DC Field | Value | Language |
---|---|---|
dc.contributor.author | Moon, Seokhyun | ko |
dc.contributor.author | Hwang, Sang-Yeon | ko |
dc.contributor.author | Lim, Jaechang | ko |
dc.contributor.author | Kim, Woo Youn | ko |
dc.date.accessioned | 2024-06-19T02:00:18Z | - |
dc.date.available | 2024-06-19T02:00:18Z | - |
dc.date.created | 2024-01-08 | - |
dc.date.created | 2024-01-08 | - |
dc.date.issued | 2024-02 | - |
dc.identifier.citation | DIGITAL DISCOVERY, v.3, no.2, pp.287 - 299 | - |
dc.identifier.issn | 2635-098X | - |
dc.identifier.uri | http://hdl.handle.net/10203/319858 | - |
dc.description.abstract | Prediction of protein-ligand interactions (PLI) plays a crucial role in drug discovery as it guides the identification and optimization of molecules that effectively bind to target proteins. Despite remarkable advances in deep learning-based PLI prediction, the development of a versatile model capable of accurately scoring binding affinity and conducting efficient virtual screening remains a challenge. The main obstacle in achieving this lies in the scarcity of experimental structure-affinity data, which limits the generalization ability of existing models. Here, we propose a viable solution to address this challenge by introducing a novel data augmentation strategy combined with a physics-informed graph neural network. The model showed significant improvements in both scoring and screening, outperforming task-specific deep learning models in various tests including derivative benchmarks, and notably achieving results comparable to the state-of-the-art performance based on distance likelihood learning. This demonstrates the potential of this approach to drug discovery. PIGNet2, a versatile protein-ligand interaction prediction model that performs well in both molecule identification and optimization, demonstrates its potential in early-stage drug discovery. | - |
dc.language | English | - |
dc.publisher | ROYAL SOC CHEMISTRY | - |
dc.title | PIGNet2: a versatile deep learning-based protein-ligand interaction prediction model for binding affinity scoring and virtual screening | - |
dc.type | Article | - |
dc.identifier.wosid | 001122574100001 | - |
dc.identifier.scopusid | 2-s2.0-85179616699 | - |
dc.type.rims | ART | - |
dc.citation.volume | 3 | - |
dc.citation.issue | 2 | - |
dc.citation.beginningpage | 287 | - |
dc.citation.endingpage | 299 | - |
dc.citation.publicationname | DIGITAL DISCOVERY | - |
dc.identifier.doi | 10.1039/d3dd00149k | - |
dc.contributor.localauthor | Kim, Woo Youn | - |
dc.contributor.nonIdAuthor | Hwang, Sang-Yeon | - |
dc.contributor.nonIdAuthor | Lim, Jaechang | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordPlus | FORCE-FIELD | - |
dc.subject.keywordPlus | CD-HIT | - |
dc.subject.keywordPlus | DOCKING | - |
dc.subject.keywordPlus | OPTIMIZATION | - |
dc.subject.keywordPlus | DISCOVERY | - |
dc.subject.keywordPlus | ACCURATE | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.