scvi-tools

Name: scvi-tools
Availability: InStock
Author: estrella-231

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

Updated May 24, 2026

Search Tags:#single-cell #batch correction #differential expression #probabilistic modeling #AnnData #multimodal integration

Ready to run

npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill scvi-tools-estrella-231

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: scvi-tools
Source: https://github.com/Estrella-231/Mathematical_modeling_tongmeng/tree/main/.agents/skills/scvi-tools
Command: npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill scvi-tools-estrella-231

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

scvi-tools helps you analyze single-cell omics by learning probabilistic latent representations that reduce technical batch effects while preserving biological signal.

Core Features & Use Cases

Batch correction & integration: Use scVI-style variational models to harmonize multiple batches or studies and enable joint embeddings.
Uncertainty-aware differential expression: Run differential expression with Bayesian testing that quantifies uncertainty and handles zero-inflation.
Multi-modality support: Model RNA, ATAC, protein (CITE-seq), multimodal multi-omics, and spatial transcriptomics via specialized models (e.g., totalVI, PeakVI, MultiVI, DestVI).
Transfer learning & annotation: Perform semi-supervised annotation and query-to-reference transfer using models like scANVI.

Quick Start

Train a model on raw count data in an AnnData object by registering it with setup_anndata and then calling train to obtain a batch-corrected latent embedding.

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 across multiple studies?▼

Batch correction on scRNA-seq data uses probabilistic variational models to learn latent representations that reduce technical batch effects while preserving biological signal. You register raw counts and batch covariates using setup_anndata, then train the model to obtain a harmonized joint embedding.

Can I integrate multimodal single-cell data like CITE-seq and scATAC-seq together?▼

Multimodal integration supports RNA, ATAC, and protein modalities using specialized models like totalVI, PeakVI, and MultiVI. These models learn joint probabilistic latent spaces from multi-omics inputs, enabling robust cross-modality integration and downstream analysis.

How does uncertainty-aware differential expression handle zero-inflation in single-cell counts?▼

Uncertainty-aware differential expression uses Bayesian testing to quantify uncertainty while explicitly handling zero-inflation in raw count data. This probabilistic approach provides confidence intervals for expression differences across biological groups rather than deterministic p-values alone.

What input format is required for probabilistic single-cell modeling?▼

Probabilistic single-cell modeling requires AnnData objects containing raw count layers as input. You must correctly register batch covariates, sample metadata, and modality-specific keys using the setup_anndata function before training any models.

Can I transfer learned cell type annotations to a new query dataset?▼

Query-to-reference transfer uses semi-supervised models like scANVI to annotate new single-cell datasets. By leveraging a pre-trained probabilistic reference model, you can predict cell types for unannotated query data while accounting for batch effects.

Does this approach support spatial transcriptomics deconvolution?▼

Spatial transcriptomics deconvolution is supported via specialized models like DestVI. It uses probabilistic modeling to estimate cell type abundances and spatially resolved gene expression profiles from mixed spatial spots, providing uncertainty estimates for the deconvolved signals.