EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unified protein–small molecule graph neural networks for binding site prediction

Jian Wang, Nikolay V Dokholyan iD

Proceedings of the National Academy of Sciences · 10.03.2026 · 123 (10)

DOI: 10.1073/pnas.2524913123 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 03.03.2026. Verfasst von Jian Wang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology and Neuroscience, University of Virginia, School of Medicine, Charlottesville, VA 22903. Hauptthemen laut MEDLINE: Proteins. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCCIH NIH HHS, NIA NIH HHS, National Science Foundation (NSF).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting small molecule binding sites on proteins remains a key challenge in structure-based drug discovery. While AlphaFold3 has transformed protein structure prediction, accurate identification of functional sites such as ligand binding pockets remains a distinct and unresolved problem. Graph neural networks have emerged as promising tools for this task, but most current approaches focus on local structural features and are trained on relatively small datasets, limiting their ability to model long-range protein–ligand interactions. Here, we develop YuelPocket, a graph neural network that addresses these limitations. YuelPocket operates in two complementary modes: residue-level prediction for identifying contact residues and coordinate-level prediction for pinpointing pocket centers. Trained on the large-scale PLINDER dataset, YuelPocket achieves higher success rates in both Distance to Closest Atom and Center-to-Center metrics compared to the state-of-the-art methods. Crucially, YuelPocket demonstrates high robustness on AlphaFold-predicted structures, maintaining high accuracy for targets with deviations from experimental structures. We hope that YuelPocket will serve as a robust framework for accurate binding site identification, enabling reliable functional annotation and structure-guided drug discovery.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsGraph Neural NetworksBinding SitesLigandsProtein BindingProtein ConformationModels, MolecularDrug Discovery

Stichwörter der Autor:innen

druggable site identificationprotein binding siteprotein pocket prediction

Substanzen

ProteinsLigands

Autor:innen und Institutionen

  • Department of Neurology and Neuroscience, University of Virginia, School of Medicine, Charlottesville, VA 22903.
  • Department of Neurology, University of Virginia, School of Medicine, Charlottesville, VA 22903.
  • Departments of Neuroscience, Biomedical Engineering, Pharmacology, Microbiology, Immunology, & Cancer Biology, University of Virginia, School of Medicine, Charlottesville, VA 22903.

ORCID-Profile: Nikolay V Dokholyan

Förderung

  • NCCIH NIH HHS
  • NIA NIH HHS
  • National Science Foundation (NSF)
  • NIGMS NIH HHS
  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Wang, J., & Dokholyan, N. V. (2026). Unified protein–small molecule graph neural networks for binding site prediction. Proceedings of the National Academy of Sciences, 123(10). https://doi.org/10.1073/pnas.2524913123

Vancouver

Wang J, Dokholyan NV. Unified protein–small molecule graph neural networks for binding site prediction. Proceedings of the National Academy of Sciences. 2026;123(10). doi:10.1073/pnas.2524913123

BibTeX
@article{Wang2026,
  author = {Wang, Jian and Dokholyan, Nikolay V},
  title = {Unified protein–small molecule graph neural networks for binding site prediction},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2026},
  volume = {123},
  number = {10},
  doi = {10.1073/pnas.2524913123}
}
Kostenlos starten →