EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AlloPool is a deep learning framework that infers protein allostery from molecular dynamics simulations

Matthieu Marfoglia, Miguel A Pedraza-Joya, Lucas Guirardel, Aisima Chatzi Souleiman, Patrick Barth iD

PLOS Biology · 2026

DOI: 10.1371/journal.pbio.3004002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Biology, 2026. Verfasst von Matthieu Marfoglia und 4 weiteren Autor:innen. Beteiligte Einrichtung: Interfaculty Institute of Bioengineering, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland. Hauptthemen laut MEDLINE: Molecular Dynamics Simulation, Deep Learning, Proteins. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, EPFL and the Ludwig Institute for Cancer Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in artificial intelligence have transformed protein structure prediction and design. However, protein function is governed not only by static structures but also by the conformational dynamics that allow proteins to access distinct functional states. Predicting these dynamic transitions, central to many biological processes, remains challenging due to the scarcity of high-resolution experimental data, which limits the training of machine-learning models for dynamic and energetic property prediction. Here, we present AlloPool, a graph neural network (GNN)-based framework that interprets molecular dynamics simulations by iteratively pruning residue–residue interactions to uncover minimal, time-resolved interaction networks that govern protein conformational dynamics and structural responses to chemical or mechanical perturbations, collectively known as allostery. By integrating temporal attention with graph aggregation, AlloPool learns evolving interaction graphs from equilibrium and non-equilibrium molecular dynamics simulations, enabling accurate reconstruction of dynamic trajectories and the interaction networks that drive conformational transitions. Validated across diverse dynamic protein systems, including binding domains, mechanosensors, signaling receptors, and enzymes, AlloPool maps allosteric communication pathways, predicts the effects of ligand binding, mechanical forces, and mutations, discovers transient dynamic states and outperforms existing machine-learning approaches in dynamic trajectory reconstruction. This advance provides a general framework for interpreting protein dynamics with broad implications for drug discovery, synthetic biology, and protein engineering.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Molecular Dynamics SimulationDeep LearningProteinsAllosteric RegulationGraph Neural NetworksProtein ConformationProtein Binding

Substanzen

Proteins

Autor:innen und Institutionen

  • Interfaculty Institute of Bioengineering, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
  • Ludwig Institute for Cancer Research Lausanne, Lausanne, Switzerland.

ORCID-Profile: Patrick Barth

Förderung

  • Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
  • EPFL and the Ludwig Institute for Cancer Research

Zitieren

APA

Marfoglia, M., Pedraza-Joya, M. A., Guirardel, L., Chatzi Souleiman, A., & Barth, P. (2026). AlloPool is a deep learning framework that infers protein allostery from molecular dynamics simulations. PLOS Biology. https://doi.org/10.1371/journal.pbio.3004002

Vancouver

Marfoglia M, Pedraza-Joya MA, Guirardel L, Chatzi Souleiman A, Barth P. AlloPool is a deep learning framework that infers protein allostery from molecular dynamics simulations. PLOS Biology. 2026. doi:10.1371/journal.pbio.3004002

BibTeX
@article{Marfoglia2026,
  author = {Marfoglia, Matthieu and Pedraza-Joya, Miguel A and Guirardel, Lucas and Chatzi Souleiman, Aisima and Barth, Patrick},
  title = {AlloPool is a deep learning framework that infers protein allostery from molecular dynamics simulations},
  journal = {PLOS Biology},
  year = {2026},
  doi = {10.1371/journal.pbio.3004002}
}
Kostenlos starten →