Dyna-1 Model for Predicting Millisecond Protein Dynamics Published in Nature
chaitjo · x · 2026-08-11
The Dyna-1 model has been officially published in Nature. By curating over 100 Nuclear Magnetic Resonance (NMR) relaxation datasets, researchers discovered that micro-to-millisecond protein dynamics can be inferred from missing signals in NMR spectra.
Trained on this massive experimental data, the Dyna-1 model effectively predicts conformational interconversions at the millisecond timescale. This work addresses the historical lack of standardized large-scale data, providing a new predictive tool for understanding protein biological functions.
Related event: Nature Publishes Protein Dynamics Model Dyna-1(2 posts)→
More from Research
- Beyond the Paper: Why Research Artifacts Should Be Science's Basic Unit — valis2400 · 2026-09-21
- BindCraft2 protein design suite launches with full open-source code, free for academic and industry use — mmbronstein · 2026-09-21
- Simpler proof of Komlós conjecture posted to arXiv by Karingula and Lovett — stevenstrogatz · 2026-09-21
- Komlós conjecture solution announced, with overlooked implications for neural network quantization — stevenstrogatz · 2026-09-21
- CIC + LEM surprisingly proves Con(ZF), a breakthrough found with AI tool Fable — leloykun · 2026-09-21
- Qwen presents OmniVChat: synthesized data, benchmark and RL for native audio-visual dialogue — Qwen · 2026-09-21