Author :
Wong, Ginny Y. ; Leung, Frank H. F. ; Ling, Sai Ho
Author_Institution :
Dept. of Electron. & Inf. Eng., Hong Kong Polytech. Univ., Hung Hom, China
Abstract :
Identification of protein-ligand binding site is an important task in structure-based drug design and docking algorithms. In the past two decades, different approaches have been developed to predict the binding site, such as the geometric, energetic, and sequence-based methods. When scores are calculated from these methods, the algorithm for doing classification becomes very important and can affect the prediction results greatly. In this paper, the support vector machine (SVM) is used to cluster the pockets that are most likely to bind ligands with the attributes of geometric characteristics, interaction potential, offset from protein, conservation score, and properties surrounding the pockets. Our approach is compared to LIGSITE, LIGSITEcsc, SURFNET, Fpocket, PocketFinder, Q-SiteFinder, ConCavity, and MetaPocket on the data set LigASite and 198 drug-target protein complexes. The results show that our approach improves the success rate from 60 to 80 percent at AUC measure and from 61 to 66 percent at top 1 prediction. Our method also provides more comprehensive results than the others.
Keywords :
biochemistry; bioinformatics; drugs; molecular biophysics; proteins; support vector machines; F pocket; LIGSITE; Q-site finder; SURFNET; SVM; data set LigASite; docking algorithms; drug-target protein complexes; energetic methods; geometric characteristics; geometric methods; meta pocket; pocket finder; protein-ligand binding site; sequence-based methods; structure-based drug design; support vector machine; Bioinformatics; Computational biology; Diseases; Drugs; Proteins; Support vector machines; Three-dimensional displays; Bioinformatics; binding sites predication; protein-ligand binding sites; structure-based drug design; support vector machine (SVM);