scvi-tools

Name: scvi-tools
Author: anthropics

23kstars2.7kforks

How to install scvi-tools?

anthropics/knowledge-work-plugins/scvi-tools

$npx -y skills add anthropics/knowledge-work-plugins --skill scvi-tools

Installs into the current project.

Summary

Deep learning for single-cell analysis using scvi-tools. This skill should be used when users need (1) data integration and batch correction with scVI/scANVI, (2) ATAC-seq analysis with PeakVI, (3) CITE-seq multi-modal analysis with totalVI, (4) multiome RNA+ATAC analysis with Mu

Files · 1

View on GitHub

SKILL.md

1	# scvi-tools Deep Learning Skill
2
3	This skill provides guidance for deep learning-based single-cell analysis using scvi-tools, the leading framework for probabilistic models in single-cell genomics.
4
5	## How to Use This Skill
6
7	1. Identify the appropriate workflow from the model/workflow tables below
8	2. Read the corresponding reference file for detailed steps and code
9	3. Use scripts in `scripts/` to avoid rewriting common code
10	4. For installation or GPU issues, consult `references/environment_setup.md`
11	5. For debugging, consult `references/troubleshooting.md`
12
13	## When to Use This Skill
14
15	- When scvi-tools, scVI, scANVI, or related models are mentioned
16	- When deep learning-based batch correction or integration is needed
17	- When working with multi-modal data (CITE-seq, multiome)
18	- When reference mapping or label transfer is required
19	- When analyzing ATAC-seq or spatial transcriptomics data
20	- When learning latent representations of single-cell data
21
22	## Model Selection Guide
23
24	\| Data Type \| Model \| Primary Use Case \|
25	\|-----------\|-------\|------------------\|
26	\| scRNA-seq \| scVI \| Unsupervised integration, DE, imputation \|
27	\| scRNA-seq + labels \| scANVI \| Label transfer, semi-supervised integration \|
28	\| CITE-seq (RNA+protein) \| totalVI \| Multi-modal integration, protein denoising \|
29	\| scATAC-seq \| PeakVI \| Chromatin accessibility analysis \|
30	\| Multiome (RNA+ATAC) \| MultiVI \| Joint modality analysis \|
31	\| Spatial + scRNA reference \| DestVI \| Cell type deconvolution \|
32	\| RNA velocity \| veloVI \| Transcriptional dynamics \|
33	\| Cross-technology \| sysVI \| System-level batch correction \|
34
35	## Workflow Reference Files
36
37	\| Workflow \| Reference File \| Description \|
38	\|----------\|---------------\|-------------\|
39	\| Environment Setup \| `references/environment_setup.md` \| Installation, GPU, version info \|
40	\| Data Preparation \| `references/data_preparation.md` \| Formatting data for any model \|
41	\| scRNA Integration \| `references/scrna_integration.md` \| scVI/scANVI batch correction \|
42	\| ATAC-seq Analysis \| `references/atac_peakvi.md` \| PeakVI for accessibility \|
43	\| CITE-seq Analysis \| `references/citeseq_totalvi.md` \| totalVI for protein+RNA \|
44	\| Multiome Analysis \| `references/multiome_multivi.md` \| MultiVI for RNA+ATAC \|
45	\| Spatial Deconvolution \| `references/spatial_deconvolution.md` \| DestVI spatial analysis \|
46	\| Label Transfer \| `references/label_transfer.md` \| scANVI reference mapping \|
47	\| scArches Mapping \| `references/scarches_mapping.md` \| Query-to-reference mapping \|
48	\| Batch Correction \| `references/batch_correction_sysvi.md` \| Advanced batch methods \|
49	\| RNA Velocity \| `references/rna_velocity_velovi.md` \| veloVI dynamics \|
50	\| Troubleshooting \| `references/troubleshooting.md` \| Common issues and solutions \|
51
52	## CLI Scripts
53
54	Modular scripts for common workflows. Chain together or modify as needed.
55
56	### Pipeline Scripts
57
58	\| Script \| Purpose \| Usage \|
59	\|--------\|---------\|-------\|
60	\| `prepare_data.py` \| QC, filter, HVG selection \| `python scripts/prepare_data.py raw.h5ad prepared.h5ad --batch-key batch` \|
61	\| `train_model.py` \| Train any scvi-tools model \| `python scripts/train_model.py prepared.h5ad results/ --model scvi` \|
62	\| `cluster_embed.py` \| Neighbors, UMAP, Leiden \| `python scripts/cluster_embed.py adata.h5ad results/` \|
63	\| `differential_expression.py` \| DE analysis \| `python scripts/differential_expression.py model/ adata.h5ad de.csv --groupby leiden` \|
64	\| `transfer_labels.py` \| Label transfer with scANVI \| `python scripts/transfer_labels.py ref_model/ query.h5ad results/` \|
65	\| `integrate_datasets.py` \| Multi-dataset integration \| `python scripts/integrate_datasets.py results/ data1.h5ad data2.h5ad` \|
66	\| `validate_adata.py` \| Check data compatibility \| `python scripts/validate_adata.py data.h5ad --batch-key batch` \|
67
68	### Example Workflow
69
70	```bash
71	# 1. Validate input data
72	python scripts/validate_adata.py raw.h5ad --batch-key batch --suggest
73
74	# 2. Prepare data (QC, HVG selection)
75	python scripts/prepare_data.py raw.h5ad prepared.h5ad --batch-key batch --n-hvgs 2000
76
77	# 3. Train model
78	python scripts/train_model.py prepared.h5ad results/ --model scvi --batch-key batch
79
80	# 4. Cluster and visualize
81	python scripts/cluster_embed.py results/adata_trained.h5ad results/ --resolution 0.8
82
83	# 5.

