Model sample identity as biological variation in multi-donor scRNA-seq data with MRVI.
npx skills add https://github.com/tony-zhelonkin/SciAgent-toolkit --skill scvi-mrvi
Please help me install this Agent Skill. Skill: scvi-mrvi Source: https://github.com/tony-zhelonkin/SciAgent-toolkit/tree/main/skills/scvi-mrvi Command: npx skills add https://github.com/tony-zhelonkin/SciAgent-toolkit --skill scvi-mrvi
MRVI enables multi-donor single-cell RNA-seq analyses by modeling sample identity as biological variation, providing cell-type-specific insights and covariate-aware differential expression.
Setup an AnnData object with sample_id as the biological key, initialize MRVI, and train to obtain both latent representations for downstream analyses.
High-intent search queries and answers about installing and using this skill.
To analyze multi-sample scRNA-seq data while accounting for sample effects, model sample identity as biological variation using MRVI. This computes cell-type-specific sample distances and provides covariate-aware differential expression at single-cell resolution.
Single-cell resolution differential expression in cohort studies retains individual cell variance, whereas pseudobulk aggregates counts per sample. MRVI enables single-cell resolution covariate-aware differential expression without losing cellular heterogeneity across donors.
To set up AnnData for multi-donor scRNA-seq analysis with MRVI, load raw counts and define a sample_id biological key. You can optionally include a batch_key as a nuisance variable to handle technical variations during initialization.
You can perform cell-type clustering and sample effect analysis simultaneously in scvi-tools using MRVI. It generates a sample-invariant latent space for clustering and a sample-aware space for studying sample effects across donors.
Use MRVI instead of standard scVI for cohort-scale scRNA-seq when you need to model sample identity as biological variation across many donors. MRVI provides covariate-linked differential abundance and cell-type-specific sample distances.
tony-zhelonkinPerform unsupervised integration and batch correction for scRNA-seq data using scVI.
Victory-HugoRun scvi-tools deep generative models on single-cell RNA sequencing data.
nahisahoIntegrates multi-batch scRNA-seq data using scVI-tools to produce unified latent representations and annotations.
ovachieverApply scvi-tools probabilistic models to single-cell omics data in AnnData format.
