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.
BSD 3-Clause "New" or "Revised" License
76
stars
17
forks
source link
Predicting the gene expression on a new anndata variable with specific perturbation. #39
I am trying to prediction the gene expression level of the trained model on a testing set of my anndata where I want to predict how the cells response to the perturbation given a condition as an input.
Is there a function like that in CPA model as I tried to find in the tutorial and API and it doesn't seem to have.
Dear Authors,
I am trying to prediction the gene expression level of the trained model on a testing set of my anndata where I want to predict how the cells response to the perturbation given a condition as an input.
Is there a function like that in CPA model as I tried to find in the tutorial and API and it doesn't seem to have.
Thanks with Warm regards,
Rom Uddamvathanak