PromptShop

Scvi Tools

Scvi Tools

Install

npx promptshop add scvi-tools

Details

What This Skill Does

This skill guides users in performing deep learning-based single-cell analysis using scvi-tools. It assists in selecting appropriate workflows, preparing data, and troubleshooting common issues. It is intended for researchers working with single-cell genomics data who want to leverage probabilistic models for tasks like batch correction and integration.

When to Use

Perform deep learning-based batch correction of scRNA-seq data. Integrate multi-modal single-cell data (e.g., CITE-seq). Transfer cell type labels from a reference dataset. Analyze scATAC-seq data for chromatin accessibility. Deconvolve spatial transcriptomics data using scRNA-seq references. Learn latent representations of single-cell data.

Key Features

Provides a model selection guide based on data type and use case. Offers reference files with detailed steps and code examples. Includes scripts to avoid rewriting common code. Provides guidance on environment setup and troubleshooting. Supports various scvi-tools models (scVI, scANVI, totalVI, etc.). Offers workflows for data preparation and scRNA integration.

This skill provides guidance for deep learning-based single-cell analysis using scvi-tools, the leading framework for probabilistic models in single-cell genomics.

How to Use This Skill

Identify the appropriate workflow from the model/workflow tables below Read the corresponding reference file for detailed steps and code Use scripts in scripts/ to avoid rewriting common code For installation or GPU issues, consult references/environment_setup.md For debugging, consult references/troubleshooting.md

When to Use This Skill

When scvi-tools, scVI, scANVI, or related models are mentioned When deep learning-based batch correction or integration is needed When working with multi-modal data (CITE-seq, multiome) When reference mapping or label transfer is required When analyzing ATAC-seq or spatial transcriptomics data When learning latent representations of single-cell data

Model Selection Guide

Data TypeModelPrimary Use Case
scRNA-seqscVIUnsupervised integration, DE, imputation
scRNA-seq + labelsscANVILabel transfer, semi-supervised integration
CITE-seq (RNA+protein)totalVIMulti-modal integration, protein denoising
scATAC-seqPeakVIChromatin accessibility analysis
Multiome (RNA+ATAC)MultiVIJoint modality analysis
Spatial + scRNA referenceDestVICell type deconvolution
RNA velocityveloVITranscriptional dynamics
Cross-technologysysVISystem-level batch correction

Workflow Reference Files

WorkflowReference FileDescription
Environment Setupreferences/environment_setup.mdInstallation, GPU, version info
Data Preparationreferences/data_preparation.mdFormatting data for any model
scRNA Integrationreferences/scrna_integration.mdscVI/scANVI batch correction
ATAC-seq Analysisreferences/atac_peakvi.mdPeakVI for accessibility
CITE-seq Analysisreferences/citeseq_totalvi.mdtotalVI for protein+RNA
Multiome Analysisreferences/multiome_multivi.mdMultiVI for RNA+ATAC
Spatial Deconvolutionreferences/spatial_deconvolution.mdDestVI spatial analysis
Label Transferreferences/label_transfer.mdscANVI reference mapping
sc Arches Mappingreferences/scarches_mapping.mdQuery-to-reference mapping
Batch Correctionreferences/batch_correction_sysvi.mdAdvanced batch methods
RNA Velocityreferences/rna_velocity_velovi.mdveloVI dynamics
Troubleshootingreferences/troubleshooting.mdCommon issues and solutions

CLI Scripts

Modular scripts for common workflows. Chain together or modify as needed.

Pipeline Scripts

ScriptPurposeUsage
prepare_data.pyQC, filter, HVG selectionpython scripts/prepare_data.py raw.h5ad prepared.h5ad --batch-key batch
train_model.pyTrain any scvi-tools modelpython scripts/train_model.py prepared.h5ad results/ --model scvi
cluster_embed.pyNeighbors, UMAP, Leidenpython scripts/cluster_embed.py adata.h5ad results/
differential_expression.pyDE analysispython scripts/differential_expression.py model/ adata.h5ad de.csv --groupby leiden
transfer_labels.pyLabel transfer with scANVIpython scripts/transfer_labels.py ref_model/ query.h5ad results/
integrate_datasets.pyMulti-dataset integrationpython scripts/integrate_datasets.py results/ data1.h5ad data2.h5ad
validate_adata.pyCheck data compatibilitypython scripts/validate_adata.py data.h5ad --batch-key batch

Example Workflow

1. Validate input data

python scripts/validate_adata.py raw.h5ad --batch-key batch --suggest

  1. Prepare data (QC, HVG selection) python scripts/prepare_data.py raw.h5ad prepared.h5ad --batch-key batch --n-hvgs 2000

  2. Train model python scripts/train_model.py prepared.h5ad results/ --model scvi --batch-key batch

  3. Cluster and visualize python scripts/cluster_embed.py results/adata_trained.h5ad results/ --resolution 0.8

  4. Differential expression python scripts/differential_expression.py results/model results/adata_clustered.h5ad results/de.csv --groupby leiden

Python Utilities

The scripts/model_utils.py provides importable functions for custom workflows:

FunctionPurpose
prepare_adata()Data preparation (QC, HVG, layer setup)
train_scvi()Train scVI or scANVI
evaluate_integration()Compute integration metrics
get_marker_genes()Extract DE markers
save_results()Save model, data, plots
auto_select_model()Suggest best model
quick_clustering()Neighbors + UMAP + Leiden

Critical Requirements

Raw counts required: scvi-tools models require integer count data adata.layers["counts"] = adata. X.copy() # Before normalization scvi.model. SCVI.setup_anndata(adata, layer="counts")

HVG selection: Use 2000-4000 highly variable genes sc.pp.highly_variable_genes(adata, n_top_genes=2000, batch_key="batch", layer="counts", flavor="seurat_v3") adata = adata[:, adata.var['highly_variable']].copy()

Batch information: Specify batch_key for integration scvi.model. SCVI.setup_anndata(adata, layer="counts", batch_key="batch")

Quick Decision Tree

Need to integrate scRNA-seq data? ├── Have cell type labels? → scANVI (references/label_transfer.md) └── No labels? → scVI (references/scrna_integration.md)

Have multi-modal data? ├── CITE-seq (RNA + protein)? → totalVI (references/citeseq_totalvi.md) ├── Multiome (RNA + ATAC)? → MultiVI (references/multiome_multivi.md) └── scATAC-seq only? → PeakVI (references/atac_peakvi.md)

Have spatial data? └── Need cell type deconvolution? → DestVI (references/spatial_deconvolution.md)

Have pre-trained reference model? └── Map query to reference? → sc Arches (references/scarches_mapping.md)

Need RNA velocity? └── veloVI (references/rna_velocity_velovi.md)

Strong cross-technology batch effects? └── sysVI (references/batch_correction_sysvi.md)

Key Resources

scvi-tools Documentation scvi-tools Tutorials Model Hub Git Hub Issuesscvi-tools Deep Learning Skill

When scvi-tools, scVI, scANVI, or related