RiboBridge: protein-conditioned de novo RNA binder structure design
Abstract
Designing RNA molecules that bind to target protein structures requires generating both an RNA conformation and its bound complex geometry, without assuming a predefined binding site. Existing approaches generally model these coupled processes within a unified representation, entangling RNA conformation generation with protein-relative placement. In this work, we introduce RiboBridge, a structure-first framework that separates RNA conformational generation from protein--RNA assembly through cross-frame interaction geometry. RiboBridge first proposes multiple candidate RNA-binding interfaces on the protein surface, generates canonical RNA conformations within a pretrained RNA structural latent space (RiboSphere), and then predicts protein--RNA interaction constraints to bridge the independently defined RNA and protein coordinate frames. The resulting interaction geometry is converted into a geometrically consistent protein-relative pose through rigid placement. We evaluate RiboBridge on a temporally split, sequence-filtered, and redundancy-controlled benchmark of 124 protein--RNA complexes. Under post-hoc interface-correspondence evaluation, where native information is used only after generation to select among already generated predicted-pocket candidates, RiboBridge achieves the highest fNAT and DockQ and the lowest interface and ligand RMSDs among compared methods. Component ablations and stage-wise diagnostics further characterize the contributions of RNA conformational generation, interaction prediction, and rigid placement, identifying the main sources of complex-recovery error.
Related
- The latest AI breakthroughs in structural biology: protein binder design and conformational state prediction
- Aptamers without SELEX: De novo design from protein structure in hours
- What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design
- Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling
- Agent-guided epitope excision enables economical de novo binder design
BibTeX
@misc{zhang2026ribobridge,
title = {{RiboBridge: protein-conditioned de novo RNA binder structure design}},
author = {Zhou Zhang and Hanqun Cao and Minghao Sun and Odin Zhang and Yang Zhang and Pheng Ann Heng and Wujun Li and Tianfan Fu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.30668},
eprint = {2610.30668},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.30668},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - RiboBridge: protein-conditioned de novo RNA binder structure design
AU - Zhou Zhang
AU - Hanqun Cao
AU - Minghao Sun
AU - Odin Zhang
AU - Yang Zhang
AU - Pheng Ann Heng
AU - Wujun Li
AU - Tianfan Fu
PY - 2026
DA - 2026/10/22
PB - arXiv
DO - 10.48550/arxiv.2610.30668
UR - https://arxiv.org/abs/2610.30668
AB - Designing RNA molecules that bind to target protein structures requires generating both an RNA conformation and its bound complex geometry, without assuming a predefined binding site. Existing approaches generally model these coupled processes within a unified representation, entangling RNA conformation generation with protein-relative placement. In this work, we introduce RiboBridge, a structure-first framework that separates RNA conformational generation from protein--RNA assembly through cross-frame interaction geometry. RiboBridge first proposes multiple candidate RNA-binding interfaces on the protein surface, generates canonical RNA conformations within a pretrained RNA structural latent space (RiboSphere), and then predicts protein--RNA interaction constraints to bridge the independently defined RNA and protein coordinate frames. The resulting interaction geometry is converted into a geometrically consistent protein-relative pose through rigid placement. We evaluate RiboBridge on a temporally split, sequence-filtered, and redundancy-controlled benchmark of 124 protein--RNA complexes. Under post-hoc interface-correspondence evaluation, where native information is used only after generation to select among already generated predicted-pocket candidates, RiboBridge achieves the highest fNAT and DockQ and the lowest interface and ligand RMSDs among compared methods. Component ablations and stage-wise diagnostics further characterize the contributions of RNA conformational generation, interaction prediction, and rigid placement, identifying the main sources of complex-recovery error.
ER -