用强化学习引导扩散模型，直接优化RNA三维结构设计。
RIDER: 3D RNA Inverse Design with Reinforcement Learning-Guided Diffusion
- 基于图神经网络的扩散模型，条件于目标三维结构生成序列。
- 结构相似性提升超100%，设计出与天然序列不同的新结构。
- 采用多维度自洽性奖励，解决传统方法依赖序列恢复的问题。
RNA三维结构的逆向设计对合成生物学和治疗应用至关重要。现有深度学习方法通常以天然序列恢复为目标，但该指标无法准确反映结构保真度，因为不同序列可折叠成相似三维结构。为此，我们提出RIDER框架，通过强化学习直接优化三维结构相似性。首先，构建并预训练一个基于图神经网络的生成扩散模型，条件于目标三维结构，在序列恢复上比现有最优方法提升9%。随后，使用改进的策略梯度算法，结合四个基于三维自洽性度量的任务特定奖励函数进行微调。实验表明，RIDER在所有指标上均实现超过100%的结构相似性提升，并成功发现与天然序列显著不同的设计。
原文摘要 · Abstract (English)
The inverse design of RNA three-dimensional (3D) structures is crucial for engineering functional RNAs in synthetic biology and therapeutics. While recent deep learning approaches have advanced this field, they are typically optimized and evaluated using native sequence recovery, which is a limited surrogate for structural fidelity, since different sequences can fold into similar 3D structures and high recovery does not necessarily indicate correct folding. To address this limitation, we propose RIDER, an RNA Inverse DEsign framework with Reinforcement learning that directly optimizes for 3D structural similarity. First, we develop and pre-train a GNN-based generative diffusion model conditioned on the target 3D structure, achieving a 9% improvement in native sequence recovery over state-of-the-art methods. Then, we fine-tune the model with an improved policy gradient algorithm using four task-specific reward functions based on 3D self-consistency metrics. Experimental results show that RIDER improves structural similarity by over 100% across all metrics and discovers designs that are distinct from native sequences.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。