# Scalable Deep Learning for RNA Secondary Structure Prediction

arXiv: https://arxiv.org/abs/2307.10073 · HTML: https://mlsanity.com/paper/2307.10073/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 47 references that are in the map.
- First posted on arXiv 14 Jul 2023.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Axial Attention in Multidimensional Transformers](https://mlsanity.com/paper/1912.12180/) (2019)
- [RNA Secondary Structure Prediction By Learning Unrolled Algorithms](https://mlsanity.com/paper/2002.05810/) (2020)
- [Designing RNA Secondary Structures is Hard](https://mlsanity.com/paper/1710.11513/) (2017)
- [LinearFold: linear-time approximate RNA folding by 5'-to-3' dynamic programming and beam search](https://mlsanity.com/paper/2001.04020/) (2019)
- [Probabilistic Transformer: Modelling Ambiguities and Distributions for RNA Folding and Molecule Design](https://mlsanity.com/paper/2205.13927/) (2022)

## Built on by (most cited first, 3 of 3)

- [A Comprehensive Survey of Foundation Models in Medicine](https://mlsanity.com/paper/2406.10729/) (2024)
- [Rethinking Performance Measures of RNA Secondary Structure Problems](https://mlsanity.com/paper/2401.05351/) (2023)
- [Scaling RNA Foundation Models through Iterative Refinement](https://mlsanity.com/paper/2610.13106/) (2026)

## Abstract (arXiv)

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.