Scalable Deep Learning for RNA Secondary Structure Prediction

Jörg K. H. Franke, Frederic Runge, Frank Hutter
7/14/2023
cs.LGq-bio.BM

Official code: automl/RNAformer (43 stars, Apache-2.0, last commit 2025-09-23).

Abstract

The field of RNA secondary structure prediction has made significant progress with the adoption of deep learning techniques. In this work, we present the RNAformer, a lean deep learning model using axial attention and recycling in the latent space. We gain performance improvements by designing the architecture for modeling the adjacency matrix directly in the latent space and by scaling the size of the model. Our approach achieves state-of-the-art performance on the popular TS0 benchmark dataset and even outperforms methods that use external information. Further, we show experimentally that the RNAformer can learn a biophysical model of the RNA folding process.

View on arXivView PDF

Code Implementations(1)

automl/RNAformerOfficial
Apache-2.0

Scalable Deep Learning for RNA Secondary Structure Prediction

4310Shell, PythonJul 13, 20231 years agoApache-2.0

Similar Papers

Comprehensive benchmarking of large language models for RNA secondary structure prediction

88% match1 repo152024

RNA Secondary Structure Prediction Using Transformer-Based Deep Learning Models

87% match2024

Deep Learning Framework for RNA Inverse Folding with Geometric Structure Potentials

86% match2025

Kirigami: large convolutional kernels improve deep learning-based RNA secondary structure prediction

85% match1 repo42024

A Comprehensive Benchmark for RNA 3D Structure-Function Modeling

83% match1 repo462025

RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks

82% match2 repos3862024

Cite this paper

@article{franke2023scalable,
  title  = {Scalable Deep Learning for RNA Secondary Structure Prediction},
  author = {Jörg K. H. Franke and Frederic Runge and Frank Hutter},
  year   = {2023},
  eprint = {2307.10073},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.10073v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.10073.svg)](https://codeofpaper.com/paper/2307.10073)

Discussion