DeepPTMPred: a multi-modal deep learning framework for accurate prediction of protein post-translational modification sites
Chenkui Wang, Qianhui Jiang, Dan Yu, Jiahui Guan, Zimeng Chen, Xiaoling Lu, Bin Yan, Jing Qin, Yong Liu, Junwen Wang · 2026
Read DeepPTMPred: a multi-modal deep learning framework for accurate prediction of protein post-translational modification sites by Chenkui Wang, Qianhui Jiang, Dan Yu, Jiahui Guan, Zimeng Chen, Xiaoling Lu, Bin Yan, Jing Qin, Yong Liu, Junwen Wang (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-13275012.txt.
Description
Chenkui Wang and co-authors built DeepPTMPred in 2026, a model that predicts where proteins are marked after they are made. Such marks steer cell work, but lab hunts for them are slow. The model handles seventeen mark types at once, blending the protein sequence, its folded shape from AlphaFold, and patterns from its evolution. Its CNN-Transformer core reads close links in the sequence, while the other inputs add space and context.
Scores were high for four mark types, by area under the curve. Hydroxylation reached ninety-six point five, and malonylation ninety-one point six. O-linked glycosylation reached ninety-one point zero, and phosphorylation eighty-nine point five. On tau, the model found known phosphorylation sites. It also flagged two new sites tied to early tangle stages and early Alzheimer disease. The team sees the tool aiding work on sites and what they do.
Catalog record
| CREATOR | Chenkui Wang, Qianhui Jiang, Dan Yu, Jiahui Guan, Zimeng Chen, Xiaoling Lu, Bin Yan, Jing Qin, Yong Liu, Junwen Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |