Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385838908> ?p ?o ?g. }
- W4385838908 abstract "Abstract Predicting protein-ligand binding sites is crucial in studying protein interactions with applications in biotechnology and drug discovery. Two distinct paradigms have emerged for this purpose: sequence-based methods, which leverage protein sequence information, and structure-based methods, which rely on the three-dimensional (3D) structure of the protein. To enhance the state-of-the-art performance in this field, we propose a novel approach combining both paradigms’ strengths. Our hybrid model integrates two recent deep learning architectures: protein language models (pLMs) from the sequence-based paradigm and Graph Neural Networks (GNNs) from the structure-based paradigm. Specifically, we construct a residue-level Graph Attention Network (GAT) model based on the protein’s 3D structure that uses pre-trained pLM embeddings as node features. This integration enables our model to capture both the sequential information encoded in the protein sequence and the structural relationships within the protein. The model has improved state-of-the-art performance on a benchmark dataset over a range of ligands and ligand types. Ablation studies have demonstrated the role of the graph attention mechanism, particularly in densely connected graphs. Moreover, we have shown that as more complex pLMs are employed to represent node features, the relative impact of the GNN architecture diminishes. This observation suggests that, to some extent, the structural information required for accurate binding site prediction is inherently captured by the pLMs themselves. protein-ligand binding sites, binding residues prediction, graph neural networks, graph attention, protein language models, protein embeddings" @default.
- W4385838908 created "2023-08-16" @default.
- W4385838908 creator A5031810686 @default.
- W4385838908 creator A5049617942 @default.
- W4385838908 creator A5069572460 @default.
- W4385838908 date "2023-08-15" @default.
- W4385838908 modified "2023-10-03" @default.
- W4385838908 title "Hybrid protein-ligand binding residue prediction with protein language models: Does the structure matter?" @default.
- W4385838908 cites W1019830208 @default.
- W4385838908 cites W1653739410 @default.
- W4385838908 cites W2018661561 @default.
- W4385838908 cites W2031194866 @default.
- W4385838908 cites W2034937344 @default.
- W4385838908 cites W2043638247 @default.
- W4385838908 cites W2050077513 @default.
- W4385838908 cites W2090649877 @default.
- W4385838908 cites W2091563009 @default.
- W4385838908 cites W2102461176 @default.
- W4385838908 cites W2111608447 @default.
- W4385838908 cites W2126234813 @default.
- W4385838908 cites W2128402268 @default.
- W4385838908 cites W2130479394 @default.
- W4385838908 cites W2140538197 @default.
- W4385838908 cites W2144258433 @default.
- W4385838908 cites W2145023212 @default.
- W4385838908 cites W2168621448 @default.
- W4385838908 cites W2211863317 @default.
- W4385838908 cites W2528395340 @default.
- W4385838908 cites W2617750324 @default.
- W4385838908 cites W2747680751 @default.
- W4385838908 cites W2767813457 @default.
- W4385838908 cites W2911930496 @default.
- W4385838908 cites W2914877211 @default.
- W4385838908 cites W2915583118 @default.
- W4385838908 cites W2919831875 @default.
- W4385838908 cites W2949342052 @default.
- W4385838908 cites W2955341169 @default.
- W4385838908 cites W2990453062 @default.
- W4385838908 cites W2999309192 @default.
- W4385838908 cites W3005669732 @default.
- W4385838908 cites W3007743886 @default.
- W4385838908 cites W3177828909 @default.
- W4385838908 cites W3188579603 @default.
- W4385838908 cites W3195997474 @default.
- W4385838908 cites W3211795435 @default.
- W4385838908 cites W4200348619 @default.
- W4385838908 cites W4213345021 @default.
- W4385838908 cites W4220991280 @default.
- W4385838908 cites W4281993476 @default.
- W4385838908 cites W4283390570 @default.
- W4385838908 cites W4311970063 @default.
- W4385838908 cites W4313527276 @default.
- W4385838908 cites W4317672193 @default.
- W4385838908 cites W4318141876 @default.
- W4385838908 cites W4319071809 @default.
- W4385838908 cites W4319294199 @default.
- W4385838908 cites W4319762935 @default.
- W4385838908 cites W4362663312 @default.
- W4385838908 doi "https://doi.org/10.1101/2023.08.11.553028" @default.
- W4385838908 hasPublicationYear "2023" @default.
- W4385838908 type Work @default.
- W4385838908 citedByCount "0" @default.
- W4385838908 crossrefType "posted-content" @default.
- W4385838908 hasAuthorship W4385838908A5031810686 @default.
- W4385838908 hasAuthorship W4385838908A5049617942 @default.
- W4385838908 hasAuthorship W4385838908A5069572460 @default.
- W4385838908 hasBestOaLocation W43858389081 @default.
- W4385838908 hasConcept C119857082 @default.
- W4385838908 hasConcept C132525143 @default.
- W4385838908 hasConcept C153083717 @default.
- W4385838908 hasConcept C154945302 @default.
- W4385838908 hasConcept C18051474 @default.
- W4385838908 hasConcept C41008148 @default.
- W4385838908 hasConcept C47701112 @default.
- W4385838908 hasConcept C50644808 @default.
- W4385838908 hasConcept C55493867 @default.
- W4385838908 hasConcept C70721500 @default.
- W4385838908 hasConcept C80444323 @default.
- W4385838908 hasConcept C86803240 @default.
- W4385838908 hasConceptScore W4385838908C119857082 @default.
- W4385838908 hasConceptScore W4385838908C132525143 @default.
- W4385838908 hasConceptScore W4385838908C153083717 @default.
- W4385838908 hasConceptScore W4385838908C154945302 @default.
- W4385838908 hasConceptScore W4385838908C18051474 @default.
- W4385838908 hasConceptScore W4385838908C41008148 @default.
- W4385838908 hasConceptScore W4385838908C47701112 @default.
- W4385838908 hasConceptScore W4385838908C50644808 @default.
- W4385838908 hasConceptScore W4385838908C55493867 @default.
- W4385838908 hasConceptScore W4385838908C70721500 @default.
- W4385838908 hasConceptScore W4385838908C80444323 @default.
- W4385838908 hasConceptScore W4385838908C86803240 @default.
- W4385838908 hasLocation W43858389081 @default.
- W4385838908 hasOpenAccess W4385838908 @default.
- W4385838908 hasPrimaryLocation W43858389081 @default.
- W4385838908 hasRelatedWork W1995553782 @default.
- W4385838908 hasRelatedWork W1998728673 @default.
- W4385838908 hasRelatedWork W2020481171 @default.
- W4385838908 hasRelatedWork W2035942032 @default.
- W4385838908 hasRelatedWork W2119378770 @default.
- W4385838908 hasRelatedWork W2154436290 @default.