Back

Ribonanza: deep learning of RNA structure through dual crowdsourcing

He, S.; Huang, R.; Townley, J.; Kretsch, R. C.; Karagianes, T. G.; Cox, D. B. T.; Blair, H.; Penzar, D.; Vyaltsev, V.; Aristova, E.; Zinkevich, A.; Bakulin, A.; Sohn, H.; Krstevski, D.; Fukui, T.; Tatematsu, F.; Uchida, Y.; Jang, D.; Lee, J. S.; Shieh, R.; Ma, T.; Martynov, E.; Shugaev, M. V.; Bukhari, H. S. T.; Fujikawa, K.; Onodera, K.; Henkel, C.; Ron, S.; Romano, J.; Nicol, J. J.; Nye, G. P.; Wu, Y.; Choe, C.; Reade, W.; Eterna participants, ; Das, R.

2024-02-27 biophysics
10.1101/2024.02.24.581671 bioRxiv
Show abstract

Prediction of RNA structure from sequence remains an unsolved problem, and progress has been slowed by a paucity of experimental data. Here, we present Ribonanza, a dataset of chemical mapping measurements on two million diverse RNA sequences collected through Eterna and other crowdsourced initiatives. Ribonanza measurements enabled solicitation, training, and prospective evaluation of diverse deep neural networks through a Kaggle challenge, followed by distillation into a single, self-contained model called RibonanzaNet. When fine tuned on auxiliary datasets, RibonanzaNet achieves state-of-the-art performance in modeling experimental sequence dropout, RNA hydrolytic degradation, and RNA secondary structure, with implications for modeling RNA tertiary structure.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.