# Computational approaches for RNA structure prediction and design

## TL;DR

This paper reviews how deep learning is improving RNA structure prediction and enabling better RNA design.

## Contribution

The paper provides an overview of recent deep-learning-based methods for RNA structure prediction and their impact on RNA design.

## Key findings

- Deep learning has significantly improved RNA structure prediction accuracy compared to traditional methods.
- New MSA-free and generalist deep-learning models can predict complex RNA structures from single sequences.
- Advances in prediction are driving progress in RNA design and structural biology.

## Abstract

Determining the three-dimensional (3D) structure of RNA is crucial for understanding its diverse biological functions. The field of computational RNA structure prediction has recently been transformed by deep learning, which has dramatically improved accuracy beyond that of conventional homology- and de novo modeling approaches. This article overviews these advancements. We first summarize the principles of foundational conventional approaches before detailing the current state-of-the-art deep-learning-based approaches. Deep-learning-based approaches are categorized into strategies that leverage multiple sequence alignments (MSAs), recent MSA-free methods that rely on single sequences, and emerging generalist models that can predict entire heterogenic biomolecular complexes. Furthermore, we discuss how these predictive breakthroughs are accelerating the field of RNA design. Finally, we outline the current challenges and future directions for computational RNA structural biology.