RiboDFM: Robust RNA sequence design using backbone-conditioned discrete flow matching
- 1Shandong University
Abstract
Designing RNA sequences that fold into predefined 3D structures is central to RNA engineering, yet it remains challenging due to the scarcity of experimentally determined structures and the complex sequence-structure relationships. Here, we present RiboDFM, a backbone-conditioned discrete flow-matching framework for RNA sequence design. RiboDFM progressively resolves fully masked sequences by integrating a geometric backbone encoder, an auxiliary base-pairing prediction head, and language model representations into a discrete flow sampler. To expand our training data, we supplemented experimental structures with a large-scale collection of trRosettaRNA2-predicted models. Across diverse benchmarks, RiboDFM achieves high sequence recovery and generates sequences with greater tertiary-structure self-consistency than existing methods. RiboDFM also performs strongly on aptamer-focused design tasks. Finally, beyond sequence generation, the nucleotide probabilities derived from RiboDFM' s flow trajectory serve as an intrinsic measure of sequence-structure compatibility. This enables reliable confidence estimation for designed sequences, as well as reference-free, zero-shot assessment of predicted structure models. Together, these results establish RiboDFM as an effective framework for structure-based RNA sequence design.
Related
- Inverse FoldDir: Structure-conditioned Protein Sequence Design by Dirichlet Flow Matching
- RiboBridge couples RNA backbone generation to sequence design through a learned interaction topology
- TopoFlow: Evolutionarily Conditioned Flow Matching for Protein Conformational Ensemble Generation
- TempoBridge: Source-Conditioned Flow Matching with Optimal Transport Couplings for Single-Cell Population Transitions
- GeoSinkhorn Flow: Geometry-Aware Flow Matching for Perturbation-Conditioned Dynamics in Single cell Data Phenoscapes
BibTeX
@misc{liu2026ribodfm,
title = {{RiboDFM: Robust RNA sequence design using backbone-conditioned discrete flow matching}},
author = {X. Liu and X. An and Z. Peng and W. Wang and J. Yang},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.22.761295},
url = {https://www.biorxiv.org/content/10.64898/2026.10.22.761295v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - RiboDFM: Robust RNA sequence design using backbone-conditioned discrete flow matching
AU - X. Liu
AU - X. An
AU - Z. Peng
AU - W. Wang
AU - J. Yang
PY - 2026
DA - 2026/10/22
PB - bioRxiv
DO - 10.64898/2026.10.22.761295
UR - https://www.biorxiv.org/content/10.64898/2026.10.22.761295v1
AB - Designing RNA sequences that fold into predefined 3D structures is central to RNA engineering, yet it remains challenging due to the scarcity of experimentally determined structures and the complex sequence-structure relationships. Here, we present RiboDFM, a backbone-conditioned discrete flow-matching framework for RNA sequence design. RiboDFM progressively resolves fully masked sequences by integrating a geometric backbone encoder, an auxiliary base-pairing prediction head, and language model representations into a discrete flow sampler. To expand our training data, we supplemented experimental structures with a large-scale collection of trRosettaRNA2-predicted models. Across diverse benchmarks, RiboDFM achieves high sequence recovery and generates sequences with greater tertiary-structure self-consistency than existing methods. RiboDFM also performs strongly on aptamer-focused design tasks. Finally, beyond sequence generation, the nucleotide probabilities derived from RiboDFM' s flow trajectory serve as an intrinsic measure of sequence-structure compatibility. This enables reliable confidence estimation for designed sequences, as well as reference-free, zero-shot assessment of predicted structure models. Together, these results establish RiboDFM as an effective framework for structure-based RNA sequence design.
ER -