Deep generative models for single-cell genomics built on PyTorch. Handles batch correction (scVI), multimodal integration (TOTALVI, MultiVI), spatial deconvolution (DestVI), and probabilistic differential expression. The API is consistent across models: setup your AnnData with raw counts, register covariates, train, extract latents. Works well when you need uncertainty quantification or complex batch effects that simpler methods struggle with. Models live in either scvi.model or scvi.external namespaces, which matters for imports. Requires Python 3.12+ as of version 1.4. For basic preprocessing and clustering, stick with scanpy. Use this when you need the statistical rigor of variational inference or when integrating messy multi-batch datasets.
npx skills add https://github.com/k-dense-ai/scientific-agent-skills --skill scvi-tools