skills.rest
SciMate-AI
SciMate-AIOFFICIAL
Explore all skills by this author →
GitHub

scvi-tools

Train probabilistic single-cell models on raw-count AnnData for batch correction and integration.

1|Updated Mar 11, 2026
Search Tags:#multimodal#single-cell#batch-correction#scRNA-seq#differential-expression#bayesian#variational-inference
One-click install
npx skills add https://github.com/SciMate-AI/scicli --skill scvi-tools-scimate-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scvi-tools
Source: https://github.com/SciMate-AI/scicli/tree/main/internal/skills/bundled/claude-scientific-skills/skills/scvi-tools
Command: npx skills add https://github.com/SciMate-AI/scicli --skill scvi-tools-scimate-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

scvi-tools provides probabilistic models and workflows for single-cell genomics, enabling batch correction, imputation, differential expression, and multi-modal integration with uncertainty quantification.

Core Features & Use Cases

  • Batch correction and data integration across scRNA-seq experiments (scVI, SCANVI)
  • Multimodal modeling and integration (TOTALVI, MultiVI, MrVI, DESTVI)
  • Trajectory inference, RNA velocity, and perturbation analysis (VeloVI, CONTRASTIVEVI, Decipher)
  • Differential expression with Bayesian FDP control and posterior summarization
  • Flexible workflows for RNA, ATAC, methylation, and cytometry data
  • Model deployment and inference with scalable, GPU-accelerated training

Quick Start

Train a standard scVI model on your raw-count AnnData to obtain a batch-corrected latent space and start downstream analyses.

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 with uncertainty quantification?▼

Batch correction on scRNA-seq data with uncertainty quantification uses probabilistic models like scVI to generate a batch-corrected latent space from raw-count AnnData, handling covariates robustly during GPU-accelerated training.

Can I integrate multimodal single-cell datasets combining RNA and ATAC data?▼

Integrating multimodal single-cell datasets combining RNA and ATAC uses models like MultiVI and TOTALVI, processing raw-count AnnData to jointly model multi-omics data and output a unified latent space.

What is the best way to run differential expression analysis for single-cell genomics?▼

Differential expression analysis for single-cell genomics uses Bayesian FDP control and posterior summarization to identify genes, leveraging trained probabilistic models to compute expression differences with uncertainty.

Does this probabilistic single-cell analysis workflow support trajectory inference and RNA velocity?▼

Probabilistic single-cell analysis supports trajectory inference and RNA velocity using specialized models like VeloVI and Decipher, extending raw-count AnnData workflows to infer dynamic cellular trajectories.

Do I need raw-count AnnData to train variational inference models for single-cell integration?▼

Training variational inference models for single-cell integration requires raw-count AnnData input, following a consistent setup-train-then-extract API to handle batch effects and covariates during GPU-accelerated model training.

When should I use probabilistic models over standard tools for single-cell multimodal integration?▼

Probabilistic models are suited for complex single-cell multimodal integration when you need uncertainty quantification, batch correction across diverse experiments, and joint modeling of RNA, ATAC, methylation, and cytometry data.

Related Skills

Explore More Data & Analytics Skills→
Victory-HugoVictory-Hugo
1

scvi-tools

Run scvi-tools deep generative models on single-cell RNA sequencing data.

Community
Advanced
tondevreltondevrel
19

scanpy

Analyze single-cell gene expression data with AnnData and scRNA-seq workflows.

Community
Advanced
ovachieverovachiever
52

tensorrt-llm

Optimize LLM inference on NVIDIA GPUs with TensorRT-LLM.

Community
Advanced
biomaps-infrabiomaps-infra

bio-scvi-tools

Train SCVI models on single-cell RNA-seq data with AnnData.

Official
Advanced