facebookresearch/CPA
The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell level. CPA performs OOD predictions of unseen combinations of drugs, learns interpretable embeddings, estimates dose-response curves, and provides uncertainty estimates.
Jupyter NotebookMIT
Stargazers
- achuthasubhashGUNTUR , INDIA
- ahy1221Peking University
- alreadydoneHeidelberg / Shenzhen
- ankitshah009@cmu-mlsp
- capitulationAnkara, TURKEY
- cdedonnoRoche
- CShorten
- deevdevil88University of Oxford
- diegovalenzuelaiturra@TeselaGen
- elliewithLondon
- eueungInstitut Teknologi Bandung (ITB)
- fengwangEMPA
- fly51flyPRIS
- furkanmtorunExact Sciences
- ggsonic
- GitHub30Osaka, Japan
- gokceneraslanGenentech
- guymitch2007New York, NY
- HiramCilloDecision Point
- jiweiqiMountain View, CA
- jllubia
- jorgegonzalezv
- jusjosgraHealx
- jz314
- kexinhuang12345Bay Area
- kormilitzinUniversity of Oxford
- linnanwangBrown University
- mxhmNationwide Children's Hospital
- neddenriep
- nggihSRW&Co.
- plpxsk@Genentech
- rushtehraniUber
- Salah856https://thefoodlab.com/
- singha53-zzUniversity of British Columbia
- tuan3wHanoi
- vbansal86