scvi-multivi
CommunityUnify multiome RNA+ATAC data with MultiVI.
System Documentation
What problem does it solve?
MultiVI jointly integrates paired and unpaired single-cell RNA and ATAC data using scvi-tools, producing a shared latent embedding with cross-modality imputation. Use when combining 10x Multiome with RNA-only or ATAC-only datasets, when running differential expression plus differential accessibility on joint embeddings, or for multiome batch correction. For ATAC-only analysis use scvi-peakvi; for regulatory TF-to-gene inference on unpaired data use scglue-unpaired-multiomics-integration.
Core Features & Use Cases
- Joint RNA+ATAC integration with cross-modality imputation producing a shared latent representation.
- Supports combining 10x Multiome with RNA-only or ATAC-only datasets and joint differential analyses.
- Provides guidance for data preparation, model configuration, and interpretation of outputs (latent space, imputed modalities).
Quick Start
Prepare an AnnData object with RNA and ATAC modalities and train a scvi-tools MULTIVI model to generate a joint latent embedding and cross-modal imputations.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: scvi-multivi Download link: https://github.com/tony-zhelonkin/SciAgent-toolkit/archive/main.zip#scvi-multivi Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.