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
Issues
- 2
Bug in sciplex3 preprocessing?
#4 opened by mughetto - 1
- 2
Issues regarding the model training process
#14 opened by hxzhu491 - 0
datasets question
#17 opened by DingMaolinBio - 0
dose response
#15 opened by xqz1995 - 0
Hyperparameter Sweep
#12 opened by yanwu2014 - 0
one-hot encoder of control
#9 opened by yjgeno - 0
- 0
Question in the paper
#5 opened by meghbhalerao - 1
- 1
raw/processed datasets available?
#2 opened by juliachen123