Machine Learning Approaches for Predicting Protein Complex Similarity

dc.contributor.author Delıbaş, Ayşe Bahar
dc.contributor.author Akbal-Delibas, Bahar
dc.contributor.author Haspel, Nurit
dc.contributor.other Computer Engineering
dc.date.accessioned 2019-06-27T08:01:35Z
dc.date.available 2019-06-27T08:01:35Z
dc.date.issued 2017
dc.department Fakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü en_US
dc.description.abstract Discriminating native-like structures from false positives with high accuracy is one of the biggest challenges in protein-protein docking. While there is an agreement on the existence of a relationship between various favorable intermolecular interactions (e.g. Van der Waals electrostatic and desolvation forces) and the similarity of a conformation to its native structure the precise nature of this relationship is not known. Existing protein-protein docking methods typically formulate this relationship as a weighted sum of selected terms and calibrate their weights by using a training set to evaluate and rank candidate complexes. Despite improvements in the predictive power of recent docking methods producing a large number of false positives by even state-of-the-art methods often leads to failure in predicting the correct binding of many complexes. With the aid of machine learning methods we tested several approaches that not only rank candidate structures relative to each other but also predict how similar each candidate is to the native conformation. We trained a two-layer neural network a multilayer neural network and a network of Restricted Boltzmann Machines against extensive data sets of unbound complexes generated by RosettaDock and PyDock. We validated these methods with a set of refinement candidate structures. We were able to predict the root mean squared deviations (RMSDs) of protein complexes with a very small often less than 1.5 angstrom error margin when trained with structures that have RMSD values of up to 7 angstrom. In our most recent experiments with the protein samples having RMSD values up to 27 angstrom the average prediction error was still relatively small attesting to the potential of our approach in predicting the correct binding of protein-protein complexes. en_US]
dc.identifier.citationcount 0
dc.identifier.doi 10.1089/cmb.2016.0137 en_US
dc.identifier.endpage 51
dc.identifier.issn 1066-5277 en_US
dc.identifier.issn 1557-8666 en_US
dc.identifier.issn 1066-5277
dc.identifier.issn 1557-8666
dc.identifier.issue 1
dc.identifier.pmid 27748625 en_US
dc.identifier.scopus 2-s2.0-85009060594 en_US
dc.identifier.scopusquality Q2
dc.identifier.startpage 40 en_US
dc.identifier.uri https://hdl.handle.net/20.500.12469/412
dc.identifier.uri https://doi.org/10.1089/cmb.2016.0137
dc.identifier.volume 24 en_US
dc.identifier.wos WOS:000391761300005 en_US
dc.identifier.wosquality Q2
dc.institutionauthor Akbal-Delibas, Bahar en_US
dc.language.iso en en_US
dc.publisher Mary Ann Liebert Inc Publ en_US
dc.relation.journal Journal of Computational Biology en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/closedAccess en_US
dc.scopus.citedbyCount 0
dc.subject Machine learning en_US
dc.subject Neural networks en_US
dc.subject Protein docking and refinement en_US
dc.subject RMSD prediction en_US
dc.subject Scoring functions en_US
dc.title Machine Learning Approaches for Predicting Protein Complex Similarity en_US
dc.type Article en_US
dc.wos.citedbyCount 0
dspace.entity.type Publication
relation.isAuthorOfPublication 229c2e99-3e3a-429f-bc29-b66887aeacda
relation.isAuthorOfPublication.latestForDiscovery 229c2e99-3e3a-429f-bc29-b66887aeacda
relation.isOrgUnitOfPublication fd8e65fe-c3b3-4435-9682-6cccb638779c
relation.isOrgUnitOfPublication.latestForDiscovery fd8e65fe-c3b3-4435-9682-6cccb638779c

Files