skills.rest
Hung-3008
Hung-3008COMMUNITY
Explore all skills by this author →
GitHub

scvi-tools

Train scvi-tools models on single-cell omics data for batch correction and uncertainty quantification.

1|Updated Mar 4, 2026
Search Tags:#multimodal#single-cell#batch-correction#scRNA-seq#scvi-tools#differential-expression#probabilistic-models
One-click install
npx skills add https://github.com/Hung-3008/agusta --skill scvi-tools-hung-3008
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scvi-tools
Source: https://github.com/Hung-3008/agusta/tree/main/.agents/skills/scvi-tools
Command: npx skills add https://github.com/Hung-3008/agusta --skill scvi-tools-hung-3008

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

scvi-tools provides probabilistic, deep generative models for single-cell omics to jointly model RNA, proteins, and chromatin accessibility, enabling batch correction and uncertainty quantification across modalities.

Core Features & Use Cases

  • Probabilistic modeling for scRNA-seq, scATAC-seq, and multimodal data
  • Batch correction, differential expression with uncertainty, and transfer learning
  • Joint latent representations for clustering and downstream analyses
  • GPU-accelerated workflows and Scanpy integration
  • Models include scVI, TOTALVI, MultiVI, PeakVI, DestVI, and more for diverse modalities

Quick Start

Install scvi-tools, load your data into an AnnData object, register covariates with setup_anndata, and run train to obtain a latent representation for 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 correct batch effects in scRNA-seq data using probabilistic models?▼

You correct batch effects in scRNA-seq data by loading raw counts into an AnnData object, registering covariates via setup_anndata, and training a probabilistic model like scVI to extract a corrected latent representation.

What is the best way to integrate multimodal single-cell data like RNA and chromatin accessibility?▼

Multimodal single-cell integration is handled by training deep generative models like MultiVI to jointly model RNA and chromatin accessibility, producing a shared latent space for clustering and downstream analysis.

Can I perform differential expression analysis with uncertainty quantification for scRNA-seq?▼

Differential expression with uncertainty quantification in scRNA-seq is performed by training a probabilistic model and using its APIs to extract posterior estimates, yielding statistically robust differential results.

Does scvi-tools work with Scanpy and require GPU acceleration?▼

scvi-tools integrates directly with Scanpy for downstream analyses and supports GPU-accelerated workflows to efficiently train deep generative models on large-scale single-cell datasets.

Do I need raw count data in AnnData format to run scvi-tools models?▼

Raw count data in AnnData format is required to run scvi-tools models. You must load your single-cell data into an AnnData object and register covariates before initializing and training.

When should I use transfer learning for scRNA-seq data?▼

Transfer learning for scRNA-seq data is used when applying a trained probabilistic model to new data via SCANVI, enabling label transfer and integrating new samples into an existing latent space.

Related Skills

Explore More Data & Analytics Skills→
Estrella-231Estrella-231

scvi-tools

Model single-cell omics data and correct batch effects with scvi-tools.

Community
Advanced
Victory-HugoVictory-Hugo
1

scanpy

Perform end-to-end single-cell RNA-seq analysis with Scanpy.

Community
Intermediate
Estrella-231Estrella-231

scanpy

Run scanpy workflows on AnnData objects for single-cell RNA-seq preprocessing and exploratory analysis.

Community
Intermediate
CHENyiru3CHENyiru3

scvi-tools

Train scVI models on AnnData for batch-corrected latent representations.

Community
Advanced