People who liked this also viewed

6 picks

Type

scvi-tools

23kstars2.7kforks

View on GitHub

How to install scvi-tools?

anthropics/knowledge-work-plugins/scvi-tools

$npx -y skills add anthropics/knowledge-work-plugins --skill scvi-tools

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# scvi-tools Deep Learning Skill
2
3	This skill provides guidance for deep learning-based single-cell analysis using scvi-tools, the leading framework for probabilistic models in single-cell genomics.
4
5	## How to Use This Skill
6
7	1. Identify the appropriate workflow from the model/workflow tables below
8	2. Read the corresponding reference file for detailed steps and code
9	3. Use scripts in `scripts/` to avoid rewriting common code
10	4. For installation or GPU issues, consult `references/environment_setup.md`
11	5. For debugging, consult `references/troubleshooting.md`
12
13	## When to Use This Skill
14
15	- When scvi-tools, scVI, scANVI, or related models are mentioned
16	- When deep learning-based batch correction or integration is needed
17	- When working with multi-modal data (CITE-seq, multiome)
18	- When reference mapping or label transfer is required
19	- When analyzing ATAC-seq or spatial transcriptomics data
20	- When learning latent representations of single-cell data
21
22	## Model Selection Guide
23
24	\| Data Type \| Model \| Primary Use Case \|
25	\|-----------\|-------\|------------------\|
26	\| scRNA-seq \| scVI \| Unsupervised integration, DE, imputation \|
27	\| scRNA-seq + labels \| scANVI \| Label transfer, semi-supervised integration \|
28	\| CITE-seq (RNA+protein) \| totalVI \| Multi-modal integration, protein denoising \|
29	\| scATAC-seq \| PeakVI \| Chromatin accessibility analysis \|
30	\| Multiome (RNA+ATAC) \| MultiVI \| Joint modality analysis \|
31	\| Spatial + scRNA reference \| DestVI \| Cell type deconvolution \|
32	\| RNA velocity \| veloVI \| Transcriptional dynamics \|
33	\| Cross-technology \| sysVI \| System-level batch correction \|
34
35	## Workflow Reference Files
36
37	\| Workflow \| Reference File \| Description \|
38	\|----------\|---------------\|-------------\|
39	\| Environment Setup \| `references/environment_setup.md` \| Installation, GPU, version info \|
40	\| Data Preparation \| `references/data_preparation.md` \| Formatting data for any model \|
41	\| scRNA Integration \| `references/scrna_integration.md` \| scVI/scANVI batch correction \|
42	\| ATAC-seq Analysis \| `references/atac_peakvi.md` \| PeakVI for accessibility \|
43	\| CITE-seq Analysis \| `references/citeseq_totalvi.md` \| totalVI for protein+RNA \|
44	\| Multiome Analysis \| `references/multiome_multivi.md` \| MultiVI for RNA+ATAC \|
45	\| Spatial Deconvolution \| `references/spatial_deconvolution.md` \| DestVI spatial analysis \|
46	\| Label Transfer \| `references/label_transfer.md` \| scANVI reference mapping \|
47	\| scArches Mapping \| `references/scarches_mapping.md` \| Query-to-reference mapping \|
48	\| Batch Correction \| `references/batch_correction_sysvi.md` \| Advanced batch methods \|
49	\| RNA Velocity \| `references/rna_velocity_velovi.md` \| veloVI dynamics \|
50	\| Troubleshooting \| `references/troubleshooting.md` \| Common issues and solutions \|
51
52	## CLI Scripts
53
54	Modular scripts for common workflows. Chain together or modify as needed.
55
56	### Pipeline Scripts
57
58	\| Script \| Purpose \| Usage \|
59	\|--------\|---------\|-------\|
60	\| `prepare_data.py` \| QC, filter, HVG selection \| `python scripts/prepare_data.py raw.h5ad prepared.h5ad --batch-key batch` \|
61	\| `train_model.py` \| Train any scvi-tools model \| `python scripts/train_model.py prepared.h5ad results/ --model scvi` \|
62	\| `cluster_embed.py` \| Neighbors, UMAP, Leiden \| `python scripts/cluster_embed.py adata.h5ad results/` \|
63	\| `differential_expression.py` \| DE analysis \| `python scripts/differential_expression.py model/ adata.h5ad de.csv --groupby leiden` \|
64	\| `transfer_labels.py` \| Label transfer with scANVI \| `python scripts/transfer_labels.py ref_model/ query.h5ad results/` \|
65	\| `integrate_datasets.py` \| Multi-dataset integration \| `python scripts/integrate_datasets.py results/ data1.h5ad data2.h5ad` \|
66	\| `validate_adata.py` \| Check data compatibility \| `python scripts/validate_adata.py data.h5ad --batch-key batch` \|
67
68	### Example Workflow
69
70	```bash
71	# 1. Validate input data
72	python scripts/validate_adata.py raw.h5ad --batch-key batch --suggest
73
74	# 2. Prepare data (QC, HVG selection)
75	python scripts/prepare_data.py raw.h5ad prepared.h5ad --batch-key batch --n-hvgs 2000
76
77	# 3. Train model
78	python scripts/train_model.py prepared.h5ad results/ --model scvi --batch-key batch
79
80	# 4. Cluster and visualize
81	python scripts/cluster_embed.py results/adata_trained.h5ad results/ --resolution 0.8
82
83	# 5.

People who liked this also viewed

6 picks

Type