FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313626698> ?p ?o ?g. }

• W4313626698 abstract "Abstract Geometric deep learning has recently achieved great success in non-Euclidean domains, and learning on 3D structures of large biomolecules is emerging as a distinct research area. However, its efficacy is largely constrained due to the limited quantity of structural data. Meanwhile, protein language models trained on substantial 1D sequences have shown burgeoning capabilities with scale in a broad range of applications. Nevertheless, no preceding studies consider combining these different protein modalities to promote the representation power of geometric neural networks. To address this gap, we make the foremost step to integrate the knowledge learned by well-trained protein language models into several state-of-the-art geometric networks. Experiments are evaluated on a variety of protein representation learning benchmarks, including protein-protein interface prediction, model quality assessment, protein-protein rigid-body docking, and binding affinity prediction, leading to an overall improvement of 20% over baselines and the new state-of-the-art performance. Strong evidence indicates that the incorporation of protein language models’ knowledge enhances geometric networks’ capacity by a significant margin and can be generalized to complex tasks." @default.
• W4313626698 created "2023-01-07" @default.
• W4313626698 creator A5019398608 @default.
• W4313626698 creator A5040225125 @default.
• W4313626698 creator A5081787254 @default.
• W4313626698 date "2023-01-06" @default.
• W4313626698 modified "2023-10-17" @default.
• W4313626698 title "When Geometric Deep Learning Meets Pretrained Protein Language Models" @default.
• W4313626698 cites W1030883578 @default.
• W4313626698 cites W1512387364 @default.
• W4313626698 cites W1976666280 @default.
• W4313626698 cites W2022322548 @default.
• W4313626698 cites W2059117301 @default.
• W4313626698 cites W2061636126 @default.
• W4313626698 cites W2092285329 @default.
• W4313626698 cites W2099438806 @default.
• W4313626698 cites W2110505462 @default.
• W4313626698 cites W2114162221 @default.
• W4313626698 cites W2114850508 @default.
• W4313626698 cites W2117451312 @default.
• W4313626698 cites W2130479394 @default.
• W4313626698 cites W2153959628 @default.
• W4313626698 cites W2170463736 @default.
• W4313626698 cites W2171641243 @default.
• W4313626698 cites W2301595689 @default.
• W4313626698 cites W2534288757 @default.
• W4313626698 cites W2594183968 @default.
• W4313626698 cites W2594725344 @default.
• W4313626698 cites W2617750324 @default.
• W4313626698 cites W2739455021 @default.
• W4313626698 cites W2739999456 @default.
• W4313626698 cites W2784883284 @default.
• W4313626698 cites W2809216727 @default.
• W4313626698 cites W2902353954 @default.
• W4313626698 cites W2905812122 @default.
• W4313626698 cites W2914721378 @default.
• W4313626698 cites W2919831875 @default.
• W4313626698 cites W2951690294 @default.
• W4313626698 cites W2953524386 @default.
• W4313626698 cites W2969996838 @default.
• W4313626698 cites W2980272550 @default.
• W4313626698 cites W2980789587 @default.
• W4313626698 cites W2992752586 @default.
• W4313626698 cites W3005407385 @default.
• W4313626698 cites W3042283064 @default.
• W4313626698 cites W3088578860 @default.
• W4313626698 cites W3095583226 @default.
• W4313626698 cites W3096561213 @default.
• W4313626698 cites W3104705366 @default.
• W4313626698 cites W3110563343 @default.
• W4313626698 cites W3127980148 @default.
• W4313626698 cites W3144239152 @default.
• W4313626698 cites W3146944767 @default.
• W4313626698 cites W3164107346 @default.
• W4313626698 cites W3177828909 @default.
• W4313626698 cites W3186179742 @default.
• W4313626698 cites W3193271391 @default.
• W4313626698 cites W3199799076 @default.
• W4313626698 cites W3202105508 @default.
• W4313626698 cites W4206367183 @default.
• W4313626698 cites W4210997669 @default.
• W4313626698 cites W4223581484 @default.
• W4313626698 cites W4280489149 @default.
• W4313626698 cites W4281626490 @default.
• W4313626698 cites W4290877452 @default.
• W4313626698 doi "https://doi.org/10.1101/2023.01.05.522958" @default.
• W4313626698 hasPublicationYear "2023" @default.
• W4313626698 type Work @default.
• W4313626698 citedByCount "0" @default.
• W4313626698 crossrefType "posted-content" @default.
• W4313626698 hasAuthorship W4313626698A5019398608 @default.
• W4313626698 hasAuthorship W4313626698A5040225125 @default.
• W4313626698 hasAuthorship W4313626698A5081787254 @default.
• W4313626698 hasBestOaLocation W43136266981 @default.
• W4313626698 hasConcept C108583219 @default.
• W4313626698 hasConcept C119857082 @default.
• W4313626698 hasConcept C136764020 @default.
• W4313626698 hasConcept C137293760 @default.
• W4313626698 hasConcept C154945302 @default.
• W4313626698 hasConcept C17744445 @default.
• W4313626698 hasConcept C199539241 @default.
• W4313626698 hasConcept C2776359362 @default.
• W4313626698 hasConcept C34947359 @default.
• W4313626698 hasConcept C41008148 @default.
• W4313626698 hasConcept C49777392 @default.
• W4313626698 hasConcept C50644808 @default.
• W4313626698 hasConcept C774472 @default.
• W4313626698 hasConcept C94625758 @default.
• W4313626698 hasConceptScore W4313626698C108583219 @default.
• W4313626698 hasConceptScore W4313626698C119857082 @default.
• W4313626698 hasConceptScore W4313626698C136764020 @default.
• W4313626698 hasConceptScore W4313626698C137293760 @default.
• W4313626698 hasConceptScore W4313626698C154945302 @default.
• W4313626698 hasConceptScore W4313626698C17744445 @default.
• W4313626698 hasConceptScore W4313626698C199539241 @default.
• W4313626698 hasConceptScore W4313626698C2776359362 @default.
• W4313626698 hasConceptScore W4313626698C34947359 @default.
• W4313626698 hasConceptScore W4313626698C41008148 @default.
• W4313626698 hasConceptScore W4313626698C49777392 @default.
• W4313626698 hasConceptScore W4313626698C50644808 @default.

• next