La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching

2026-10-08

AI Summary

This study addresses the challenges of reconciling global folding with local structural details and the scarcity of supervision signals in the joint design of RNA sequences and three-dimensional structures. To this end, it proposes a generative framework based on geometric latent flow matching. This approach introduces a novel shared network architecture that jointly generates and reconstructs atoms through sparse backbone encoding and residual-level latent representations. By leveraging multi-model ensemble data augmentation to construct a high-quality, large-scale RNA structure library, the framework supports inverse folding tasks without requiring additional training. Experimental results demonstrate that the proposed method significantly outperforms baseline models in both designability and co-designability metrics, while exhibiting robust performance across various sampling budgets and refolding models.

Abstract

RNA function arises from the coupling of nucleotide sequence and three-dimensional structure, motivating their joint design. Coordinating global folding with nucleotide-level detail remains challenging under limited structural supervision. We introduce La-Ribo, a generative framework for RNA sequence-structure co-design via geometry-latent flow matching. La-Ribo retains a sparse phosphate-sugar--base scaffold and encodes nucleotide identity and local conformation in residue-wise latents. A shared flow network generates both jointly, and an RNA-specific decoder then reconstructs all heavy atoms. To expand supervision, we construct a quality-controlled corpus of 168,561 RNA structures, integrating experimental data with predictions from three folding models, including 10,631 MSA-supported structures generated in this work. La-Ribo improves designability and codesignability over the evaluated baselines across sampling budgets and two refolding models, and the same prior supports scaffold-conditioned inverse folding without additional training.

Problem

• RNA co-design
• sequence-structure joint design
• limited structural supervision
• global folding coordination

Innovation

• RNA co-design
• Flow matching
• Latent representation
• Inverse folding
• Generative framework