scvi-tools

Model single-cell omics data with PyTorch-based variational autoencoders for batch correction.

1|Updated Mar 19, 2026

Search Tags:#multimodal #single-cell #annotation #batch-correction #scvi-tools #differential-expression #probabilistic

Ready to run

npx skills add https://github.com/JosephWoodall/noosphere --skill scvi-tools-josephwoodall

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: scvi-tools
Source: https://github.com/JosephWoodall/noosphere/tree/main/.agent/skills/scvi-tools
Command: npx skills add https://github.com/JosephWoodall/noosphere --skill scvi-tools-josephwoodall

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

scvi-tools enables probabilistic modeling of single-cell data to denoise, integrate across batches, and combine multiple modalities in a principled Bayesian framework.

Core Features & Use Cases

End-to-end probabilistic models for scRNA-seq (scVI) and multimodal data (TOTALVI, MultiVI) with batch correction and uncertainty quantification
Semi-supervised annotation, trajectory and velocity extensions, and differential expression analysis
Multimodal and cross-domain integration (RNA, protein, ATAC) with transfer learning and cross-modality imputation
Consistent API and seamless interoperability with AnnData/Scanpy for scalable workflows
Robust reference mapping, visualization, and downstream statistical analyses

Quick Start

Install scvi-tools, prepare raw count data in AnnData, train a model (SCVI or TOTALVI), and obtain latent representations for downstream analysis.

Frequently Asked Questions about scvi-tools

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How does probabilistic batch correction work for single-cell RNA-seq data?▼

Probabilistic batch correction for single-cell RNA-seq data uses a PyTorch-based variational autoencoder with amortized inference to learn robust latent representations. This Bayesian framework denoises data and integrates multiple studies while quantifying uncertainty across batches.

Can I integrate multimodal datasets like ATAC-seq and RNA-seq together?▼

Yes, you can integrate multimodal datasets like ATAC-seq and RNA-seq together using probabilistic models designed for cross-domain integration. This framework supports RNA, protein, and ATAC modalities, enabling cross-modality imputation and combined analysis across multiple studies.

How do I perform semi-supervised cell-type annotation on scRNA-seq counts?▼

To perform semi-supervised cell-type annotation on scRNA-seq counts, prepare raw count data in AnnData format and train a probabilistic model. The framework learns latent representations that enable semi-supervised annotation alongside trajectory and velocity extensions.

What is the best way to run differential expression analysis after batch correction?▼

The best way to run differential expression analysis after batch correction is to use the latent representations from the trained variational autoencoder. This probabilistic framework provides downstream statistical analyses, including differential expression, directly on the learned representations.

Does this single-cell integration framework work with AnnData and Scanpy workflows?▼

Yes, this single-cell integration framework works with AnnData and Scanpy workflows. It offers a consistent API and seamless interoperability with AnnData for scalable workflows, requiring raw count data to be prepared in AnnData format before model training.

When should I use variational autoencoders for single-cell omics data integration?▼

You should use variational autoencoders for single-cell omics data integration when you need to denoise datasets, correct batch effects across multiple studies, or combine modalities like methylation and RNA-seq in a principled Bayesian framework with uncertainty quantification.