Beyond Sequence: Impact of Geometric Context for RNA Property Prediction

TL;DR

This paper systematically evaluates how incorporating 2D and 3D geometric information improves RNA property prediction, demonstrating that geometry-aware models outperform sequence-only models especially in low-data and noisy scenarios.

Contribution

It introduces a curated RNA dataset with structural annotations and provides the first comprehensive evaluation of geometric encoding in RNA property prediction models.

Findings

Geometry-aware models reduce prediction RMSE by ~12%.

Explicit geometry encoding excels in low-data and partial labeling regimes.

Sequence-based models are more robust to sequencing noise.

Abstract

Accurate prediction of RNA properties, such as stability and interactions, is crucial for advancing our understanding of biological processes and developing RNA-based therapeutics. RNA structures can be represented as 1D sequences, 2D topological graphs, or 3D all-atom models, each offering different insights into its function. Existing works predominantly focus on 1D sequence-based models, which overlook the geometric context provided by 2D and 3D geometries. This study presents the first systematic evaluation of incorporating explicit 2D and 3D geometric information into RNA property prediction, considering not only performance but also real-world challenges such as limited data availability, partial labeling, sequencing noise, and computational efficiency. To this end, we introduce a newly curated set of RNA datasets with enhanced 2D and 3D structural annotations, providing a resource for model evaluation on RNA data. Our findings reveal that models with explicit geometry encoding generally outperform sequence-based models, with an average prediction RMSE reduction of around 12% across all various RNA tasks and excelling in low-data and partial labeling regimes, underscoring the value of explicitly incorporating geometric context. On the other hand, geometry-unaware sequence-based models are more robust under sequencing noise but often require around $2-5\times$ training data to match the performance of geometry-aware models. Our study offers further insights into the trade-offs between different RNA representations in practical applications and addresses a significant gap in evaluating deep learning models for RNA tasks.