Learning the PTM code through a coarse-to-fine mechanism-aware framework
Jingjie Zhang, Hanqun Cao, Zijun Gao, Yu Wang, Shaoning Li, Jun Xu, Cheng Tan, Jun Zhu, Chang-Yu Hsieh, Chunbin Gu, Pheng Ann Heng · 2026
Read Learning the PTM code through a coarse-to-fine mechanism-aware framework by Jingjie Zhang, Hanqun Cao, Zijun Gao, Yu Wang, Shaoning Li, Jun Xu, Cheng Tan, Jun Zhu, Chang-Yu Hsieh, Chunbin Gu, Pheng Ann Heng (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/pmc-13377107.txt.
Description
Jingjie Zhang and co-authors build a model that reads the code of marks placed on proteins after they are made, in work from 2026. Those marks, called post-translational modifications, steer how proteins act and how cells signal. The hard part is to call both where marks land and which enzyme put them there.
Their model, COMPASS-PTM, learns in two sweeps, from broad strokes to fine ones. It starts from a protein language model and adds facts on shape and charge, plus a prompt that codes how marks help or block each other. On large tests, it beat the best past tools by wide gaps on both jobs. It also found known enzyme marks and tied gene faults to mark shifts, which helps users trust its calls.
Catalog record
| CREATOR | Jingjie Zhang, Hanqun Cao, Zijun Gao, Yu Wang, Shaoning Li, Jun Xu, Cheng Tan, Jun Zhu, Chang-Yu Hsieh, Chunbin Gu, Pheng Ann Heng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 84 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |