Targeting the intrinsically disordered AR-NTD through a machine learning-based enhanced sampling workflow
Kai Zhu, Huating Wang, Jintu Zhang, Renling Hu, Linlong Jiang, Hui Zhang, Yu Kang, Tingjun Hou, Dan Li · 2026
Read Targeting the intrinsically disordered AR-NTD through a machine learning-based enhanced sampling workflow by Kai Zhu, Huating Wang, Jintu Zhang, Renling Hu, Linlong Jiang, Hui Zhang, Yu Kang, Tingjun Hou, Dan Li (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-13396667.txt.
Description
Zhu and co-authors attack, in 2026, one of drug design's hardest targets. It is the intrinsically disordered N-terminal domain of the androgen receptor, a prostate cancer driver with no stable shape to grip. They built a computational workflow built on enhanced sampling with machine learning collective variables. Using the known modulator EPI-002 as a probe, they mapped the Tau-5 region of the domain in detail.
The simulations mapped nine metastable states of Tau-5. They showed ligand recognition runs on pi-pi stacking plus hydrogen bonds, mediated by structured water molecules trapped at the interface. Screening compound libraries against the druggable shapes they found yielded K53, a designed blocker that binds the domain directly and shuts down androgen receptor transcription. K53 showed potent activity against enzalutamide-resistant prostate cancer cells, sparing normal cells, a relevant advance since receptor variants appear in nearly 40 percent of castration-resistant cases.
Catalog record
| CREATOR | Kai Zhu, Huating Wang, Jintu Zhang, Renling Hu, Linlong Jiang, Hui Zhang, Yu Kang, Tingjun Hou, Dan Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 80 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |