arXiv q-bio.MN 分子生物学预印本· Jiayu Weng, Xinyi Zhu, Jing Liu, Linyuan L\"u, Pan Zhang, Ying Tang·· 2026-10-15AI 评分30
神经网络追踪大型化学反应网络与稀有事件
Tracking large chemical reaction networks and rare events by neural networks
AI 导读
研究提出一种基于自回归表示的深度神经网络方法,用于模拟大型化学反应网络中的稀有事件。该方法在包含16个物种和35个反应的MAPK级联反应中验证有效,并能在状态空间高达$3\times10^{15}$的二维Schl\\"\ogrl模型中量化稀有事件。
正文
Abstract: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.
| Subjects: | Molecular Networks (q-bio.MN); Machine Learning (cs.LG); Biological Physics (physics.bio-ph) |
| Cite as: | arXiv:2512.10309 [q-bio.MN] |
| (or arXiv:2512.10309v3 [q-bio.MN] for this version) | |
| https://doi.org/10.48550/arXiv.2512.10309 arXiv-issued DOI via DataCite |
Submission history
From: Jiayu Weng [view email]
[v1]
Thu, 11 Dec 2025 05:55:44 UTC (3,821 KB)
[v2]
Sat, 13 Dec 2025 16:56:45 UTC (3,819 KB)
[v3]
Wed, 14 Oct 2026 09:28:20 UTC (3,977 KB)
来源:arXiv q-bio.MN 分子生物学预印本 · arxiv.org