EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Tracking large chemical reaction networks and rare events by neural networks

Jiayu Weng, Xinyi Zhu, Jing Liu, Linyuan Lü, Pan Zhang, Ying Tang

PRX Intelligence · 24.09.2026

DOI: 10.1103/k3mz-573d ↗

Kurz gefasst

Fachartikel in der Zeitschrift PRX Intelligence, online erschienen am 24.09.2026. Verfasst von Jiayu Weng und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Chemical reaction networks are widely used to model stochastic dynamics in biophysical processes. Their exact probabilistic description via the chemical master equation becomes intractable for high-dimensional systems due to the exponential growth of the state space. This difficulty is further exacerbated when metastable transitions and rare events dominate the dynamics. Here, we present an advanced neural-network approach that effectively tackles large reaction networks and rare-event dynamics within a unified framework. Building on autoregressive representations of the full joint probability distribution, we achieve efficient training through second-order optimization methods, including natural gradient descent and the time-dependent variational principle. We leverage enhanced-sampling strategies that enable accurate resolution of low-probability regions governing rare transitions. We demonstrate the method on a multistable genetic toggle switch and a mitogen-activated protein kinase (MAPK) cascade consisting of 16 species and 35 reactions with dense coupling. We further quantify rare events in spatially extended Schlögl models in both one- and two-dimensional lattices, reaching system sizes with extremely large state spaces up to $3\times10^{15}$. These results highlight the potential of neural modeling as a flexible and scalable framework for studying high-dimensional chemical reaction networks and rare events.

Zitieren

APA

Weng, J., Zhu, X., Liu, J., Lü, L., Zhang, P., & Tang, Y. (2026). Tracking large chemical reaction networks and rare events by neural networks. PRX Intelligence. https://doi.org/10.1103/k3mz-573d

Vancouver

Weng J, Zhu X, Liu J, Lü L, Zhang P, Tang Y. Tracking large chemical reaction networks and rare events by neural networks. PRX Intelligence. 2026. doi:10.1103/k3mz-573d

BibTeX
@article{Weng2026,
  author = {Weng, Jiayu and Zhu, Xinyi and Liu, Jing and Lü, Linyuan and Zhang, Pan and Tang, Ying},
  title = {Tracking large chemical reaction networks and rare events by neural networks},
  journal = {PRX Intelligence},
  year = {2026},
  doi = {10.1103/k3mz-573d}
}
Kostenlos starten →