multiDGD: A versatile deep generative model for multi-omics data
Viktoria Schuster, Emma Dann, Anders Krogh, Sarah A. Teichmann · 2024
Read multiDGD: A versatile deep generative model for multi-omics data by Viktoria Schuster, Emma Dann, Anders Krogh, Sarah A. Teichmann (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-11579284.txt.
Description
Viktoria Schuster and a team present in a 2024 paper one model that can hold more than one kind of cell data at once. The model is called multiDGD. Labs now read gene use and more in one cell at huge scale. The data grow hard to hold and hard to read. Past models for such mixed data tend to do few tasks, or balk at large sets, which makes joint work slow.
The model learns a shared sketch of gene use and of how open the gene pack is in each cell. It rebuilds the data well with no need to pick traits first. On sets from man and mouse it learns neat groups of cells. It can fold in new sets at a late stage with no fresh train. It can also flag links from genes to the zones that switch them on or off.
Catalog record
| CREATOR | Viktoria Schuster, Emma Dann, Anders Krogh, Sarah A. Teichmann |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 100 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |