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.
@article{arxiv.2307.10073,
title = {Scalable Deep Learning for RNA Secondary Structure Prediction},
author = {Jörg K. H. Franke and Frederic Runge and Frank Hutter},
journal= {arXiv preprint arXiv:2307.10073},
year = {2023}
}
Comments
Accepted at the 2023 ICML Workshop on Computational Biology. Honolulu, Hawaii, USA, 2023