Show simple item record

dc.contributor.authorChen, Peng
dc.date.accessioned2015-08-04T07:11:46Z
dc.date.available2015-08-04T07:11:46Z
dc.date.issued2013
dc.identifier.isbn9783642396779
dc.identifier.issn18650929
dc.identifier.doi10.1007/978-3-642-39678-6_35
dc.identifier.urihttp://hdl.handle.net/10754/564671
dc.description.abstractProtein-ligand binding is an important mechanism for some proteins to perform their functions, and those binding sites are the residues of proteins that physically bind to ligands. So far, the state-of-the-art methods search for similar, known structures of the query and predict the binding sites based on the solved structures. However, such structural information is not commonly available. In this paper, we propose a sequence-based approach to identify protein-ligand binding residues. Due to the highly imbalanced samples between the ligand-binding sites and non ligand-binding sites, we constructed several balanced data sets, for each of which a random forest (RF)-based classifier was trained. The ensemble of these RF classifiers formed a sequence-based protein-ligand binding site predictor. Experimental results on CASP9 targets demonstrated that our method compared favorably with the state-of-the-art. © Springer-Verlag Berlin Heidelberg 2013.
dc.publisherSpringer Nature
dc.subjectCo-evolutionary encoding
dc.subjectProtein-ligand binding
dc.subjectRandom forest
dc.titleConsensus of sample-balanced classifiers for identifying ligand-binding residue by co-evolutionary physicochemical characteristics of amino acids
dc.typeConference Paper
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.identifier.journalEmerging Intelligent Computing Technology and Applications
dc.conference.date28 July 2013 through 31 July 2013
dc.conference.name9th International Conference on Intelligent Computing, ICIC 2013
dc.conference.locationNanning
kaust.personChen, Peng


This item appears in the following Collection(s)

Show simple item record