Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2603.19636 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914410245652480 |
|---|---|
| author | Zhang, Zhou Cao, Hanqun Tan, Cheng Wu, Fang Heng, Pheng Ann Fu, Tianfan |
| author_facet | Zhang, Zhou Cao, Hanqun Tan, Cheng Wu, Fang Heng, Pheng Ann Fu, Tianfan |
| contents | Accurate RNA structure modeling remains difficult because RNA backbones are highly flexible, non-canonical interactions are prevalent, and experimentally determined 3D structures are comparatively scarce. We introduce \emph{RiboSphere}, a framework that learns \emph{discrete} geometric representations of RNA by combining vector quantization with flow matching. Our design is motivated by the modular organization of RNA architecture: complex folds are composed from recurring structural motifs. RiboSphere uses a geometric transformer encoder to produce SE(3)-invariant (rotation/translation-invariant) features, which are discretized with finite scalar quantization (FSQ) into a finite vocabulary of latent codes. Conditioned on these discrete codes, a flow-matching decoder reconstructs atomic coordinates, enabling high-fidelity structure generation. We find that the learned code indices are enriched for specific RNA motifs, suggesting that the model captures motif-level compositional structure rather than acting as a purely compressive bottleneck. Across benchmarks, RiboSphere achieves strong performance in structure reconstruction (RMSD 1.25\,Å, TM-score 0.84), and its pretrained discrete representations transfer effectively to inverse folding and RNA--ligand binding prediction, with robust generalization in data-scarce regimes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19636 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RiboSphere: Learning Unified and Efficient Representations of RNA Structures Zhang, Zhou Cao, Hanqun Tan, Cheng Wu, Fang Heng, Pheng Ann Fu, Tianfan Machine Learning Accurate RNA structure modeling remains difficult because RNA backbones are highly flexible, non-canonical interactions are prevalent, and experimentally determined 3D structures are comparatively scarce. We introduce \emph{RiboSphere}, a framework that learns \emph{discrete} geometric representations of RNA by combining vector quantization with flow matching. Our design is motivated by the modular organization of RNA architecture: complex folds are composed from recurring structural motifs. RiboSphere uses a geometric transformer encoder to produce SE(3)-invariant (rotation/translation-invariant) features, which are discretized with finite scalar quantization (FSQ) into a finite vocabulary of latent codes. Conditioned on these discrete codes, a flow-matching decoder reconstructs atomic coordinates, enabling high-fidelity structure generation. We find that the learned code indices are enriched for specific RNA motifs, suggesting that the model captures motif-level compositional structure rather than acting as a purely compressive bottleneck. Across benchmarks, RiboSphere achieves strong performance in structure reconstruction (RMSD 1.25\,Å, TM-score 0.84), and its pretrained discrete representations transfer effectively to inverse folding and RNA--ligand binding prediction, with robust generalization in data-scarce regimes. |
| title | RiboSphere: Learning Unified and Efficient Representations of RNA Structures |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.19636 |