Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226188399> ?p ?o ?g. }
- W4226188399 endingPage "966" @default.
- W4226188399 startingPage "955" @default.
- W4226188399 abstract "Protein secondary structure (SS) prediction is a classic problem of computational biology and is widely used in structural characterization and to infer homology. While most SS predictors have been trained on thousands of sequences, a previous approach had developed a compact model of training proteins that used a C-Alpha, C-Beta Side Chain (CABS)-algorithm derived energy based feature representation. Here, the previous approach is extended to Deep Belief Networks (DBN). Deep learning methods are notorious for requiring large datasets and there is a wide consensus that training deep models from scratch on small datasets, works poorly. By contrast, we demonstrate a simple DBN architecture containing a single hidden layer, trained only on the CB513 dataset. Testing on an independent set of G Switch proteins improved the Q 3 score of the previous compact model by almost 3%. The findings are further confirmed by comparison to several deep learning models which are trained on thousands of proteins. Finally, the DBN performance is also compared with Position Specific Scoring Matrix (PSSM)-profile based feature representation. The importance of (i) structural information in protein feature representation and (ii) complementary small dataset learning approaches for detection of structural fold switching are demonstrated." @default.
- W4226188399 created "2022-05-05" @default.
- W4226188399 creator A5027208445 @default.
- W4226188399 creator A5037891222 @default.
- W4226188399 creator A5081411825 @default.
- W4226188399 date "2023-03-01" @default.
- W4226188399 modified "2023-10-16" @default.
- W4226188399 title "Empirical Study of Protein Feature Representation on Deep Belief Networks Trained With Small Data for Secondary Structure Prediction" @default.
- W4226188399 cites W1491040459 @default.
- W4226188399 cites W1499450468 @default.
- W4226188399 cites W1596947964 @default.
- W4226188399 cites W1606410455 @default.
- W4226188399 cites W1967195968 @default.
- W4226188399 cites W1972434016 @default.
- W4226188399 cites W1976005460 @default.
- W4226188399 cites W1981132436 @default.
- W4226188399 cites W2006318414 @default.
- W4226188399 cites W2008708467 @default.
- W4226188399 cites W2008807736 @default.
- W4226188399 cites W2018207366 @default.
- W4226188399 cites W2032188785 @default.
- W4226188399 cites W2032757954 @default.
- W4226188399 cites W2041369927 @default.
- W4226188399 cites W2042042193 @default.
- W4226188399 cites W2042160423 @default.
- W4226188399 cites W2046192291 @default.
- W4226188399 cites W2051210555 @default.
- W4226188399 cites W2059136964 @default.
- W4226188399 cites W2074231493 @default.
- W4226188399 cites W2085277871 @default.
- W4226188399 cites W2095450147 @default.
- W4226188399 cites W2096344315 @default.
- W4226188399 cites W2096495474 @default.
- W4226188399 cites W2099254366 @default.
- W4226188399 cites W2100495367 @default.
- W4226188399 cites W2100697211 @default.
- W4226188399 cites W2104710719 @default.
- W4226188399 cites W2104972430 @default.
- W4226188399 cites W2107903949 @default.
- W4226188399 cites W2108067237 @default.
- W4226188399 cites W2114107538 @default.
- W4226188399 cites W2116064496 @default.
- W4226188399 cites W2126165751 @default.
- W4226188399 cites W2128577591 @default.
- W4226188399 cites W2134782652 @default.
- W4226188399 cites W2139582206 @default.
- W4226188399 cites W2141915739 @default.
- W4226188399 cites W2142678478 @default.
- W4226188399 cites W2145023212 @default.
- W4226188399 cites W2147209844 @default.
- W4226188399 cites W2153153865 @default.
- W4226188399 cites W2153187042 @default.
- W4226188399 cites W2157437977 @default.
- W4226188399 cites W2158714788 @default.
- W4226188399 cites W2161072217 @default.
- W4226188399 cites W2171559274 @default.
- W4226188399 cites W2409640637 @default.
- W4226188399 cites W2518750490 @default.
- W4226188399 cites W2607268717 @default.
- W4226188399 cites W2887029338 @default.
- W4226188399 cites W2918335507 @default.
- W4226188399 cites W2963640180 @default.
- W4226188399 cites W2969644707 @default.
- W4226188399 cites W3010290582 @default.
- W4226188399 cites W3021559842 @default.
- W4226188399 cites W3027554922 @default.
- W4226188399 cites W3083777350 @default.
- W4226188399 doi "https://doi.org/10.1109/tcbb.2022.3168676" @default.
- W4226188399 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35439138" @default.
- W4226188399 hasPublicationYear "2023" @default.
- W4226188399 type Work @default.
- W4226188399 citedByCount "0" @default.
- W4226188399 crossrefType "journal-article" @default.
- W4226188399 hasAuthorship W4226188399A5027208445 @default.
- W4226188399 hasAuthorship W4226188399A5037891222 @default.
- W4226188399 hasAuthorship W4226188399A5081411825 @default.
- W4226188399 hasBestOaLocation W42261883991 @default.
- W4226188399 hasConcept C108583219 @default.
- W4226188399 hasConcept C119857082 @default.
- W4226188399 hasConcept C138885662 @default.
- W4226188399 hasConcept C153180895 @default.
- W4226188399 hasConcept C154945302 @default.
- W4226188399 hasConcept C17744445 @default.
- W4226188399 hasConcept C199539241 @default.
- W4226188399 hasConcept C2776359362 @default.
- W4226188399 hasConcept C2776401178 @default.
- W4226188399 hasConcept C41008148 @default.
- W4226188399 hasConcept C41895202 @default.
- W4226188399 hasConcept C55493867 @default.
- W4226188399 hasConcept C59404180 @default.
- W4226188399 hasConcept C62614982 @default.
- W4226188399 hasConcept C86803240 @default.
- W4226188399 hasConcept C94625758 @default.
- W4226188399 hasConcept C97385483 @default.
- W4226188399 hasConceptScore W4226188399C108583219 @default.
- W4226188399 hasConceptScore W4226188399C119857082 @default.
- W4226188399 hasConceptScore W4226188399C138885662 @default.
- W4226188399 hasConceptScore W4226188399C153180895 @default.