forests
Abstract:This article describes a novel method for predicting ligand-binding sites of proteins. This method uses only 8 structural properties as input vector to train 9 random forest classifiers which are combined to predict binding residues. These predicted binding residues are then clustered into some predicted ligand-binding sites. According to our measurement criterion, this method achieved a success rate of 0.914 in the bound state dataset and 0.800 in the unbound state dataset, which are better than three other methods: Q-SiteFinder, SCREEN and Morita's method. It indicates that the proposed method here is successful for predicting ligand-binding sites.
Keywords: ASA; Feature vector for residue; Morita's method; NMR; PSAIA; Q-SiteFinder; SCREEN; Solvation energy; X-ray crystallography; hydrophobicity; jackknife test; ligand-binding site prediction; patch-based residue characterization; pocket depth; random forests
Document Type: Research Article
Publication date: December 1, 2011
- Protein & Peptide Letters publishes short papers in all important aspects of protein and peptide research, including structural studies, recombinant expression, function, synthesis, enzymology, immunology, molecular modeling, drug design etc. Manuscripts must have a significant element of novelty, timeliness and urgency that merit rapid publication. Reports of crystallisation, and preliminary structure determinations of biologically important proteins are acceptable. Purely theoretical papers are also acceptable provided they provide new insight into the principles of protein/peptide structure and function.