FusionPHI: A phage-host interaction prediction network model based on attention-driven multi-modal feature fusion
Xiangjun Li, Ruitao Li, Zhui Tu, Qingting Wei · 2026
Read FusionPHI: A phage-host interaction prediction network model based on attention-driven multi-modal feature fusion by Xiangjun Li, Ruitao Li, Zhui Tu, Qingting Wei (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/plos-pone-0356238.txt.
Description
Xiangjun Li, Ruitao Li, Zhui Tu, and Qingting Wei built FusionPHI, a model that predicts which bacteria a given virus can infect. Phage therapy needs that information before it can match a bacteria-killing virus to a patient's strain. Their 2026 paper feeds the model three views of each partner. They are genome letter statistics, protein chemistry, and evolved gene motif embeddings. A two-stage attention mechanism fuses them.
The model scored strongly on its test data. Ablation tests showed each information stream earns its place, and so does the attention fusion. A case check on a textbook E. coli phage behaved as hoped. Faster, trustworthy matching could make phage therapy practical against antibiotic-resistant infections, instead of a laboratory fishing expedition.
Catalog record
| CREATOR | Xiangjun Li, Ruitao Li, Zhui Tu, Qingting Wei |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 65723 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |