La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching
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.
Related
- PeTFlow: Flow-Matching Based All-Atom Peptide Design through Side-Chain State Tokenization
- RNA Design via Conditioned Flow Matching and Finite-Policy Reinforcement Learning
- Design of peptides with noncanonical amino acids using flow matching
- RNAbpFlow: base pair-augmented SE(3) flow matching for conditional RNA 3D structure generation
- Empirical Bayes Flow Matching for Continuous Cryo-EM Heterogeneity
BibTeX
@misc{ma2026laribo,
title = {{La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching}},
author = {Runze Ma and Will Hua and Shuangjia Zheng},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.12236},
eprint = {2610.12236},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.12236},
}
RIS
TY - UNPB
TI - La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching
AU - Runze Ma
AU - Will Hua
AU - Shuangjia Zheng
PY - 2026
DA - 2026/10/08
PB - arXiv
DO - 10.48550/arxiv.2610.12236
UR - https://arxiv.org/abs/2610.12236
AB - 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.
ER -