
==== Front
bioRxiv
BIORXIV
bioRxiv
Cold Spring Harbor Laboratory

10.1101/2024.03.31.587283
preprint
2
Article
gRNAde: Geometric Deep Learning for 3D RNA inverse design
Joshi Chaitanya K. http://orcid.org/0000-0003-4722-1815

Jamasb Arian R. http://orcid.org/0000-0002-6727-7579

Viñas Ramon
Harris Charles
Mathis Simon V.
Morehead Alex
Anand Rishabh
Liò Pietro http://orcid.org/0000-0002-0540-5053

25 5 2024
2024.03.31.587283http://biorxiv.org/lookup/doi/10.1101/2024.03.31.587283
nihpp-2024.03.31.587283.pdf
Abstract

Computational RNA design tasks are often posed as inverse problems, where sequences are designed based on adopting a single desired secondary structure without considering 3D geometry and conformational diversity. We introduce gRNAde , a g eometric RNA de sign pipeline operating on 3D RNA backbones to design sequences that explicitly account for structure and dynamics. Under the hood, gRNAde is a multi-state Graph Neural Network that generates candidate RNA sequences conditioned on one or more 3D backbone structures where the identities of the bases are unknown. On a single-state fixed backbone re-design benchmark of 14 RNA structures from the PDB identified by Das et al. [2010], gRNAde obtains higher native sequence recovery rates (56% on average) compared to Rosetta (45% on average), taking under a second to produce designs compared to the reported hours for Rosetta. We further demonstrate the utility of gRNAde on a new benchmark of multi-state design for structurally flexible RNAs, as well as zero-shot ranking of mutational fitness landscapes in a retrospective analysis of a recent RNA polymerase ribozyme structure.
==== Body
pmc
