Predicting microbe-disease associations via graph neural network and contrastive learning
Cong Jiang, Junxuan Feng, Bingshen Shan, Qiyue Chen, Jian Yang, Gang Wang, Xiaogang Peng, Xiaozheng Li · 2024
Read Predicting microbe-disease associations via graph neural network and contrastive learning by Cong Jiang, Junxuan Feng, Bingshen Shan, Qiyue Chen, Jian Yang, Gang Wang, Xiaogang Peng, Xiaozheng Li (2024) 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-11671253.txt.
Description
Cong Jiang and co-authors build a network model that predicts which microbes link to which diseases, in a 2024 paper. Lab proof of such links is slow and costly, so ranked guesses save real effort. Their model, GCATCMDA, learns from known links.
Similarity webs for microbes and for diseases come first. An encoder that mixes graph convolution with attention reads features from each web and from the link web itself. A fusion step blends layer outputs, and contrastive training keeps a node's features steady across webs. A decoder then scores each pair. Tests beat prior methods, and case studies back the model as a working tool.
Catalog record
| CREATOR | Cong Jiang, Junxuan Feng, Bingshen Shan, Qiyue Chen, Jian Yang, Gang Wang, Xiaogang Peng, Xiaozheng Li |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |