RNA-TorsionBERT: leveraging language models for RNA 3D torsion angles prediction
Clément Bernard, Guillaume Postic, Sahar Ghannay, Fariza Tahi, Jianlin Cheng · 2025
Read RNA-TorsionBERT: leveraging language models for RNA 3D torsion angles prediction by Clément Bernard, Guillaume Postic, Sahar Ghannay, Fariza Tahi, Jianlin Cheng (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11758789.txt.
Description
Bernard and co-authors present a 2024 paper on RNA-TorsionBERT, a language model that predicts how RNA chains twist. An RNA strand's 3D fold hinges on the twist angles along its backbone. Guessing those angles from the letter sequence alone would speed structure building. The team adapted the BERT style of language model to read RNA as text.
Wide benchmarks show sharper angle guesses than prior best methods. The model's guesses also power a scoring tool that grades near-native folds without peeking at true angles. That scorer judges structure quality well, the tests show. The authors offer both tools to a field where exact RNA shapes still resist prediction.
Catalog record
| CREATOR | Clément Bernard, Guillaume Postic, Sahar Ghannay, Fariza Tahi, Jianlin Cheng |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 37 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |