Decoupling topological and molecular features for interpretable biomolecular interaction prediction
Qi Wu, Yinbo Liu, Feng Yang, Weihong Huang, Xiaolei Zhu, Juan Liu · 2026
Read Decoupling topological and molecular features for interpretable biomolecular interaction prediction by Qi Wu, Yinbo Liu, Feng Yang, Weihong Huang, Xiaolei Zhu, Juan Liu (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-13544631.txt.
Description
Qi Wu and co-authors present FlexBIP, a flexible framework for predicting interactions between biomolecules, in a 2026 paper. Such predictions underpin cell biology and drug discovery, yet most tools handle one task or one data type, which limits their reach. Their design splits a molecule's own features from the web of connections it sits in, then fuses the two adaptively.
Node traits, link properties, and extra graph information can all enter as available. The same frame covers same-type and mixed-type interactions, plus yes-no, multi-class, and numeric predictions. Tests across fifteen benchmark datasets spanning eight task types are reported as strong.
Catalog record
| CREATOR | Qi Wu, Yinbo Liu, Feng Yang, Weihong Huang, Xiaolei Zhu, Juan Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |