RNA FrameFlow: Flow Matching for de novo 3D RNA Backbone Generation

Rishabh Anand, Chaitanya K. Joshi, Alex Morehead, Arian Rokkum Jamasb, Charles Harris, Simon V Mathis, Kieran Didi, Bryan Hooi, Pietro LioSubmission to ICLR 2025 · Rejected

Abstract

We introduce RNA-FrameFlow, the first generative model for de novo 3D RNA backbone design. We build upon $SE(3)$ flow matching for protein backbone generation and establish protocols for data preparation and evaluation to address unique challenges posed by RNA modeling. We formulate RNA structures as a set of rigid-body frames and associated loss functions which account for larger, more conformationally flexible RNA backbones (13 atoms per nucleotide) vs. proteins (4 atoms per residue). Toward tackling the lack of diversity in 3D RNA datasets, we explore training with structural clustering and cropping augmentations. Additionally, we define a suite of evaluation metrics to measure whether the generated RNA structures are globally self-consistent (via inverse folding followed by forward folding) and locally recover RNA-specific structural descriptors. The most performant version of RNA-FrameFlow generates locally realistic RNA backbones of 40-150 nucleotides, over 40\% of which pass our validity criteria as measured by a self-consistency TM-score $\geq0.45$, at which two RNAs have the same global fold.
BibTeX
@article{anand2025rna,
  author = {Rishabh Anand and Chaitanya K. Joshi and Alex Morehead and Arian Rokkum Jamasb and Charles Harris and Simon V Mathis and Kieran Didi and Bryan Hooi and Pietro Lio},
  title = {{RNA FrameFlow: Flow Matching for de novo 3D RNA Backbone Generation}},
  journal = {Accepted by TMLR},
  year = {2025},
  url = {https://openreview.net/forum?id=wOc1Yx5s09},
}
Figure