Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.12236

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

Runze Ma·Will Hua·Shuangjia Zheng
View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

q-bio.BMcs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Runze Ma, Will Hua, Shuangjia Zheng. 2026-10-08. La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching. https://arxiv.org/abs/2610.12236

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Non-Markovain Quantum State Diffusion for the Tunneling in SARS-COVID-19 virus

In the context of biology, unlike the comprehensively established Standard Model in physics, many biological processes lack a complete theoretical framework and are often described phenomenologically. A pertinent example is olfaction -- the process through which humans and animals distinguish various odors. The conventional biological explanation for olfaction relies on the lock and key model, which, while useful, does not fully account for all observed phenomena. As an alternative or complement to this model, vibration-assisted electron tunneling has been proposed. Drawing inspiration from the vibration-assisted electron tunneling model for olfaction, we have developed a theoretical model for electron tunneling in SARS-CoV-2 virus infection within a non-Markovian framework. We approach this by solving the non-Markovian quantum stochastic Schrodinger equation. In our model, the spike protein and the GPCR receptor are conceptualized as a dimer, utilizing the spin-Boson model to facilitate the description of electron tunneling. Our analysis demonstrates that electron tunneling in this context exhibits inherently non-Markovian characteristics, extending into the intermediate and strong coupling regimes between the dimer components. This behavior stands in stark contrast to predictions from Markovian models, which fail to accurately describe electron tunneling in the strong coupling limit. Notably, Markovian approximations often lead to unphysical negative probabilities in this regime, underscoring their limitations and highlighting the necessity of incorporating non-Markovian dynamics for a more realistic description of biological quantum processes. This approach not only broadens our understanding of viral infection mechanisms but also enhances the biological accuracy and relevance of our theoretical framework in describing complex biological interactions.

q-bio.BM↗
arXiv2026

Leveraging secondary-structure information for accurate nucleic acid structure prediction with OFoldNA

Recent advances in biomolecular structure prediction have enabled accurate modelling of increasingly complex molecular systems. However, nucleic acid structure prediction remains challenging because of conformational flexibility and the limited availability of high-quality 3D structural data. Secondary structure (SS) provides a more readily available layer of structural information that captures base-pairing relationships and folding topology. Here we present OFoldNA, an all-atom diffusion model that incorporates SS information into nucleic acid folding and protein--nucleic acid co-folding. Without external SS information, OFoldNA achieved leading performance on FoldBench for both nucleic acid monomer folding and protein--nucleic acid co-folding, with particularly strong performance on DNA monomers and protein--DNA interfaces involving longer nucleic acid chains. When accurate base-pairing information was provided, OFoldNA-SS2TS further improved both folding and co-folding accuracy, while partial SS information also yielded consistent gains. The same auxiliary branch can also be used for RNA SS prediction as OFoldNA-SS, which achieved the best out-of-distribution performance on CHANRG. Together, these results show that intermediate structural information such as nucleic acid SS can be leveraged to improve all-atom 3D modelling, providing a general direction for incorporating complementary structural modalities into molecular structure prediction and design.

q-bio.BM↗
arXiv2026

UNAAGI: Atom-Level Diffusion for Generating Non-Canonical Amino Acid Substitutions

A central challenge in structural biology is identifying beneficial amino acid substitutions, a problem that underpins both mutational effect prediction and protein engineering. Recent inverse-folding models, trained to reconstruct sequences from structure, have shown considerable promise for identifying functional mutations. However, current approaches are constrained to designing sequences composed exclusively of canonical amino acids (CAAs). Non-canonical amino acids (NCAAs) offer greater chemical diversity and are frequently used for protein engineering in vivo, yet they remain largely inaccessible to current variant effect prediction methods. To address this gap, we introduce \textbf{UNAAGI}, a diffusion-based generative model that reconstructs residue identities from atomic-level structure using an E(3)-equivariant framework. By modeling side chains in full atomic detail rather than as discrete tokens, UNAAGI enables the exploration of canonical and non-canonical amino acid substitutions within a unified generative paradigm. We evaluate UNAAGI zero-shot, without mutational-effect supervision or task-specific fine-tuning, on experimental mutational-effect benchmarks and demonstrate substantially improved performance on NCAA substitutions relative to existing methods.

q-bio.BM↗