anthropics/knowledge-work-plugins

scvi-tools

Deep learning for single-cell analysis using scvi-tools.

View source

How to use

  1. Copy the installation command and review the source package before installing it in your own agent environment.
  2. Check the source document for required tools, credentials and supported hosts.
  3. Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill scvi-tools

Before you start

  • Installation does not include a model subscription, API allowance or permission to access your files.
  • Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

scvi-tools Deep Learning Skill

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

  1. Identify the appropriate workflow from the model/workflow tables below
  2. Read the corresponding reference file for detailed steps and code
  3. Use scripts in scripts/ to avoid rewriting common code
  4. For installation or GPU issues, consult references/environment_setup.md
  5. 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
scArches 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

bash
# 1. Validate input data
python scripts/validate_adata.py raw.h5ad --batch-key batch --suggest

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

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

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

# 5. 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

  1. Raw counts required: scvi-tools models require integer count data
python
   adata.layers["counts"] = adata.X.copy()  # Before normalization
   scvi.model.SCVI.setup_anndata(adata, layer="counts")
  1. HVG selection: Use 2000-4000 highly variable genes
python
   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()
  1. Batch information: Specify batch_key for integration
python
   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? → scArches (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

Related by task

from this repository

More skills

All skills
anthropics
Official

process-doc

Document a business process — flowcharts, RACI, and SOPs. Use when formalizing a process that lives in someone's head, building a RACI to clarify who owns what, writing an SOP for a handoff or audit, or capturing the exceptions and edge cases of how work actually gets done.

1h installs
1
GitHub stars
36.6K
Updated
Nov 20
anthropics
Official

data-visualization

Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.

1h installs
5
GitHub stars
36.6K
Updated
Nov 20
anthropics
Official

accessibility-review

Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with "audit accessibility", "check a11y", "is this accessible?", or when reviewing a design for color contrast, keyboard navigation, touch target size, or screen reader behavior before handoff.

1h installs
4
GitHub stars
36.6K
Updated
Nov 20
anthropics
Official

sql-queries

Write correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.). Use when writing queries, optimizing slow SQL, translating between dialects, or building complex analytical queries with CTEs, window functions, or aggregations.

1h installs
4
GitHub stars
36.6K
Updated
Nov 20