AnnoGCD: a generalized category discovery framework for automatic cell type annotation
Francesco Ceccarelli, Pietro Liò, Sean B Holden · 2024
Read AnnoGCD: a generalized category discovery framework for automatic cell type annotation by Francesco Ceccarelli, Pietro Liò, Sean B Holden (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-11629990.txt.
Description
Francesco Ceccarelli and co-authors present AnnoGCD, a tool that labels cell types in single cell gene data, in a 2024 paper. Hand labeled training sets are costly, and new cell types keep turning up. A tool that only knows fixed labels misses them.
AnnoGCD mixes a small labeled set with raw data. A first block sorts the known types, and a second block hunts for new clusters on its own. Tests ran on five human data sets and a mouse atlas. The tool beat rivals on both known and new types, and it held up when some types were rare. Code and data are posted in public.
Catalog record
| CREATOR | Francesco Ceccarelli, Pietro Liò, Sean B Holden |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |