Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376508699> ?p ?o ?g. }
- W4376508699 endingPage "146" @default.
- W4376508699 startingPage "137" @default.
- W4376508699 abstract "The emergence of deep learning models such as AlphaFold2 has revolutionized the structure prediction of proteins. Nevertheless, much remains unexplored, especially on how we utilize structure models to predict biological properties. Herein, we present a method using features extracted from protein language models (PLMs) to predict the major histocompatibility complex class II (MHC-II) binding affinity of peptides. Specifically, we evaluated a novel transfer learning approach where the backbone of our model was interchanged with architectures designed for image classification tasks. Features extracted from several PLMs (ESM1b, ProtXLNet or ProtT5-XL-UniRef) were passed into image models (EfficientNet v2b0, EfficientNet v2m or ViT-16). The optimal pairing of the PLM and image classifier resulted in the final model TransMHCII, outperforming NetMHCIIpan 3.2 and NetMHCIIpan 4.0-BA on the receiver operating characteristic area under the curve, balanced accuracy and Jaccard scores. The architecture innovation may facilitate the development of other deep learning models for biological problems." @default.
- W4376508699 created "2023-05-15" @default.
- W4376508699 creator A5011861711 @default.
- W4376508699 creator A5024130985 @default.
- W4376508699 creator A5034363587 @default.
- W4376508699 creator A5082923660 @default.
- W4376508699 date "2023-04-01" @default.
- W4376508699 modified "2023-09-25" @default.
- W4376508699 title "TransMHCII: a novel MHC-II binding prediction model built using a protein language model and an image classifier" @default.
- W4376508699 cites W1839525253 @default.
- W4376508699 cites W1849277567 @default.
- W4376508699 cites W1927635887 @default.
- W4376508699 cites W1985437611 @default.
- W4376508699 cites W2043097326 @default.
- W4376508699 cites W2049349724 @default.
- W4376508699 cites W2064574008 @default.
- W4376508699 cites W2069672947 @default.
- W4376508699 cites W2076819852 @default.
- W4376508699 cites W2082108597 @default.
- W4376508699 cites W2094706980 @default.
- W4376508699 cites W2096182040 @default.
- W4376508699 cites W2099500226 @default.
- W4376508699 cites W2109257525 @default.
- W4376508699 cites W2122779464 @default.
- W4376508699 cites W2149350146 @default.
- W4376508699 cites W2165068832 @default.
- W4376508699 cites W2395611524 @default.
- W4376508699 cites W2589139221 @default.
- W4376508699 cites W2779582662 @default.
- W4376508699 cites W2783102765 @default.
- W4376508699 cites W2906544215 @default.
- W4376508699 cites W2948058491 @default.
- W4376508699 cites W2995494055 @default.
- W4376508699 cites W3004696891 @default.
- W4376508699 cites W3024570138 @default.
- W4376508699 cites W3083537918 @default.
- W4376508699 cites W3146944767 @default.
- W4376508699 cites W3166730506 @default.
- W4376508699 cites W3177500196 @default.
- W4376508699 cites W3177828909 @default.
- W4376508699 cites W4206601343 @default.
- W4376508699 cites W4206950245 @default.
- W4376508699 cites W4225726690 @default.
- W4376508699 cites W4225868104 @default.
- W4376508699 cites W4283821679 @default.
- W4376508699 cites W4303645584 @default.
- W4376508699 doi "https://doi.org/10.1093/abt/tbad011" @default.
- W4376508699 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37342671" @default.
- W4376508699 hasPublicationYear "2023" @default.
- W4376508699 type Work @default.
- W4376508699 citedByCount "0" @default.
- W4376508699 crossrefType "journal-article" @default.
- W4376508699 hasAuthorship W4376508699A5011861711 @default.
- W4376508699 hasAuthorship W4376508699A5024130985 @default.
- W4376508699 hasAuthorship W4376508699A5034363587 @default.
- W4376508699 hasAuthorship W4376508699A5082923660 @default.
- W4376508699 hasBestOaLocation W43765086991 @default.
- W4376508699 hasConcept C108583219 @default.
- W4376508699 hasConcept C115961682 @default.
- W4376508699 hasConcept C119857082 @default.
- W4376508699 hasConcept C121332964 @default.
- W4376508699 hasConcept C14103023 @default.
- W4376508699 hasConcept C150899416 @default.
- W4376508699 hasConcept C153180895 @default.
- W4376508699 hasConcept C154945302 @default.
- W4376508699 hasConcept C203519979 @default.
- W4376508699 hasConcept C41008148 @default.
- W4376508699 hasConcept C54101563 @default.
- W4376508699 hasConcept C62520636 @default.
- W4376508699 hasConcept C95623464 @default.
- W4376508699 hasConceptScore W4376508699C108583219 @default.
- W4376508699 hasConceptScore W4376508699C115961682 @default.
- W4376508699 hasConceptScore W4376508699C119857082 @default.
- W4376508699 hasConceptScore W4376508699C121332964 @default.
- W4376508699 hasConceptScore W4376508699C14103023 @default.
- W4376508699 hasConceptScore W4376508699C150899416 @default.
- W4376508699 hasConceptScore W4376508699C153180895 @default.
- W4376508699 hasConceptScore W4376508699C154945302 @default.
- W4376508699 hasConceptScore W4376508699C203519979 @default.
- W4376508699 hasConceptScore W4376508699C41008148 @default.
- W4376508699 hasConceptScore W4376508699C54101563 @default.
- W4376508699 hasConceptScore W4376508699C62520636 @default.
- W4376508699 hasConceptScore W4376508699C95623464 @default.
- W4376508699 hasFunder F4320309117 @default.
- W4376508699 hasIssue "2" @default.
- W4376508699 hasLocation W43765086991 @default.
- W4376508699 hasLocation W43765086992 @default.
- W4376508699 hasOpenAccess W4376508699 @default.
- W4376508699 hasPrimaryLocation W43765086991 @default.
- W4376508699 hasRelatedWork W2441762250 @default.
- W4376508699 hasRelatedWork W2889705046 @default.
- W4376508699 hasRelatedWork W2960456850 @default.
- W4376508699 hasRelatedWork W3192840557 @default.
- W4376508699 hasRelatedWork W4223943233 @default.
- W4376508699 hasRelatedWork W4312200629 @default.
- W4376508699 hasRelatedWork W4317565044 @default.
- W4376508699 hasRelatedWork W4380075502 @default.
- W4376508699 hasRelatedWork W4382286161 @default.