MoAGL-SA: a multi-omics adaptive integration method with graph learning and self attention for cancer subtype classification
Lei Cheng, Qian Huang, Zhengqun Zhu, Yanan Li, Shuguang Ge, Longzhen Zhang, Ping Gong · 2024
Read MoAGL-SA: a multi-omics adaptive integration method with graph learning and self attention for cancer subtype classification by Lei Cheng, Qian Huang, Zhengqun Zhu, Yanan Li, Shuguang Ge, Longzhen Zhang, Ping Gong (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-11585958.txt.
Description
Lei Cheng and co-authors sort cancer subtypes by fusing many layers of cell data at once. Their 2024 paper notes that single-layer reads miss links between genes, marks, and RNA that mark a subtype. Prior fusion tools also drop the web of ties between patients, which holds useful shape.
Their method builds a patient graph from each data layer, runs graph networks to embed each layer, then lets self-attention weigh which layers matter for each case. A final classifier names the subtype. On three cancer sets it beat rival tools, the authors report. It also flagged key marker genes for breast cancer, which aids lab follow-up.
Catalog record
| CREATOR | Lei Cheng, Qian Huang, Zhengqun Zhu, Yanan Li, Shuguang Ge, Longzhen Zhang, Ping Gong |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 119 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |