RNA-FrameFlow: Flow Matching for de novo 3D RNA Backbone Design

TL;DR

RNA-FrameFlow is a novel generative model that designs 3D RNA backbones by adapting flow matching techniques from protein modeling, addressing RNA-specific challenges and evaluating structural validity.

Contribution

It introduces the first generative model for 3D RNA backbone design using SE(3) flow matching, with new protocols for data preparation and evaluation tailored to RNA.

Findings

Generates realistic RNA backbones of 40-150 nucleotides

Over 40% of generated RNAs pass validity criteria based on self-consistency

Effective data augmentation improves model diversity

Abstract

We introduce RNA-FrameFlow, the first generative model for 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 >= 0.45, at which two RNAs have the same global fold. Open-source code: https://github.com/rish-16/rna-backbone-design