scVAG: Unified single-cell clustering via variational-autoencoder integration with Graph Attention Autoencoder
Seyedpouria Laghaee, Morteza Eskandarian, Mohammadamin Fereidoon, Somayyeh Koohi · 2024
Read scVAG: Unified single-cell clustering via variational-autoencoder integration with Graph Attention Autoencoder by Seyedpouria Laghaee, Morteza Eskandarian, Mohammadamin Fereidoon, Somayyeh Koohi (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-11648904.txt.
Description
Seyedpouria Laghaee and co-authors present a 2024 paper on grouping single cells by their gene activity. Single-cell sequencing reveals how cells differ, yet its data are noisy and vast. Their system, scVAG, fuses two deep learning parts: a variational autoencoder and a graph attention autoencoder, replacing a stiff linear step in an earlier method.
Across twenty data sets, scVAG beat a dozen rival clustering tools. Scores rose about five percent on one standard index and four on another. Pictures of the learned space showed clean clusters that matched the true cell labels. The compact codes it learns capture fine expression patterns that linear methods flatten. Better clusters help biologists spot rare cell types and disease states.
Catalog record
| CREATOR | Seyedpouria Laghaee, Morteza Eskandarian, Mohammadamin Fereidoon, Somayyeh Koohi |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |