scvi-tools

Train PyTorch-based VAE models on AnnData for single-cell analysis.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Org-GAgent/result-interpreter --skill scvi-tools-org-gagent
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scvi-tools
Source: https://github.com/Org-GAgent/result-interpreter/tree/main/.skills/scientific-skills/scvi-tools
Command: npx skills add https://github.com/Org-GAgent/result-interpreter --skill scvi-tools-org-gagent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

scvi-tools provides a principled probabilistic framework for analyzing and integrating single-cell data across batches and modalities, enabling batch correction, differential expression, imputation, and multimodal analyses.

Core Features & Use Cases

  • Unified API for scRNA-seq, scATAC-seq, CITE-seq, spatial transcriptomics and multi-omics
  • End-to-end workflows including data registration, latent space learning, differential expression, and imputation
  • Supports batch-corrected analyses, probabilistic DE testing, and multimodal integration with shared latent representations
  • Real-world use cases include cross-batch integration, cross-modality annotation, and multi-condition trajectory analysis
  • Extensible with external tools and adapters for large-scale single-cell projects

Quick Start

Train a model on your AnnData with scvi-tools to obtain a joint latent representation and start downstream analysis.

Frequently Asked Questions about scvi-tools

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

FAQPage Schema
How do I perform batch correction on scRNA-seq data using a probabilistic model?▼

Multimodal integration for CITE-seq and spatial transcriptomics applies a unified API to learn shared latent representations across modalities. This enables cross-modality annotation and joint downstream analyses.

Can I use Bayesian differential expression testing for single-cell data across multiple conditions?▼

scvi-tools supports scRNA-seq, scATAC-seq, CITE-seq, and spatial transcriptomics through a unified API. This multimodal coverage enables cross-modality annotation and multi-omics integration within a single probabilistic framework.

What is the best way to integrate multimodal single-cell data like CITE-seq and spatial transcriptomics?▼

Multimodal integration for CITE-seq and spatial transcriptomics applies a unified API to learn shared latent representations across modalities. This enables cross-modality annotation and joint downstream analyses.

Do I need AnnData formatted objects to run scvi-tools workflows?▼

Bayesian differential expression testing for single-cell data provides probabilistic framework p-values across multiple conditions. It operates within end-to-end workflows to identify statistically significant gene expression changes.

Does scvi-tools support scATAC-seq and spatial transcriptomics for multimodal integration?▼

scvi-tools supports scRNA-seq, scATAC-seq, CITE-seq, and spatial transcriptomics through a unified API. This multimodal coverage enables cross-modality annotation and multi-omics integration within a single probabilistic framework.

How does the VAE encoder-decoder architecture handle single-cell imputation and latent representations?▼

The VAE encoder-decoder architecture handles single-cell imputation by probabilistically reconstructing missing values while learning latent representations. This PyTorch-based approach enables standardized batch-corrected analyses.