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.
anndata 0.10.0 updated changed a class name from SparseDataset to BaseCompressedSparseDataset and scvi-tools has not updated to be compatible yet.
Changing anndata to 0.9.2
anndata0.10.0 updated changed a class name fromSparseDatasettoBaseCompressedSparseDatasetandscvi-toolshas not updated to be compatible yet. Changinganndatato 0.9.2