arXiv cs.AI· Andrzej Mizera, Jakub Zarzycki·· 3 天前AI 评分20
GATTACA：基于图神经网络的强化学习框架用于控制生物网络
Graph Neural Network-Based Reinforcement Learning for Controlling Biological Networks - the GATTACA Framework
AI 导读
研究者提出 GATTACA，一个基于深度强化学习的可扩展计算框架，用于控制布尔网络模型以模拟细胞重编程。该框架将图神经网络与图卷积操作融入 DRL 智能体的动作价值函数近似器，并改进了伪吸引子状态的识别方法。在多个大规模真实生物网络上的实验验证了其可扩展性与有效性。
正文 · 原文
Abstract:Cellular reprogramming, the artificial transformation of one cell type into another, has been attracting increasing research attention due to its therapeutic potential for complex diseases. However, identifying effective reprogramming strategies through classical wet-lab experiments is hindered by lengthy time commitments and high costs.
In this study, we explore the use of deep reinforcement learning (DRL) to control Boolean network models of complex biological systems, such as gene regulatory and signalling pathway networks. We formulate a novel control problem for Boolean network models under the asynchronous update mode, specifically in the context of cellular reprogramming. To solve it, we devise GATTACA, a scalable computational framework.
To facilitate scalability of our framework, we consider previously introduced concept of a pseudo-attractor and improve the procedure for effective identification of pseudo-attractor states. We then incorporate graph neural networks with graph convolution operations into the artificial neural network approximator of the DRL agent's action-value function. This allows us to leverage the available knowledge on the structure of a biological system and to indirectly, yet effectively, encode the system's modelled dynamics into a latent representation.
Experiments on several large-scale, real-world biological networks from the literature demonstrate the scalability and effectiveness of our approach.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Molecular Networks (q-bio.MN) |
| Cite as: | arXiv:2505.02712 [cs.LG] |
| (or arXiv:2505.02712v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2505.02712 arXiv-issued DOI via DataCite |
Submission history
From: Andrzej Mizera [view email]
[v1]
Mon, 5 May 2025 15:07:20 UTC (5,099 KB)
[v2]
Fri, 30 May 2025 10:59:25 UTC (203 KB)
[v3]
Mon, 17 Nov 2025 17:35:01 UTC (200 KB)
[v4]
Sun, 11 Oct 2026 20:47:29 UTC (200 KB)
来源：arXiv cs.AI · arxiv.org