Comparison of Different Ranking Methods in Protein-Ligand Binding Site Prediction

In recent years, although many ligand-binding site prediction methods have been developed, there has still been a great demand to improve the prediction accuracy and compare different prediction algorithms to evaluate their performances. In this work, in order to improve the performance of the protein-ligand binding site prediction method presented in our former study, a comparison of different binding site ranking lists was studied. Four kinds of properties, i.e., pocket size, distance from the protein centroid, sequence conservation and the number of hydrophobic residues, have been chosen as the corresponding ranking criterion respectively. Our studies show that the sequence conservation information helps to rank the real pockets with the most successful accuracy compared to others. At the same time, the pocket size and the distance of binding site from the protein centroid are also found to be helpful. In addition, a multi-view ranking aggregation method, which combines the information among those four properties, was further applied in our study. The results show that a better performance can be achieved by the aggregation of the complementary properties in the prediction of ligand-binding sites.

[1]  David P. Dobkin,et al.  The quickhull algorithm for convex hulls , 1996, TOMS.

[2]  Song Liu,et al.  Protein binding site prediction using an empirical scoring function , 2006, Nucleic acids research.

[3]  Mainak Guharoy,et al.  Conserved residue clusters at protein-protein interfaces and their use in binding site identification , 2010, BMC Bioinformatics.

[4]  D. Levitt,et al.  POCKET: a computer graphics method for identifying and displaying protein cavities and their surrounding amino acids. , 1992, Journal of molecular graphics.

[5]  Geoffrey J. Barton,et al.  The contrasting properties of conservation and correlated phylogeny in protein functional residue prediction , 2015 .

[6]  B. Honig,et al.  On the nature of cavities on protein surfaces: Application to the identification of drug‐binding sites , 2006, Proteins.

[7]  Richard M. Jackson,et al.  Q-SiteFinder: an energy-based method for the prediction of protein-ligand binding sites , 2005, Bioinform..

[8]  R. Abagyan,et al.  Comprehensive identification of "druggable" protein ligand binding sites. , 2004, Genome informatics. International Conference on Genome Informatics.

[9]  Lingle Wang,et al.  Ligand binding to protein-binding pockets with wet and dry regions , 2011, Proceedings of the National Academy of Sciences.

[10]  Pinak Chakrabarti,et al.  Prediction of Active Site Cleft Using Support Vector Machines , 2010, J. Chem. Inf. Model..

[11]  Alexander D. MacKerell,et al.  Binding Response: A Descriptor for Selecting Ligand Binding Site on Protein Surfaces , 2007, J. Chem. Inf. Model..

[12]  Bingding Huang,et al.  MetaPocket: a meta approach to improve protein ligand binding site prediction. , 2009, Omics : a journal of integrative biology.

[13]  B. Matthews.  Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.

[14]  M Hendlich,et al.  LIGSITE: automatic and efficient detection of potential small molecule-binding sites in proteins. , 1997, Journal of molecular graphics & modelling.

[15]  Qi Liu,et al.  Virtual Drug Screen Schema Based on Multiview Similarity Integration and Ranking Aggregation , 2012, J. Chem. Inf. Model..

[16]  Irena Roterman-Konieczna,et al.  Catalytic residues in hydrolases: analysis of methods designed for ligand-binding site prediction , 2010, J. Comput. Aided Mol. Des..

[17]  Ruixin Zhu,et al.  Novel Natural Inhibitors of CYP1A2 Identified by in Silico and in Vitro Screening , 2011, International journal of molecular sciences.

[18]  Vasyl Pihur,et al.  Weighted rank aggregation of cluster validation measures: a Monte Carlo cross-entropy approach , 2007, Bioinform..

[19]  R. Laskowski.  SURFNET: a program for visualizing molecular surfaces, cavities, and intermolecular interactions. , 1995, Journal of molecular graphics.

[20]  Ronald Fagin,et al.  Comparing top k lists , 2003, SODA '03.

[21]  Pieter F. W. Stouten,et al.  Fast prediction and visualization of protein binding pockets with PASS , 2000, J. Comput. Aided Mol. Des..

[22]  R. Wade,et al.  Computational approaches to identifying and characterizing protein binding sites for ligand design , 2009, Journal of molecular recognition : JMR.

[23]  Vincent Le Guilloux,et al.  Fpocket: An open source platform for ligand pocket detection , 2009, BMC Bioinformatics.

[24]  Andreas Prlic,et al.  Sequence analysis , 2003 .

[25]  S. Crennell,et al.  The structures of Salmonella typhimurium LT2 neuraminidase and its complexes with three inhibitors at high resolution. , 1996, Journal of molecular biology.

[26]  G. Schneider,et al.  PocketPicker: analysis of ligand binding-sites with shape descriptors , 2007, Chemistry Central Journal.

[27]  Nir Ben-Tal,et al.  The ConSurf-DB: pre-calculated evolutionary conservation profiles of protein structures , 2008, Nucleic Acids Res..

[28]  Ruixin Zhu,et al.  Investigations on Inhibitors of Hedgehog Signal Pathway: A Quantitative Structure-Activity Relationship Study , 2011, International journal of molecular sciences.

[29]  M. Schroeder,et al.  LIGSITEcsc: predicting ligand binding sites using the Connolly surface and degree of conservation , 2006, BMC Structural Biology.

[30]  Jun Gao,et al.  A new protein-ligand binding sites prediction method based on the integration of protein sequence conservation information , 2011, BMC Bioinformatics.

[31]  Daniel R. Caffrey,et al.  Are protein–protein interfaces more conserved in sequence than the rest of the protein surface? , 2004, Protein science : a publication of the Protein Society.