scvi-tools

import scvi import scanpy as sc import numpy as np # For reproducibility scvi.settings.seed = 0 # Load a dataset # In a real scenario, you'd load your own AnnData object # For this example, we'll use a built-in dataset adata = scvi.data.pbmc_dataset() # Required step: set up AnnData for scvi-tools models # This registers the data with scvi-tools, specifying layers, batch keys, etc. scvi.data.setup_anndata(adata, layer="counts", batch_key="batch") # Initialize the SCVI model model = scvi.model.SCVI(adata, n_latent=30, n_layers=2) # Train the model # This can take several minutes depending on hardware and dataset size model.train() # Get latent representation and store it in adata.obsm adata.obsm["X_scVI"] = model.get_latent_representation() # Get normalized expression and store it in adata.layers adata.layers["scvi_normalized"] = model.get_normalized_expression(transform_batch="_scvi_batch_0") print(f"Latent representation shape: {adata.obsm['X_scVI'].shape}") print(f"Normalized expression layer shape: {adata.layers['scvi_normalized'].shape}") # Further analysis could involve using scanpy on the latent space # sc.pp.neighbors(adata, use_rep="X_scVI") # sc.tl.umap(adata) # sc.pl.umap(adata, color=["cell_type", "batch"])