A highly efficient, scalable pipeline for fixed feature extraction from large-scale high-content imaging screens
Gabriel Comolet, Neeloy Bose, Jeff Winchell, Alyssa Duren-Lubanski, Tom Rusielewicz, Jordan Goldberg, Grayson Horn, Daniel Paull, Bianca Migliori · 2024
Read A highly efficient, scalable pipeline for fixed feature extraction from large-scale high-content imaging screens by Gabriel Comolet, Neeloy Bose, Jeff Winchell, Alyssa Duren-Lubanski, Tom Rusielewicz, Jordan Goldberg, Grayson Horn, Daniel Paull, Bianca Migliori (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-11667173.txt.
Description
Gabriel Comolet and eight co-authors set out ScaleFEx, a lean pipeline to pull fixed traits from large image screens of cells. Shape based maps of cells, read with AI, can show disease states and drug effects the eye cannot see. Large screens give the repeat runs that sound models need. But image data with many traits strain the work of study.
The open source Python pipeline pulls traits with real sense from the images. It runs on small kit or on cloud farms that scale. Paired with AI models, it spots shifts in the shape of drug dosed cells. It also ranks which traits can be read with sense. It works on shared data sets too. The design aims to speed finds of disease linked cell shapes and new drugs, with no need for huge compute funds.
Catalog record
| CREATOR | Gabriel Comolet, Neeloy Bose, Jeff Winchell, Alyssa Duren-Lubanski, Tom Rusielewicz, Jordan Goldberg, Grayson Horn, Daniel Paull, Bianca Migliori |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |