Improving protein and protein interactions using pseudo-dimers derived from monomeric proteins
Hao Du, Xinzhe Zheng, Yuchen Ren, He Huang, Xinqi Gong, Wanli Ouyang, Yang Zhang, Yan Lu · 2026
Read Improving protein and protein interactions using pseudo-dimers derived from monomeric proteins by Hao Du, Xinzhe Zheng, Yuchen Ren, He Huang, Xinqi Gong, Wanli Ouyang, Yang Zhang, Yan Lu (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-13392253.txt.
Description
Hao Du's team better protein-protein interaction forecast by pre-training on pseudo-dimers built from abundant monomeric proteins, addressing the scarcity of dimer shapes that limits models such as AlphaFold-Multimer and AlphaFold3. Collecting true dimer shapes is expensive and slow.
Their split-and-merge proxy splits monomers into pseudo-sensor and pseudo-ligand halves and trains models to rejoin them by predicting contacts or docking, enabling large-scale pre-training at no extra cost. Fine-tuned models beat strong baselines across benchmarks and surpassed both AlphaFold systems on several CASP15 dimer targets.
Catalog record
| CREATOR | Hao Du, Xinzhe Zheng, Yuchen Ren, He Huang, Xinqi Gong, Wanli Ouyang, Yang Zhang, Yan Lu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |