theislab/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.
PythonBSD-3-Clause
Stargazers
- akundajeStanford University
- ArianAmaniWellcome Sanger Institute
- asarigunBerlin Institute for Medical Systems Biology
- Biophysics-1998
- bitcometz
- bulbgodCincinnati Children's
- CaibinSh@gv20-therapeutics
- Candlelight-XYJ
- changebioColumbia University
- Charlesyip2016
- Ci-TJ
- cnk113University of California San Francisco
- DotBlotUniversity of Wisconsin - Madison
- fmollandinCRG
- fredmonroesplat.ai
- GA-1101CNSFA
- GilbertHan1011
- harshameghadriMedical University of Hannover (MHH)
- HarshaSatyavardhanindia
- HesamAsadUniversity of Tehran
- josephdvivianoMila - Quebec AI Institute
- LongHung-Pham
- lzlniuNovo Nordisk A/S
- mdmanurungLeiden, The Netherlands
- mxhmNationwide Children's Hospital
- Reemann
- roayaeiMeta
- RuiyuRayWangChinese Institute for Brain Research, Beijing
- rzzli
- TrumanZYXCapital Medical University
- wook2014
- wt12318ShanghaiTech Unviersity
- yanqi219San Diego
- yanwu2014Altos Labs
- yiqunchen
- zhoujoeyyiInstitute of Neuroscience, Chinese Academy of Sciences