000001115 001__ 1115
000001115 005__ 20180208210503.0
000001115 0247_ $$2pmid$$apmid:18763837
000001115 0247_ $$2DOI$$a10.1021/ci800178a
000001115 0247_ $$2WOS$$aWOS:000259398500016
000001115 037__ $$aPreJuSER-1115
000001115 041__ $$aeng
000001115 084__ $$2WoS$$aChemistry, Multidisciplinary
000001115 084__ $$2WoS$$aComputer Science, Information Systems
000001115 084__ $$2WoS$$aComputer Science, Interdisciplinary Applications
000001115 1001_ $$0P:(DE-Juel1)132307$$aZimmermann, O.$$b0$$uFZJ
000001115 245__ $$aLOCUSTRA: Accurate Prediction of Local Protein Structure Using a Two-Layer Support Vector Machine Approach
000001115 260__ $$c2008
000001115 300__ $$a1903 - 1908
000001115 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article
000001115 3367_ $$2DataCite$$aOutput Types/Journal article
000001115 3367_ $$00$$2EndNote$$aJournal Article
000001115 3367_ $$2BibTeX$$aARTICLE
000001115 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000001115 3367_ $$2DRIVER$$aarticle
000001115 440_0 $$016561$$aJournal of Chemical Information and Modeling$$v48$$x1549-9596$$y9
000001115 500__ $$aRecord converted from VDB: 12.11.2012
000001115 520__ $$aConstraint generation for 3d structure prediction and structure-based database searches benefit from fine-grained prediction of local structure. In this work, we present LOCUSTRA, a novel scheme for the multiclass prediction of local structure that uses two layers of support vector machines (SVM). Using a 16-letter structural alphabet from de Brevern et al. (Proteins: Struct., Funct., Bioinf. 2000, 41, 271-287), we assess its prediction ability for an independent test set of 222 proteins and compare our method to three-class secondary structure prediction and direct prediction of dihedral angles. The prediction accuracy is Q16=61.0% for the 16 classes of the structural alphabet and Q3=79.2% for a simple mapping to the three secondary classes helix, sheet, and coil. We achieve a mean phi(psi) error of 24.74 degrees (38.35 degrees) and a median RMSDA (root-mean-square deviation of the (dihedral) angles) per protein chain of 52.1 degrees. These results compare favorably with related approaches. The LOCUSTRA web server is freely available to researchers at http://www.fz-juelich.de/nic/cbb/service/service.php.
000001115 536__ $$0G:(DE-Juel1)FUEK411$$2G:(DE-HGF)$$aScientific Computing$$cP41$$x0
000001115 588__ $$aDataset connected to Web of Science, Pubmed
000001115 650_2 $$2MeSH$$aAlgorithms
000001115 650_2 $$2MeSH$$aComputer Simulation
000001115 650_2 $$2MeSH$$aDatabases, Factual
000001115 650_2 $$2MeSH$$aModels, Biological
000001115 650_2 $$2MeSH$$aModels, Molecular
000001115 650_2 $$2MeSH$$aPeptidyl Transferases: chemistry
000001115 650_2 $$2MeSH$$aPredictive Value of Tests
000001115 650_2 $$2MeSH$$aProtein Structure, Tertiary
000001115 650_2 $$2MeSH$$aProteins: chemistry
000001115 650_2 $$2MeSH$$aQuantitative Structure-Activity Relationship
000001115 650_2 $$2MeSH$$aStreptomyces: enzymology
000001115 650_7 $$00$$2NLM Chemicals$$aProteins
000001115 650_7 $$0EC 2.3.2.12$$2NLM Chemicals$$aPeptidyl Transferases
000001115 650_7 $$2WoSType$$aJ
000001115 7001_ $$0P:(DE-Juel1)VDB46160$$aHansmann, U. H. E.$$b1$$uFZJ
000001115 773__ $$0PERI:(DE-600)1491237-5$$a10.1021/ci800178a$$gVol. 48, p. 1903 - 1908$$p1903 - 1908$$q48<1903 - 1908$$tJournal of Chemical Information and Modeling$$v48$$x1549-9596$$y2008
000001115 8567_ $$uhttp://dx.doi.org/10.1021/ci800178a
000001115 909CO $$ooai:juser.fz-juelich.de:1115$$pVDB
000001115 9141_ $$y2008
000001115 9131_ $$0G:(DE-Juel1)FUEK411$$bSchlüsseltechnologien$$kP41$$lSupercomputing$$vScientific Computing$$x0
000001115 9201_ $$0I:(DE-Juel1)NIC-20090406$$gNIC$$kNIC$$lJohn von Neumann - Institut für Computing$$x0
000001115 970__ $$aVDB:(DE-Juel1)102034
000001115 980__ $$aVDB
000001115 980__ $$aConvertedRecord
000001115 980__ $$ajournal
000001115 980__ $$aI:(DE-Juel1)NIC-20090406
000001115 980__ $$aUNRESTRICTED