Scvi Tools

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.

skills.sh installs: 2K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill scvi-tools --agent claude-code

Installs into .claude/skills of the current project.

Files

scvi-tools

Targets scvi-tools 1.5.1, released September 10, 2026. APIs below were checked against the tagged source and official documentation. The examples are illustrative: the repository tests exercise short CPU synthetic fits for SCVI, SCANVI, TOTALVI, MULTIVI, METHYLVI, PEAKVI and POISSONVI, plus count-preserving preprocessing, DE output contracts, save/load and minification. The tested stack is Python 3.13, Scanpy 1.12.4, AnnData 0.13.4, MuData 0.4.1, PyTorch 2.14.1 and Lightning 2.6.6. Long training, hardware-specific paths and other specialized workflows remain illustrative; these checks do not establish convergence or biological validity.