A Graph-Based Deep Learning Framework with Gating and Omics-Linked Attention for Multi-Omics Integration and Biomarker Discovery
Zhanpeng Huang, Yutao Deng, Jinyuan Liu, Zhaohan Cai, Zongliang Yue · 2025
Read A Graph-Based Deep Learning Framework with Gating and Omics-Linked Attention for Multi-Omics Integration and Biomarker Discovery by Zhanpeng Huang, Yutao Deng, Jinyuan Liu, Zhaohan Cai, Zongliang Yue (2025) 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-12731160.txt.
Description
Zhanpeng Huang and co-authors fuse several omics data layers with a deep learning framework that explains its own choices, in a 2025 paper. Combining the layers promises sharper disease sorting and marker hunting, but the data are vast and mismatched. Their framework, MOGOLA, first learns within each layer using two graph network styles. A gating step then weighs how much each layer counts, and an attention step mixes the layers together.
On four benchmark datasets, the framework beat eleven rival methods. Removing any module hurt performance, confirming each part's value. The markers it surfaced carry clinical promise. The authors present the system as both accurate and readable, a pairing modern medicine needs.
Catalog record
| CREATOR | Zhanpeng Huang, Yutao Deng, Jinyuan Liu, Zhaohan Cai, Zongliang Yue |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |