Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386702974> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W4386702974 endingPage "17" @default.
- W4386702974 startingPage "1" @default.
- W4386702974 abstract "Drug discovery often relies on the successful prediction of protein-ligand binding affinity. Recent advances have shown great promise in applying graph neural networks (GNNs) for better affinity prediction by learning the representations of protein-ligand complexes. However, existing solutions usually treat protein-ligand complexes as topological graph data, thus the 3D geometry-based biomolecular structural information is not fully utilized. The essential intermolecular interactions with long-range dependencies, including type-wise interactions and molecule-wise interactions, are also neglected in GNN models. To this end, we propose a geometry-aware interactive graph neural network (GIANT) which consists of two components: 3D geometric graph learning network (3DG-NET) and pairwise interactive learning network (PI-NET). Specifically, 3DG-NET iteratively performs the node-edge interaction process to update embeddings of nodes and edges in a unified framework while preserving the 3D geometric factors among atoms, including spatial distance, polar angle and dihedral angle information in 3D space. Moreover, PI-NET is adopted to incorporate both element type-level and molecule-level interactions. Specially, interactive edges are gathered with a subsequent reconstruction loss to reflect the global type-level interactions. Meanwhile, a pairwise attentive pooling scheme is designed to identify the critical interactive atoms for complex representation learning from a semantic view. An exhaustive experimental study on two benchmarks verifies the superiority of GIANT." @default.
- W4386702974 created "2023-09-14" @default.
- W4386702974 creator A5021332177 @default.
- W4386702974 creator A5025292786 @default.
- W4386702974 creator A5027639672 @default.
- W4386702974 creator A5029874240 @default.
- W4386702974 creator A5031546626 @default.
- W4386702974 creator A5038836690 @default.
- W4386702974 creator A5069993888 @default.
- W4386702974 creator A5081254155 @default.
- W4386702974 creator A5089502940 @default.
- W4386702974 date "2023-01-01" @default.
- W4386702974 modified "2023-09-30" @default.
- W4386702974 title "GIANT: Protein-Ligand Binding Affinity Prediction via Geometry-aware Interactive Graph Neural Network" @default.
- W4386702974 doi "https://doi.org/10.1109/tkde.2023.3314502" @default.
- W4386702974 hasPublicationYear "2023" @default.
- W4386702974 type Work @default.
- W4386702974 citedByCount "0" @default.
- W4386702974 crossrefType "journal-article" @default.
- W4386702974 hasAuthorship W4386702974A5021332177 @default.
- W4386702974 hasAuthorship W4386702974A5025292786 @default.
- W4386702974 hasAuthorship W4386702974A5027639672 @default.
- W4386702974 hasAuthorship W4386702974A5029874240 @default.
- W4386702974 hasAuthorship W4386702974A5031546626 @default.
- W4386702974 hasAuthorship W4386702974A5038836690 @default.
- W4386702974 hasAuthorship W4386702974A5069993888 @default.
- W4386702974 hasAuthorship W4386702974A5081254155 @default.
- W4386702974 hasAuthorship W4386702974A5089502940 @default.
- W4386702974 hasConcept C132525143 @default.
- W4386702974 hasConcept C154945302 @default.
- W4386702974 hasConcept C184898388 @default.
- W4386702974 hasConcept C41008148 @default.
- W4386702974 hasConcept C50644808 @default.
- W4386702974 hasConcept C80444323 @default.
- W4386702974 hasConceptScore W4386702974C132525143 @default.
- W4386702974 hasConceptScore W4386702974C154945302 @default.
- W4386702974 hasConceptScore W4386702974C184898388 @default.
- W4386702974 hasConceptScore W4386702974C41008148 @default.
- W4386702974 hasConceptScore W4386702974C50644808 @default.
- W4386702974 hasConceptScore W4386702974C80444323 @default.
- W4386702974 hasLocation W43867029741 @default.
- W4386702974 hasOpenAccess W4386702974 @default.
- W4386702974 hasPrimaryLocation W43867029741 @default.
- W4386702974 hasRelatedWork W2386387936 @default.
- W4386702974 hasRelatedWork W2945365184 @default.
- W4386702974 hasRelatedWork W2971267355 @default.
- W4386702974 hasRelatedWork W3016907268 @default.
- W4386702974 hasRelatedWork W4296188765 @default.
- W4386702974 hasRelatedWork W4312266567 @default.
- W4386702974 hasRelatedWork W4312816440 @default.
- W4386702974 hasRelatedWork W4320341268 @default.
- W4386702974 hasRelatedWork W4383860413 @default.
- W4386702974 hasRelatedWork W1629725936 @default.
- W4386702974 isParatext "false" @default.
- W4386702974 isRetracted "false" @default.
- W4386702974 workType "article" @default.