scvi-tools

Analyze single-cell RNA-seq data with scvi-tools deep generative models.

13|3|Updated Jun 10, 2026

Search Tags:#deep learning #single-cell RNA-seq #batch correction #differential expression #variational inference

Ready to run

npx skills add https://github.com/tassiovale/claude-code-kit --skill scvi-tools-tassiovale

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: scvi-tools
Source: https://github.com/tassiovale/claude-code-kit/tree/main/skills/scvi-tools
Command: npx skills add https://github.com/tassiovale/claude-code-kit --skill scvi-tools-tassiovale

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires scvi-tools, scanpy, pytorch, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenges of analyzing complex single-cell data by providing deep generative models and probabilistic inference, enabling advanced data analysis tasks such as dimensionality reduction, batch correction, and differential expression.

Core Features & Use Cases

Deep Generative Models: Utilizes variational autoencoders for dimensionality reduction and batch correction.
Probabilistic Inference: Offers uncertainty quantification and statistical testing for robust analysis.
Use Case: For instance, you can use this Skill to perform batch correction on single-cell RNA-seq data, identify differentially expressed genes, and analyze cell type annotation.

Quick Start

Use the scvi-tools skill to perform batch correction on your single-cell RNA-seq data.

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 single-cell RNA-seq data?▼

Batch correction for single-cell RNA-seq data is achieved by training deep generative models with variational inference. This approach uses variational autoencoders to align data across different batches while preserving biological variance.

Can I identify differentially expressed genes using variational inference?▼

Yes, variational inference enables differential expression analysis by providing uncertainty quantification and statistical testing. This probabilistic approach ensures robust identification of differentially expressed genes in complex datasets.

What is the best way to reduce dimensions in single-cell RNA-seq datasets?▼

Dimensionality reduction in single-cell RNA-seq datasets is best handled using deep generative models. By leveraging variational autoencoders, the process captures non-linear relationships to produce a lower-dimensional representation for downstream analysis.

Do I need PyTorch to run deep generative models for single-cell analysis?▼

Yes, PyTorch is required as a dependency to run deep generative models for single-cell analysis. The framework provides the foundational backend for variational inference and model training.

When should I use deep learning for cell type annotation instead of traditional methods?▼

Deep learning for cell type annotation is ideal when dealing with complex single-cell data requiring batch correction and uncertainty quantification. Probabilistic inference provides statistically robust annotations that traditional methods often lack.