
scvi-tools
Probabilistic, deep-learning models for single-cell omics
scvi-tools packages a suite of probabilistic deep-generative models for single-cell data, built on PyTorch and integrated with the scverse/AnnData ecosystem.
Models
- scVI — dimensionality reduction, batch correction and normalisation.
- scANVI — semi-supervised label transfer.
- totalVI / MultiVI — CITE-seq and multiomic integration.
Related tools

Open source

Open source

Free for academia
Single-Cell & Spatial
Arc State
A virtual cell model predicting perturbation responses
Python libraryModel weights