Matches in SemOpenAlex for { <https://semopenalex.org/work/W2052450063> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2052450063 endingPage "1063" @default.
- W2052450063 startingPage "1049" @default.
- W2052450063 abstract "We have developed a hybrid system to predict the secondary structures (α-helix, β-sheet and coil) of proteins and achieved 66.4% accuracy, with correlation coefficients of Ccoil = 0.429, Cα = 0.470 and Cβ = 0.387. This system contains three subsystems (“experts”): a neural network module, a statistical module and a memory-based reasoning module. First, the three experts independently learn the mapping between amino acid sequences and secondary structures from the known protein structures, then a Combiner learns to combine automatically the outputs of the experts to make final predictions. The hybrid system was tested with 107 protein structures through k-way cross-validation. Its performance was better than each expert and all previously reported methods with greater than 0.99 statistical significance. It was observed that for 20% of the residues, all three experts produced the same but wrong predictions. This may suggest an upper bound on the accuracy of secondary structure predictions based on local information from the currently available protein structures, and indicate places where non-local interactions may play a dominant role in conformation. For 64% of the residues, at least two experts were the same and correct, which shows that the Combiner performed better than majority vote. For 77 % of the residues, at least one expert was correct, thus there may still be room for improvement in this hybrid approach. Rigorous evaluation procedures were used in testing the hybrid system, and statistical significance measures were developed in analyzing the differences among different methods. When measured in terms of the number of secondary structures (rather than the number of residues) that were predicted correctly, the prediction produced by the hybrid system was also better than those of individual experts." @default.
- W2052450063 created "2016-06-24" @default.
- W2052450063 creator A5008116509 @default.
- W2052450063 creator A5034304825 @default.
- W2052450063 creator A5077622597 @default.
- W2052450063 date "1992-06-01" @default.
- W2052450063 modified "2023-10-11" @default.
- W2052450063 title "Hybrid system for protein secondary structure prediction" @default.
- W2052450063 cites W1506812273 @default.
- W2052450063 cites W1981550496 @default.
- W2052450063 cites W1994322185 @default.
- W2052450063 cites W2008708467 @default.
- W2052450063 cites W2016339621 @default.
- W2052450063 cites W2035066314 @default.
- W2052450063 cites W2049695588 @default.
- W2052450063 cites W2061500593 @default.
- W2052450063 cites W2072325285 @default.
- W2052450063 cites W2073739993 @default.
- W2052450063 cites W2081359387 @default.
- W2052450063 cites W2089052645 @default.
- W2052450063 cites W2095450147 @default.
- W2052450063 cites W2119423166 @default.
- W2052450063 cites W2123333780 @default.
- W2052450063 doi "https://doi.org/10.1016/0022-2836(92)90104-r" @default.
- W2052450063 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/1613789" @default.
- W2052450063 hasPublicationYear "1992" @default.
- W2052450063 type Work @default.
- W2052450063 sameAs 2052450063 @default.
- W2052450063 citedByCount "211" @default.
- W2052450063 countsByYear W20524500632012 @default.
- W2052450063 countsByYear W20524500632013 @default.
- W2052450063 countsByYear W20524500632014 @default.
- W2052450063 countsByYear W20524500632016 @default.
- W2052450063 countsByYear W20524500632017 @default.
- W2052450063 countsByYear W20524500632018 @default.
- W2052450063 countsByYear W20524500632019 @default.
- W2052450063 countsByYear W20524500632020 @default.
- W2052450063 countsByYear W20524500632022 @default.
- W2052450063 crossrefType "journal-article" @default.
- W2052450063 hasAuthorship W2052450063A5008116509 @default.
- W2052450063 hasAuthorship W2052450063A5034304825 @default.
- W2052450063 hasAuthorship W2052450063A5077622597 @default.
- W2052450063 hasConcept C105795698 @default.
- W2052450063 hasConcept C119857082 @default.
- W2052450063 hasConcept C124101348 @default.
- W2052450063 hasConcept C154945302 @default.
- W2052450063 hasConcept C2986587452 @default.
- W2052450063 hasConcept C33923547 @default.
- W2052450063 hasConcept C41008148 @default.
- W2052450063 hasConcept C50644808 @default.
- W2052450063 hasConcept C55493867 @default.
- W2052450063 hasConcept C62614982 @default.
- W2052450063 hasConcept C86803240 @default.
- W2052450063 hasConceptScore W2052450063C105795698 @default.
- W2052450063 hasConceptScore W2052450063C119857082 @default.
- W2052450063 hasConceptScore W2052450063C124101348 @default.
- W2052450063 hasConceptScore W2052450063C154945302 @default.
- W2052450063 hasConceptScore W2052450063C2986587452 @default.
- W2052450063 hasConceptScore W2052450063C33923547 @default.
- W2052450063 hasConceptScore W2052450063C41008148 @default.
- W2052450063 hasConceptScore W2052450063C50644808 @default.
- W2052450063 hasConceptScore W2052450063C55493867 @default.
- W2052450063 hasConceptScore W2052450063C62614982 @default.
- W2052450063 hasConceptScore W2052450063C86803240 @default.
- W2052450063 hasIssue "4" @default.
- W2052450063 hasLocation W20524500631 @default.
- W2052450063 hasLocation W20524500632 @default.
- W2052450063 hasOpenAccess W2052450063 @default.
- W2052450063 hasPrimaryLocation W20524500631 @default.
- W2052450063 hasRelatedWork W1989946514 @default.
- W2052450063 hasRelatedWork W2020577335 @default.
- W2052450063 hasRelatedWork W2078778136 @default.
- W2052450063 hasRelatedWork W2083563479 @default.
- W2052450063 hasRelatedWork W2117934800 @default.
- W2052450063 hasRelatedWork W2385723709 @default.
- W2052450063 hasRelatedWork W2386796734 @default.
- W2052450063 hasRelatedWork W2472013057 @default.
- W2052450063 hasRelatedWork W2933325505 @default.
- W2052450063 hasRelatedWork W2031291218 @default.
- W2052450063 hasVolume "225" @default.
- W2052450063 isParatext "false" @default.
- W2052450063 isRetracted "false" @default.
- W2052450063 magId "2052450063" @default.
- W2052450063 workType "article" @default.