A machine learning framework for predicting and modulating condition-dependent protein phase separation
Jangwon Bae, Minjun Kang, Donghyuk Lee, Kuk-Jin Yoon, Yongwon Jung · 2026
Read A machine learning framework for predicting and modulating condition-dependent protein phase separation by Jangwon Bae, Minjun Kang, Donghyuk Lee, Kuk-Jin Yoon, Yongwon Jung (2026) 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/PMC13527070.txt.
Description
Bae and colleagues introduce LLPSense in 2026, a machine learning framework that predicts when proteins will separate into droplet-like clusters inside cells. This process, called phase separation, builds membrane-free cell compartments, but it shifts with protein amount, temperature, and the surrounding fluid, which older sequence-only models ignore.
LLPSense combines protein language model summaries with these environmental inputs, and lab tests confirmed its predictions. It revealed complex temperature-linked behavior in the protein SGTA, which was not known to phase separate before. It also correctly predicted which changes to alpha-synuclein, a protein linked to Parkinson's disease, would raise or lower separation. Guided by the model, the team could tune phase behavior on purpose through chosen mutations.
Catalog record
| CREATOR | Jangwon Bae, Minjun Kang, Donghyuk Lee, Kuk-Jin Yoon, Yongwon Jung |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 69 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |