RIDER: 3D RNA Inverse Design with Reinforcement Learning-Guided Diffusion

2026-02-18

AI Summary

This work addresses the limitations of existing RNA inverse design methods, which rely heavily on native sequence recovery rates and fail to accurately assess the geometric similarity between generated sequences and target structures upon folding. To overcome this, the authors propose RIDER, a novel framework that introduces, for the first time, a reinforcement learning reward mechanism based on 3D self-consistency into RNA inverse design. RIDER combines a graph neural network–based conditional diffusion model for pretraining and is fine-tuned using an improved policy gradient algorithm with four structure-consistency reward functions. Experimental results demonstrate that RIDER improves all structural similarity metrics by over 100%, increases native sequence recovery by 9%, and generates sequences substantially distinct from natural ones while maintaining high structural fidelity.

Technology Category

• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• RNA inverse design
• 3D structure
• native sequence recovery
• structural fidelity
• synthetic biology

Innovation

• RNA inverse design
• reinforcement learning
• diffusion model
• 3D structure optimization
• graph neural network