Problem
Research questions and friction points this paper is trying to address.
3D RNA inverse design
Geometric Deep Learning
Multi-state RNA sequences
gRNAde: Geometric Deep Learning for 3D RNA inverse design
🤖 AI Summary
This work addresses two longstanding challenges in RNA 3D inverse design: overreliance on secondary structure and neglect of conformational diversity. We propose gRNAde—the first method integrating polymorphic graph neural networks (GNNs) with autoregressive decoding for end-to-end 3D RNA sequence design. Unlike conventional approaches, gRNAde directly models geometric and topological features of polymorphic 3D backbones, supporting both monomorphic and polymorphic inputs as well as zero-shot mutation fitness ranking. Evaluated on a benchmark of 14 PDB structures, gRNAde achieves a native-sequence recovery rate of 56%, substantially outperforming Rosetta (45%), with design time under one second per instance. Its core innovation lies in pioneering the use of polymorphic GNNs for RNA 3D inverse design—enabling direct mapping from dynamic 3D conformations to functional sequences and breaking the paradigm’s dependence on secondary-structure constraints.
📝 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 geometric RNA design pipeline operating on 3D RNA backbones to design sequences that explicitly account for structure and dynamics. gRNAde uses a multi-state Graph Neural Network and autoregressive decoding to 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 ribozyme. Open source code: github.com/chaitjo/geometric-rna-design
Innovation
Methods, ideas, or system contributions that make the work stand out.
Geometric Deep Learning for RNA
Multi-state Graph Neural Network
Autoregressive decoding for sequences
🔎 Similar Papers
No similar papers found.
