Home > Publications database > LOCUSTRA: Accurate Prediction of Local Protein Structure Using a Two-Layer Support Vector Machine Approach > print

001     1115
005     20180208210503.0
024 7 _ |2 pmid
|a pmid:18763837
024 7 _ |2 DOI
|a 10.1021/ci800178a
024 7 _ |2 WOS
|a WOS:000259398500016
037 _ _ |a PreJuSER-1115
041 _ _ |a eng
084 _ _ |2 WoS
|a Chemistry, Multidisciplinary
084 _ _ |2 WoS
|a Computer Science, Information Systems
084 _ _ |2 WoS
|a Computer Science, Interdisciplinary Applications
100 1 _ |0 P:(DE-Juel1)132307
|a Zimmermann, O.
|b 0
|u FZJ
245 _ _ |a LOCUSTRA: Accurate Prediction of Local Protein Structure Using a Two-Layer Support Vector Machine Approach
260 _ _ |c 2008
300 _ _ |a 1903 - 1908
336 7 _ |0 PUB:(DE-HGF)16
|2 PUB:(DE-HGF)
|a Journal Article
336 7 _ |2 DataCite
|a Output Types/Journal article
336 7 _ |0 0
|2 EndNote
|a Journal Article
336 7 _ |2 BibTeX
|a ARTICLE
336 7 _ |2 ORCID
|a JOURNAL_ARTICLE
336 7 _ |2 DRIVER
|a article
440 _ 0 |0 16561
|a Journal of Chemical Information and Modeling
|v 48
|x 1549-9596
|y 9
500 _ _ |a Record converted from VDB: 12.11.2012
520 _ _ |a Constraint 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.
536 _ _ |0 G:(DE-Juel1)FUEK411
|2 G:(DE-HGF)
|a Scientific Computing
|c P41
|x 0
588 _ _ |a Dataset connected to Web of Science, Pubmed
650 _ 2 |2 MeSH
|a Algorithms
650 _ 2 |2 MeSH
|a Computer Simulation
650 _ 2 |2 MeSH
|a Databases, Factual
650 _ 2 |2 MeSH
|a Models, Biological
650 _ 2 |2 MeSH
|a Models, Molecular
650 _ 2 |2 MeSH
|a Peptidyl Transferases: chemistry
650 _ 2 |2 MeSH
|a Predictive Value of Tests
650 _ 2 |2 MeSH
|a Protein Structure, Tertiary
650 _ 2 |2 MeSH
|a Proteins: chemistry
650 _ 2 |2 MeSH
|a Quantitative Structure-Activity Relationship
650 _ 2 |2 MeSH
|a Streptomyces: enzymology
650 _ 7 |0 0
|2 NLM Chemicals
|a Proteins
650 _ 7 |0 EC 2.3.2.12
|2 NLM Chemicals
|a Peptidyl Transferases
650 _ 7 |2 WoSType
|a J
700 1 _ |0 P:(DE-Juel1)VDB46160
|a Hansmann, U. H. E.
|b 1
|u FZJ
773 _ _ |0 PERI:(DE-600)1491237-5
|a 10.1021/ci800178a
|g Vol. 48, p. 1903 - 1908
|p 1903 - 1908
|q 48<1903 - 1908
|t Journal of Chemical Information and Modeling
|v 48
|x 1549-9596
|y 2008
856 7 _ |u http://dx.doi.org/10.1021/ci800178a
909 C O |o oai:juser.fz-juelich.de:1115
|p VDB
913 1 _ |0 G:(DE-Juel1)FUEK411
|b Schlüsseltechnologien
|k P41
|l Supercomputing
|v Scientific Computing
|x 0
914 1 _ |y 2008
920 1 _ |0 I:(DE-Juel1)NIC-20090406
|g NIC
|k NIC
|l John von Neumann - Institut für Computing
|x 0
970 _ _ |a VDB:(DE-Juel1)102034
980 _ _ |a VDB
980 _ _ |a ConvertedRecord
980 _ _ |a journal
980 _ _ |a I:(DE-Juel1)NIC-20090406
980 _ _ |a UNRESTRICTED

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21