MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification.
Wang T, Shao W, Huang Z, Tang H, Zhang J, Ding Z, Huang K. · 2021
Read MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification. by Wang T, Shao W, Huang Z, Tang H, Zhang J, Ding Z, Huang K. (2021) 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/europmc-pmc8187432.txt.
Description
Wang and co-authors present MOGONET, a method that merges multi-omics data for patient sorting. Single data types give only part of the picture of a disease. Their graph network learns from each omics type and from links across types.
The method used mRNA, DNA methylation, and microRNA data together. The authors report that it beat other leading integration methods on several tasks. It also flagged biomarkers tied to the classes it found. Graph learning lets patient similarity guide the sorting. The tool aims at sharper diagnosis from combined molecular data.
Catalog record
| CREATOR | Wang T, Shao W, Huang Z, Tang H, Zhang J, Ding Z, Huang K. |
|---|---|
| YEAR | 2021 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 89 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |