RiboBridge couples RNA backbone generation to sequence design through a learned interaction topology
- 1School of Engineering, Westlake University, Hangzhou, China
Abstract
Designing RNAs with prescribed structures is central to RNA engineering. Backbone-first approaches generate geometry before sequence assignment, yet how to transfer relational information to sequence design remains unclear. We introduce RiboCouple, which infers a probabilistic residue-pair state from backbone geometry, recycles pair probabilities through a second pass and transfers them to sequence decoding as soft attention biases. On 550 generated backbones, pair-type decoding achieved joint refolding validity of 45.1 percent versus 33.5 percent for a matched topology-free decoder. In another 110-backbone cohort, replacing aligned pair states with statistics-matched donor states reduced validity from 46.4 percent to 21.4 percent, demonstrating that decoding depends on backbone-aligned relational information. Before external refolding, pair-confidence ranking enriched validity to 59.6 percent in the top 248 and transferred to other generators; on a 94-chain temporally held-out native-backbone benchmark, pair-coupled decoding improved secondary-structure agreement. These findings establish backbone-inferred interaction topology as an intermediate representation connecting backbone generation, sequence decoding, and candidate prioritization.
Related
- RiboDFM: Robust RNA sequence design using backbone-conditioned discrete flow matching
- Repurposing PeTriBERT for Protein Protein Interaction Prediction with Sequence Structure Fusion
- OmniTCR: a foundation model unifying T cell receptor recognition prediction and conditional sequence generation
- Constructed Negatives Shape the Evaluation of Sequence-Based Protein–Protein Interaction Models
- Steering sequence generation in protein language models through Iterative Lookback Monte Carlo Sampling
BibTeX
@misc{ma2026ribobridge,
title = {{RiboBridge couples RNA backbone generation to sequence design through a learned interaction topology}},
author = {Z. Ma and Y. Zheng},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.15.759394},
url = {https://www.biorxiv.org/content/10.64898/2026.10.15.759394v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - RiboBridge couples RNA backbone generation to sequence design through a learned interaction topology
AU - Z. Ma
AU - Y. Zheng
PY - 2026
DA - 2026/10/15
PB - bioRxiv
DO - 10.64898/2026.10.15.759394
UR - https://www.biorxiv.org/content/10.64898/2026.10.15.759394v1
AB - Designing RNAs with prescribed structures is central to RNA engineering. Backbone-first approaches generate geometry before sequence assignment, yet how to transfer relational information to sequence design remains unclear. We introduce RiboCouple, which infers a probabilistic residue-pair state from backbone geometry, recycles pair probabilities through a second pass and transfers them to sequence decoding as soft attention biases. On 550 generated backbones, pair-type decoding achieved joint refolding validity of 45.1 percent versus 33.5 percent for a matched topology-free decoder. In another 110-backbone cohort, replacing aligned pair states with statistics-matched donor states reduced validity from 46.4 percent to 21.4 percent, demonstrating that decoding depends on backbone-aligned relational information. Before external refolding, pair-confidence ranking enriched validity to 59.6 percent in the top 248 and transferred to other generators; on a 94-chain temporally held-out native-backbone benchmark, pair-coupled decoding improved secondary-structure agreement. These findings establish backbone-inferred interaction topology as an intermediate representation connecting backbone generation, sequence decoding, and candidate prioritization.
ER -