000856174 001__ 856174
000856174 005__ 20210129235247.0
000856174 0247_ $$2doi$$a10.1021/acs.jctc.8b00690
000856174 0247_ $$2ISSN$$a1549-9618
000856174 0247_ $$2ISSN$$a1549-9626
000856174 0247_ $$2pmid$$apmid:30252470
000856174 0247_ $$2WOS$$aWOS:000450695200057
000856174 0247_ $$2altmetric$$aaltmetric:49424035
000856174 037__ $$aFZJ-2018-05801
000856174 082__ $$a610
000856174 1001_ $$0P:(DE-HGF)0$$aMulnaes, Daniel$$b0
000856174 245__ $$aTopScore: Using Deep Neural Networks and Large Diverse Data Sets for Accurate Protein Model Quality Assessment
000856174 260__ $$aWashington, DC$$c2018
000856174 3367_ $$2DRIVER$$aarticle
000856174 3367_ $$2DataCite$$aOutput Types/Journal article
000856174 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1544596783_28837
000856174 3367_ $$2BibTeX$$aARTICLE
000856174 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000856174 3367_ $$00$$2EndNote$$aJournal Article
000856174 520__ $$aThe value of protein models obtained with automated protein structure prediction depends primarily on their accuracy. Protein model quality assessment is thus critical to select the model that can best answer biologically relevant questions from an ensemble of predictions. However, despite many advances in the field, different methods capture different types of errors, begging the question of which method to use. We introduce TopScore, a meta Model Quality Assessment Program (meta-MQAP) that uses deep neural networks to combine scores from 15 different primary predictors to predict accurate residue-wise and whole-protein error estimates. The predictions on six large independent data sets are highly correlated to superposition-independent errors in the model, achieving a Pearson’s Rall2 of 0.93 and 0.78 for whole-protein and residue-wise error predictions, respectively. This is a significant improvement over any of the investigated primary MQAPs, demonstrating that much can be gained by optimally combining different methods and using different and very large data sets.
000856174 536__ $$0G:(DE-HGF)POF3-511$$a511 - Computational Science and Mathematical Methods (POF3-511)$$cPOF3-511$$fPOF III$$x0
000856174 536__ $$0G:(DE-HGF)POF3-551$$a551 - Functional Macromolecules and Complexes (POF3-551)$$cPOF3-551$$fPOF III$$x1
000856174 536__ $$0G:(DE-Juel1)hkf7_20170501$$aForschergruppe Gohlke (hkf7_20170501)$$chkf7_20170501$$fForschergruppe Gohlke$$x2
000856174 588__ $$aDataset connected to CrossRef
000856174 7001_ $$0P:(DE-Juel1)172663$$aGohlke, Holger$$b1$$eCorresponding author
000856174 773__ $$0PERI:(DE-600)2166976-4$$a10.1021/acs.jctc.8b00690$$gp. acs.jctc.8b00690$$n11$$p6117–6126$$tJournal of chemical theory and computation$$v14$$x1549-9626$$y2018
000856174 8564_ $$uhttps://juser.fz-juelich.de/record/856174/files/acs.jctc.8b00690.pdf$$yRestricted
000856174 8564_ $$uhttps://juser.fz-juelich.de/record/856174/files/acs.jctc.8b00690.pdf?subformat=pdfa$$xpdfa$$yRestricted
000856174 909CO $$ooai:juser.fz-juelich.de:856174$$pVDB
000856174 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172663$$aForschungszentrum Jülich$$b1$$kFZJ
000856174 9131_ $$0G:(DE-HGF)POF3-511$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vComputational Science and Mathematical Methods$$x0
000856174 9131_ $$0G:(DE-HGF)POF3-551$$1G:(DE-HGF)POF3-550$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lBioSoft – Fundamentals for future Technologies in the fields of Soft Matter and Life Sciences$$vFunctional Macromolecules and Complexes$$x1
000856174 9141_ $$y2018
000856174 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bJ CHEM THEORY COMPUT : 2017
000856174 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000856174 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000856174 915__ $$0StatID:(DE-HGF)0310$$2StatID$$aDBCoverage$$bNCBI Molecular Biology Database
000856174 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List
000856174 915__ $$0StatID:(DE-HGF)0110$$2StatID$$aWoS$$bScience Citation Index
000856174 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000856174 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000856174 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences
000856174 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bJ CHEM THEORY COMPUT : 2017
000856174 920__ $$lyes
000856174 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000856174 9201_ $$0I:(DE-Juel1)ICS-6-20110106$$kICS-6$$lStrukturbiochemie $$x1
000856174 9201_ $$0I:(DE-Juel1)NIC-20090406$$kNIC$$lJohn von Neumann - Institut für Computing$$x2
000856174 980__ $$ajournal
000856174 980__ $$aVDB
000856174 980__ $$aI:(DE-Juel1)JSC-20090406
000856174 980__ $$aI:(DE-Juel1)ICS-6-20110106
000856174 980__ $$aI:(DE-Juel1)NIC-20090406
000856174 980__ $$aUNRESTRICTED
000856174 981__ $$aI:(DE-Juel1)IBI-7-20200312