RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matching

Divya Nori, Wengong Jin
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38395-38408, 2024.

Abstract

The growing significance of RNA engineering in diverse biological applications has spurred interest in developing AI methods for structure-based RNA design. While diffusion models have excelled in protein design, adapting them for RNA presents new challenges due to RNA’s conformational flexibility and the computational cost of fine-tuning large structure prediction models. To this end, we propose RNAFlow, a flow matching model for protein-conditioned RNA sequence-structure design. Its denoising network integrates an RNA inverse folding model and a pre-trained RosettaFold2NA network for generation of RNA sequences and structures. The integration of inverse folding in the structure denoising process allows us to simplify training by fixing the structure prediction network. We further enhance the inverse folding model by conditioning it on inferred conformational ensembles to model dynamic RNA conformations. Evaluation on protein-conditioned RNA structure and sequence generation tasks demonstrates RNAFlow’s advantage over existing RNA design methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-nori24a, title = {{RNAF}low: {RNA} Structure & Sequence Design via Inverse Folding-Based Flow Matching}, author = {Nori, Divya and Jin, Wengong}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {38395--38408}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/nori24a/nori24a.pdf}, url = {https://proceedings.mlr.press/v235/nori24a.html}, abstract = {The growing significance of RNA engineering in diverse biological applications has spurred interest in developing AI methods for structure-based RNA design. While diffusion models have excelled in protein design, adapting them for RNA presents new challenges due to RNA’s conformational flexibility and the computational cost of fine-tuning large structure prediction models. To this end, we propose RNAFlow, a flow matching model for protein-conditioned RNA sequence-structure design. Its denoising network integrates an RNA inverse folding model and a pre-trained RosettaFold2NA network for generation of RNA sequences and structures. The integration of inverse folding in the structure denoising process allows us to simplify training by fixing the structure prediction network. We further enhance the inverse folding model by conditioning it on inferred conformational ensembles to model dynamic RNA conformations. Evaluation on protein-conditioned RNA structure and sequence generation tasks demonstrates RNAFlow’s advantage over existing RNA design methods.} }
Endnote
%0 Conference Paper %T RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matching %A Divya Nori %A Wengong Jin %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-nori24a %I PMLR %P 38395--38408 %U https://proceedings.mlr.press/v235/nori24a.html %V 235 %X The growing significance of RNA engineering in diverse biological applications has spurred interest in developing AI methods for structure-based RNA design. While diffusion models have excelled in protein design, adapting them for RNA presents new challenges due to RNA’s conformational flexibility and the computational cost of fine-tuning large structure prediction models. To this end, we propose RNAFlow, a flow matching model for protein-conditioned RNA sequence-structure design. Its denoising network integrates an RNA inverse folding model and a pre-trained RosettaFold2NA network for generation of RNA sequences and structures. The integration of inverse folding in the structure denoising process allows us to simplify training by fixing the structure prediction network. We further enhance the inverse folding model by conditioning it on inferred conformational ensembles to model dynamic RNA conformations. Evaluation on protein-conditioned RNA structure and sequence generation tasks demonstrates RNAFlow’s advantage over existing RNA design methods.
APA
Nori, D. & Jin, W.. (2024). RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matching. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:38395-38408 Available from https://proceedings.mlr.press/v235/nori24a.html.

Related Material