EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamic-GLEP: a dynamics-informed deep learning framework for ligand efficacy prediction in representative Class A GPCRs

Zhiyi Chen, Yongxin Hao, Yuhong Su, Hans Ågren, Mingan Chen, Zhehuan Fan, Duanhua Cao iD, Jiacheng Xiong, Wei Zhang, Jin Liu, Xutong Li iD, Mingyue Zheng iD und 3 weitere

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag049 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Zhiyi Chen und 14 weiteren Autor:innen. Beteiligte Einrichtung: School of Life Sciences, Nanjing University, 163 Xianlin Avenue, Nanjing 210023, China. Hauptthemen laut MEDLINE: Deep Learning, Molecular Dynamics Simulation, Receptors, G-Protein-Coupled. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Academic Infrastructure for Supercomputing in Sweden (NAISS) for offering computational resources at Alvis, Shanghai Municipal Science and Technology Major Project, Strategic Priority Research Program of the Chinese Academy of Sciences, Shanghai Sailing Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

G protein–coupled receptors (GPCRs) represent the largest membrane protein family and remain central targets in drug discovery. Ligand efficacy reflects the ability to modulate receptor conformational states and extends beyond binding affinity to underpin functional selectivity. However, most computational approaches still emphasize affinity prediction, with limited capacity to capture the conformational dynamics driving efficacy. Here, we introduce Dynamic-GLEP, a structure- and mechanism-aware framework that integrates molecular dynamics (MD)–derived conformational ensembles with transfer learning on equivariant graph neural networks. By constructing multi-conformation receptor–ligand complexes and fine-tuning the EquiScore model, Dynamic-GLEP identifies conformation-dependent interaction features to distinguish agonists from nonagonists. Applied to the 5-HT1A receptor, the framework achieved an area under the curve (AUC) of 0.74 in cross-validation and 0.71 on an external Food and Drug Administration (FDA)-related dataset. Comparative analyses showed that Holo-based models are advantageous for scaffold optimization, whereas Apo-derived ensembles provided greater adaptability to chemically diverse ligands. Furthermore, extension to the adenosine A2A receptor yielded high performance (AUC > 0.85), underscoring the method’s robustness and transferability under data-scarce conditions. Collectively, these results highlight Dynamic-GLEP as a reliable and interpretable platform for ligand efficacy prediction in Class A GPCRs, with broad potential to support virtual screening, candidate prioritization, and mechanism-driven drug design.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMolecular Dynamics SimulationReceptors, G-Protein-CoupledLigandsHumansGraph Neural NetworksProtein ConformationDrug DiscoveryReceptor, Serotonin, 5-HT1A

Stichwörter der Autor:innen

GPCR ligand efficacyconformational ensemblesdeep learningmolecular dynamicsstructure-based drug designtransfer learning

Substanzen

LigandsReceptors, G-Protein-CoupledReceptor, Serotonin, 5-HT1A

Autor:innen und Institutionen

  • School of Life Sciences, Nanjing University, 163 Xianlin Avenue, Nanjing 210023, China.
  • Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China.
  • Division of Life Science and Medicine, University of Science and Technology of China, 443 Huangshan Road, Hefei 230026, Anhui, China.
  • Lingang Laboratory, 2380 Hechuan Road, Shanghai 200031, China.
  • Division of X-ray Photon Science, Department of Physics and Astronomy, Uppsala University, Box 516, SE-751 20, Uppsala, Sweden.
  • School of Physical Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Shanghai 201210, China.

ORCID-Profile: Duanhua Cao, Xutong Li, Mingyue Zheng, Dingyan Wang, Dan Teng

Förderung

  • National Academic Infrastructure for Supercomputing in Sweden (NAISS) for offering computational resources at Alvis
  • Shanghai Municipal Science and Technology Major Project, Strategic Priority Research Program of the Chinese Academy of Sciences
  • Shanghai Sailing Program
  • Fund of Youth Innovation Promotion Association
  • National Key Research and Development Program of China
  • SIMM-SHUTCM Traditional Chinese Medicine Innovation Joint Research Program
  • China Postdoctoral Science Foundation
  • National Natural Science Foundation of China

Zitieren

APA

Chen, Z., Hao, Y., Su, Y., Ågren, H., Chen, M., Fan, Z., Cao, D., Xiong, J., Zhang, W., Liu, J., Li, X., Zheng, M., Cheng, X., Wang, D., & Teng, D. (2026). Dynamic-GLEP: a dynamics-informed deep learning framework for ligand efficacy prediction in representative Class A GPCRs. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag049

Vancouver

Chen Z, Hao Y, Su Y, Ågren H, Chen M, Fan Z, et al. Dynamic-GLEP: a dynamics-informed deep learning framework for ligand efficacy prediction in representative Class A GPCRs. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag049

BibTeX
@article{Chen2026,
  author = {Chen, Zhiyi and Hao, Yongxin and Su, Yuhong and Ågren, Hans and Chen, Mingan and Fan, Zhehuan and Cao, Duanhua and Xiong, Jiacheng and Zhang, Wei and Liu, Jin and Li, Xutong and Zheng, Mingyue and Cheng, Xi and Wang, Dingyan and Teng, Dan},
  title = {Dynamic-GLEP: a dynamics-informed deep learning framework for ligand efficacy prediction in representative Class A GPCRs},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag049}
}
Kostenlos starten →