Consensus of sample-balanced classifiers for identifying ligand-binding residue by co-evolutionary physicochemical characteristics of amino acids

Handle URI:
http://hdl.handle.net/10754/564671
Title:
Consensus of sample-balanced classifiers for identifying ligand-binding residue by co-evolutionary physicochemical characteristics of amino acids
Authors:
Chen, Peng
Abstract:
Protein-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.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
Springer Science + Business Media
Journal:
Emerging Intelligent Computing Technology and Applications
Conference/Event name:
9th International Conference on Intelligent Computing, ICIC 2013
Issue Date:
2013
DOI:
10.1007/978-3-642-39678-6_35
Type:
Conference Paper
ISSN:
18650929
ISBN:
9783642396779
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorChen, Pengen
dc.date.accessioned2015-08-04T07:11:46Zen
dc.date.available2015-08-04T07:11:46Zen
dc.date.issued2013en
dc.identifier.isbn9783642396779en
dc.identifier.issn18650929en
dc.identifier.doi10.1007/978-3-642-39678-6_35en
dc.identifier.urihttp://hdl.handle.net/10754/564671en
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.en
dc.publisherSpringer Science + Business Mediaen
dc.subjectCo-evolutionary encodingen
dc.subjectProtein-ligand bindingen
dc.subjectRandom foresten
dc.titleConsensus of sample-balanced classifiers for identifying ligand-binding residue by co-evolutionary physicochemical characteristics of amino acidsen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalEmerging Intelligent Computing Technology and Applicationsen
dc.conference.date28 July 2013 through 31 July 2013en
dc.conference.name9th International Conference on Intelligent Computing, ICIC 2013en
dc.conference.locationNanningen
kaust.authorChen, Pengen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.