Search papers, labs, and topics across Lattice.
This paper introduces La-Ribo, a generative framework for RNA sequence-structure co-design using geometry-latent flow matching, addressing the challenge of coordinating global folding with nucleotide-level detail under limited structural supervision. By encoding nucleotide identity and local conformation in residue-wise latents within a sparse scaffold, La-Ribo jointly generates sequence and structure, demonstrating improved designability and codesignability over baselines. The framework leverages a novel, quality-controlled corpus of RNA structures, including newly generated MSA-supported designs, and its learned prior enables scaffold-conditioned inverse folding without retraining.
A single generative model now co-designs RNA sequence and structure, achieving state-of-the-art designability by learning from a massive, integrated structural corpus.
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.
