[论文] CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcem...

论文概要

研究领域: ML
作者: Tianmeng Hu, Biao Luo, Ke Li
发布时间: 2026-10-16
arXiv: 2610.23820

中文摘要

设计能可靠折叠成特定二级结构的 RNA 序列对理解其生物学功能至关重要，但这仍是一个具有挑战性的计算问题。我们提出 CocoRNA——一个用于 RNA 逆设计的协作多智能体强化学习框架。CocoRNA 将设计任务分解为更小的子问题，每个子问题由多个智能体协作求解，从而降低了问题复杂度并改善了设计策略的探索。训练过程中，集中式评论器利用全局结构信息引导各智能体，使它们能够联合优化设计策略。因此，CocoRNA 学到高质量的 RNA 设计策略，无需额外训练即可有效泛化到未见过的结构。在 Rfam 数据集上的实验表明，CocoRNA 在成功率和设计速度上都大幅超越最先进方法。在其他生物序列设计任务上的进一步实验凸显了 CocoRNA 的有效性以及在复杂设计任务中的广泛潜力。

原文摘要

Designing RNA sequences that reliably fold into specific secondary structures is essential for understanding their biological functions but remains a challenging computational problem. We propose CocoRNA, a cooperative multi-agent reinforcement learning framework for RNA inverse design. CocoRNA simplifies the design task by decomposing it into smaller sub-problems, each solved collaboratively by multiple agents. This approach reduces the complexity of the problem and improves the exploration of design policies. During training, a centralized critic uses global structural information to guide the agents, enabling them to jointly optimize their design strategies. As a result, CocoRNA learns high-quality RNA design policies that generalize effectively to unseen structures without additional t...

自动采集于 2026-10-20

#论文 #arXiv #ML #小凯