Learning Probabilistic Models of Hydrogen Bond Stability from Molecular Dynamics Simulation Trajectories

Handle URI:
http://hdl.handle.net/10754/594706
Title:
Learning Probabilistic Models of Hydrogen Bond Stability from Molecular Dynamics Simulation Trajectories
Authors:
Chikalov, Igor; Yao, Peggy; Moshkov, Mikhail ( 0000-0003-0085-9483 ) ; Latombe, Jean-Claude
Abstract:
Hydrogen bonds (H-bonds) play a key role in both the formation and stabilization of protein structures. H-bonds involving atoms from residues that are close to each other in the main-chain sequence stabilize secondary structure elements. H-bonds between atoms from distant residues stabilize a protein’s tertiary structure. However, H-bonds greatly vary in stability. They form and break while a protein deforms. For instance, the transition of a protein from a nonfunctional to a functional state may require some H-bonds to break and others to form. The intrinsic strength of an individual H-bond has been studied from an energetic viewpoint, but energy alone may not be a very good predictor. Other local interactions may reinforce (or weaken) an H-bond. This paper describes inductive learning methods to train a protein-independent probabilistic model of H-bond stability from molecular dynamics (MD) simulation trajectories. The training data describes H-bond occurrences at successive times along these trajectories by the values of attributes called predictors. A trained model is constructed in the form of a regression tree in which each non-leaf node is a Boolean test (split) on a predictor. Each occurrence of an H-bond maps to a path in this tree from the root to a leaf node. Its predicted stability is associated with the leaf node. Experimental results demonstrate that such models can predict H-bond stability quite well. In particular, their performance is roughly 20% better than that of models based on H-bond energy alone. In addition, they can accurately identify a large fraction of the least stable H-bonds in a given conformation. The paper discusses several extensions that may yield further improvements.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
Learning Probabilistic Models of Hydrogen Bond Stability from Molecular Dynamics Simulation Trajectories 2011, 03 (03):155 Journal of Intelligent Learning Systems and Applications
Publisher:
Scientific Research Publishing, Inc,
Journal:
Journal of Intelligent Learning Systems and Applications
Issue Date:
2-Apr-2011
DOI:
10.4236/jilsa.2011.33017
Type:
Article
ISSN:
2150-8402; 2150-8410
Additional Links:
http://www.scirp.org/journal/PaperDownload.aspx?DOI=10.4236/jilsa.2011.33017
Appears in Collections:
Articles; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorChikalov, Igoren
dc.contributor.authorYao, Peggyen
dc.contributor.authorMoshkov, Mikhailen
dc.contributor.authorLatombe, Jean-Claudeen
dc.date.accessioned2016-01-24T07:34:23Zen
dc.date.available2016-01-24T07:34:23Zen
dc.date.issued2011-04-02en
dc.identifier.citationLearning Probabilistic Models of Hydrogen Bond Stability from Molecular Dynamics Simulation Trajectories 2011, 03 (03):155 Journal of Intelligent Learning Systems and Applicationsen
dc.identifier.issn2150-8402en
dc.identifier.issn2150-8410en
dc.identifier.doi10.4236/jilsa.2011.33017en
dc.identifier.urihttp://hdl.handle.net/10754/594706en
dc.description.abstractHydrogen bonds (H-bonds) play a key role in both the formation and stabilization of protein structures. H-bonds involving atoms from residues that are close to each other in the main-chain sequence stabilize secondary structure elements. H-bonds between atoms from distant residues stabilize a protein’s tertiary structure. However, H-bonds greatly vary in stability. They form and break while a protein deforms. For instance, the transition of a protein from a nonfunctional to a functional state may require some H-bonds to break and others to form. The intrinsic strength of an individual H-bond has been studied from an energetic viewpoint, but energy alone may not be a very good predictor. Other local interactions may reinforce (or weaken) an H-bond. This paper describes inductive learning methods to train a protein-independent probabilistic model of H-bond stability from molecular dynamics (MD) simulation trajectories. The training data describes H-bond occurrences at successive times along these trajectories by the values of attributes called predictors. A trained model is constructed in the form of a regression tree in which each non-leaf node is a Boolean test (split) on a predictor. Each occurrence of an H-bond maps to a path in this tree from the root to a leaf node. Its predicted stability is associated with the leaf node. Experimental results demonstrate that such models can predict H-bond stability quite well. In particular, their performance is roughly 20% better than that of models based on H-bond energy alone. In addition, they can accurately identify a large fraction of the least stable H-bonds in a given conformation. The paper discusses several extensions that may yield further improvements.en
dc.language.isoenen
dc.publisherScientific Research Publishing, Inc,en
dc.relation.urlhttp://www.scirp.org/journal/PaperDownload.aspx?DOI=10.4236/jilsa.2011.33017en
dc.rightsArchived with thanks to Journal of Intelligent Learning Systems and Applicationsen
dc.subjectMolecular Dynamicsen
dc.subjectMachine Learningen
dc.subjectRegression Treeen
dc.titleLearning Probabilistic Models of Hydrogen Bond Stability from Molecular Dynamics Simulation Trajectoriesen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalJournal of Intelligent Learning Systems and Applicationsen
dc.eprint.versionPublisher's Version/PDFen
dc.contributor.institutionBio-Medical Informatics, Stanford University, Stanford, USAen
dc.contributor.institutionComputer Science Department, Stanford University, Stanford, USAen
dc.contributor.affiliationKing Abdullah University of Science and Technology (KAUST)en
kaust.authorChikalov, Igoren
kaust.authorMoshkov, Mikhailen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.