EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MPBind: a multitask protein binding site predictor using protein language models and equivariant GNNs

Yanli Wang iD, Frimpong Boadu, Jianlin Cheng iD

Bioinformatics · 01.11.2025 · 41 (11)

DOI: 10.1093/bioinformatics/btaf589 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 24.10.2025. Verfasst von Yanli Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211, United States. Hauptthemen laut MEDLINE: Proteins, Computational Biology, Software. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, Department of Energy, USA National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Proteins interact with a variety of molecules, including other proteins, DNAs, RNAs, ligands, ions, and lipids. These interactions play a crucial role in cellular communication, metabolic regulation, gene regulation, and structural integrity, making proteins fundamental to nearly all biological functions. Accurately predicting protein interaction (binding) sites is essential for understanding protein interaction and function. Results In this work, we introduce MPBind, a multitask protein binding site prediction method, which integrates protein language models (PLMs) that can extract structural and functional information from sequences and equivariant graph neural networks (EGNNs) that can effectively capture geometric features of 3D protein structures. Through multitask learning, it can predict binding sites on proteins that interact with five key categories of binding partners: proteins, DNA/RNA, ligands, lipids, and ions. MPBind generalizes across the five molecular classes with state-of-the-art accuracy, achieving AUROC scores of 0.83 and 0.81 for protein–protein and protein–DNA/RNA-binding site prediction, respectively. Moreover, MPBind outperforms both general and task-specific binding site prediction methods, making it a useful, versatile tool for protein binding site prediction. Availability and implementation The source code of MPBind is available at the GitHub repository: https://github.com/jianlin-cheng/MPBind.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsComputational BiologySoftwareBinding SitesProtein BindingNeural Networks, ComputerAlgorithmsRNA

Substanzen

ProteinsRNA

Autor:innen und Institutionen

  • Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211, United States.
  • NextGen Precision Health Institute, University of Missouri, Columbia, MO 65211, United States.

ORCID-Profile: Yanli Wang, Jianlin Cheng

Förderung

  • NIGMS NIH HHS
  • Department of Energy
  • USA National Science Foundation

Zitieren

APA

Wang, Y., Boadu, F., & Cheng, J. (2025). MPBind: a multitask protein binding site predictor using protein language models and equivariant GNNs. Bioinformatics, 41(11). https://doi.org/10.1093/bioinformatics/btaf589

Vancouver

Wang Y, Boadu F, Cheng J. MPBind: a multitask protein binding site predictor using protein language models and equivariant GNNs. Bioinformatics. 2025;41(11). doi:10.1093/bioinformatics/btaf589

BibTeX
@article{Wang2025,
  author = {Wang, Yanli and Boadu, Frimpong and Cheng, Jianlin},
  title = {MPBind: a multitask protein binding site predictor using protein language models and equivariant GNNs},
  journal = {Bioinformatics},
  year = {2025},
  volume = {41},
  number = {11},
  doi = {10.1093/bioinformatics/btaf589}
}
Kostenlos starten →