RNAbpFlow: base pair-augmented SE(3) flow matching for conditional RNA 3D structure generation

Abstract

Despite the groundbreaking advances in deep learning-enabled methods for biomolecular modeling, predicting accurate three-dimensional (3D) structures of RNA remains challenging due to the highly flexible nature of RNA molecules combined with the limited availability of evolutionary sequences or structural homology. Here we introduce RNAbpFlow, a novel sequence- and base-pair-conditioned SE(3)-equivariant flow matching model for generating RNA 3D structural ensemble. Leveraging a nucleobase center representation, RNAbpFlow enables end-to-end generation of all-atom RNA structures without the explicit or implicit use of evolutionary information or homologous structural templates. Experimental results show that base pairing conditioning leads to broadly generalizable performance improvements over current approaches for RNA topology sampling and predictive modeling in large-scale benchmarking. RNAbpFlow is freely available at https://github.com/Bhattacharya-Lab/RNAbpFlow.

RAGCell: retrieval-augmented generation as supervision for versatile single-cell analysis
Tianyu Liu, Fan Zhang, Jiayuan Chen +10
Bioinformatics1 Oct 2026Peer-reviewedCC BY 4.0Full textMolecular biology & gene regulationCrossref
Conditional Generation And Inpainting Of Non-coding RNA Sequences With Masked Discrete Diffusion
U. Upadhyay, C. Dai, J. Herold +2
bioRxiv17 Sep 2026PreprintCC BYFull textBiophysicsbioRxiv
Reframing enzyme function prediction as conditional generation
W. J. Rieger, S. Haeussermann, L. Herrmann +9
bioRxiv9 Sep 2026PreprintCC BYFull textMolecular biology & gene regulationbioRxiv
Research on an elderly low-vision field-aid system based on augmented reality
Xi Chen, Xu Jing, Tinglong Liu +6
Frontiers in cell and developmental biology19 Oct 2026Peer-reviewedCC BYFull textGeneral biochemistryEurope PMC
Deep Learning-Augmented Stimulated Raman Imaging for Cell-Type-Specific Metabolic Profiling in Live Neuronal Cocultures.
Li-En Lin, Xiaotian Bi, Adrian Colazo +2
Chemical & biomedical imaging28 May 2026Peer-reviewedCC BY-NC-NDFull textBiophysicsEurope PMCPMC

Cite

BibTeX RIS

BibTeX

@article{tarafder2026rnabpflow,
  title = {{RNAbpFlow: base pair-augmented SE(3) flow matching for conditional RNA 3D structure generation}},
  author = {Sumit Tarafder and Debswapna Bhattacharya},
  journal = {Nature Methods},
  year = {2026},
  month = jun,
  doi = {10.1038/s41592-026-03128-4},
  url = {https://doi.org/10.1038/s41592-026-03128-4},
  note = {CC BY-NC-ND},
}

RIS

TY  - JOUR
TI  - RNAbpFlow: base pair-augmented SE(3) flow matching for conditional RNA 3D structure generation
AU  - Sumit Tarafder
AU  - Debswapna Bhattacharya
PY  - 2026
DA  - 2026/06/30
JO  - Nature Methods
DO  - 10.1038/s41592-026-03128-4
UR  - https://doi.org/10.1038/s41592-026-03128-4
AB  - Despite the groundbreaking advances in deep learning-enabled methods for biomolecular modeling, predicting accurate three-dimensional (3D) structures of RNA remains challenging due to the highly flexible nature of RNA molecules combined with the limited availability of evolutionary sequences or structural homology. Here we introduce RNAbpFlow, a novel sequence- and base-pair-conditioned SE(3)-equivariant flow matching model for generating RNA 3D structural ensemble. Leveraging a nucleobase center representation, RNAbpFlow enables end-to-end generation of all-atom RNA structures without the explicit or implicit use of evolutionary information or homologous structural templates. Experimental results show that base pairing conditioning leads to broadly generalizable performance improvements over current approaches for RNA topology sampling and predictive modeling in large-scale benchmarking. RNAbpFlow is freely available at https://github.com/Bhattacharya-Lab/RNAbpFlow.
SN  - 1548-7091
SN  - 1548-7105
ER  -

Abstract

Related

Cite