skills.rest
Imad-Oute
Imad-OuteCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

scvi-tools

Analyze single-cell genomics data with deep probabilistic models.

Updated May 10, 2026
Search Tags:#single-cell#batch correction#differential expression#probabilistic modeling#multi-omics#trajectory inference
One-click install
npx skills add https://github.com/Imad-Oute/ResearchForge --skill scvi-tools-imad-oute
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scvi-tools
Source: https://github.com/Imad-Oute/ResearchForge/tree/main/OpenSource-Projects/claude-scientific-skills/scientific-skills/scvi-tools
Command: npx skills add https://github.com/Imad-Oute/ResearchForge --skill scvi-tools-imad-oute

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, scanpy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides advanced probabilistic frameworks for analyzing and interpreting single-cell genomics data, enabling robust extraction of meaningful biological signals amidst technical noise.

Core Features & Use Cases

  • Dimensionality Reduction & Batch Correction: Uses deep generative models to produce batch-invariant cellular embeddings for integrated analysis.
  • Cell Type Annotation: Supports semi-supervised classification and transfer learning for accurate cell type identification.
  • Differential Expression: Performs probabilistic gene-level testing with built-in uncertainty quantification.
  • Multi-modal Data Analysis: Integrates diverse data types such as RNA, protein, methylation, and spatial transcriptomics through specialized models like totalVI, MultiVI, and DestVI.
  • Trajectory & Dynamics: Infers cellular trajectories and velocity fields to study dynamic biological processes.
  • Data Imputation & Simulation: Generates synthetic or missing data points, facilitating data augmentation and exploratory analyses.

Quick Start

Setup your dataset by loading raw counts into an AnnData object, run scvi.model.SCVI, and extract low-dimensional embeddings for clustering and visualization.

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 data using deep generative models?▼

Batch correction on single-cell RNA data uses deep probabilistic models to produce batch-invariant cellular embeddings. This neural network-based approach filters technical noise to enable robust integrated analysis across diverse datasets.

Can I integrate multi-omics data like spatial transcriptomics and methylation in a single analysis?▼

Yes, multi-omics integration combines RNA, protein, methylation, and spatial transcriptomics. Specialized models like totalVI, MultiVI, and DestVI merge these diverse data types to extract unified biological signals.

How does probabilistic differential expression quantify uncertainty in single-cell genomics?▼

Probabilistic differential expression performs gene-level testing with built-in uncertainty quantification. This ensures biological discoveries in single-cell genomics account for technical variation and model confidence.

Do I need PyTorch and Scanpy to run single-cell probabilistic modeling?▼

Yes, single-cell probabilistic modeling requires PyTorch and Scanpy dependencies. The neural network-based inference engine relies on PyTorch, while Scanpy manages the AnnData objects for raw counts.

What is the best way to identify cell types from single-cell datasets with limited labels?▼

Identifying cell types from limited labels uses semi-supervised classification and transfer learning. This method accurately annotates cells by leveraging probabilistic frameworks to propagate known labels.

How do I infer cellular trajectories and velocity fields for dynamic biological processes?▼

Inferring cellular trajectories and velocity fields maps dynamic biological processes over time. This analysis extracts continuous cellular transitions from raw single-cell counts to model development.

Related Skills

Explore More Education & Research Skills→
jaechang-hitsjaechang-hits
298

scvi-tools-single-cell

Provides scVI/scANVI/totalVI/scARCHES modeling for scRNA-seq and CMI-seq data in single-cell omics analysis.

Community
Advanced
m0atm0at
1

umap-learn

Compute low-dimensional embeddings of high-dimensional data for visualization and clustering.

Community
Advanced
CHENyiru3CHENyiru3

scvi-tools

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

Community
Advanced
biomaps-infrabiomaps-infra

bio-scvi-tools

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

Official
Advanced