A Comprehensive Benchmark for RNA 3D Structure-Function Modeling

ICLR 2026 Conference Submission5940 Authors

Keywords: RNA, nucleic acids, benchmarking, graph learning, structure-function relationship, structural biology

TL;DR: RNA, nucleic acids, benchmarking, graph learning, structure-function relationship, structural biology.

Abstract:

The relationship between RNA structure and function has recently attracted interest within the deep learning community, a trend expected to intensify as nucleic acid structure models advance.
Despite this momentum, a lack of standardized, accessible benchmarks for applying deep learning to RNA 3D structures hinders progress.
To this end, we introduce a collection of seven benchmarking datasets specifically designed to support RNA structure–function prediction. Built on top of the established Python package \texttt{rnaglib}, our library streamlines data distribution and encoding, provides tools for dataset splitting and evaluation, and offers a comprehensive, user-friendly environment for model comparison. The modular and reproducible design of our datasets encourages community contributions and enables rapid customization. To demonstrate the utility of our benchmarks, we report baseline results for all tasks using a relational graph neural network.

Primary Area: datasets and benchmarks

Submission Number: 5940