---
library_name: scvi-tools
license: cc-by-4.0
tags:
- biology
- genomics
- single-cell
- model_cls_name:SCVI
- scvi_version:1.2.0
- anndata_version:0.11.1
- modality:rna
- tissue:various
- annotated:True
---
ScVI is a variational inference model for single-cell RNA-seq data that can learn an underlying
latent space, integrate technical batches and impute dropouts.
The learned low-dimensional latent representation of the data can be used for visualization and
clustering.
scVI takes as input a scRNA-seq gene expression matrix with cells and genes.
We provide an extensive [user guide](https://docs.scvi-tools.org/en/1.2.0/user_guide/models/scvi.html).
- See our original manuscript for further details of the model:
[scVI manuscript](https://www.nature.com/articles/s41592-018-0229-2).
- See our manuscript on [scvi-hub](https://www.biorxiv.org/content/10.1101/2024.03.01.582887v2) how
to leverage pre-trained models.
This model can be used for fine tuning on new data using our Arches framework:
[Arches tutorial](https://docs.scvi-tools.org/en/1.0.0/tutorials/notebooks/scarches_scvi_tools.html).
# Model Description
Tabula Sapiens is a benchmark, first-draft human cell atlas of nearly 500,000 cells from 24 organs of 15 normal human subjects.
# Metrics
We provide here key performance metrics for the uploaded model, if provided by the data uploader.
Coefficient of variation
The cell-wise coefficient of variation summarizes how well variation between different cells is
preserved by the generated model expression. Below a squared Pearson correlation coefficient of 0.4
, we would recommend not to use generated data for downstream analysis, while the generated latent
space might still be useful for analysis.
**Cell-wise Coefficient of Variation**:
| Metric | Training Value | Validation Value |
|-------------------------|----------------|------------------|
| Mean Absolute Error | 2.41 | 2.43 |
| Pearson Correlation | 0.72 | 0.71 |
| Spearman Correlation | 0.72 | 0.71 |
| R² (R-Squared) | 0.45 | 0.41 |
The gene-wise coefficient of variation summarizes how well variation between different genes is
preserved by the generated model expression. This value is usually quite high.
**Gene-wise Coefficient of Variation**:
| Metric | Training Value |
|-------------------------|----------------|
| Mean Absolute Error | 11.55 |
| Pearson Correlation | 0.59 |
| Spearman Correlation | 0.61 |
| R² (R-Squared) | -1.46 |
Differential expression metric
The differential expression metric provides a summary of the differential expression analysis
between cell types or input clusters. We provide here the F1-score, Pearson Correlation
Coefficient of Log-Foldchanges, Spearman Correlation Coefficient, and Area Under the Precision
Recall Curve (AUPRC) for the differential expression analysis using Wilcoxon Rank Sum test for each
cell-type.
**Differential expression**:
| Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
| --- | --- | --- | --- | --- | --- | --- | --- |
| fibroblast | 0.94 | 0.39 | 0.80 | 0.95 | 0.40 | 0.85 | 3014.00 |
| endothelial cell | 0.96 | 1.35 | 0.69 | 0.95 | 0.27 | 0.89 | 2077.00 |
| T cell | 0.89 | 2.38 | 0.67 | 0.88 | 0.35 | 0.82 | 546.00 |
| vascular associated smooth muscle cell | 0.92 | 3.22 | 0.68 | 0.81 | 0.21 | 0.82 | 390.00 |
| macrophage | 0.81 | 2.06 | 0.63 | 0.87 | 0.38 | 0.84 | 344.00 |
| myometrial cell | 0.83 | 3.63 | 0.63 | 0.73 | 0.25 | 0.73 | 199.00 |
| epithelial cell of uterus | 0.80 | 1.93 | 0.60 | 0.88 | 0.47 | 0.79 | 194.00 |
| pericyte | 0.83 | 3.88 | 0.62 | 0.66 | 0.30 | 0.61 | 95.00 |
| endothelial cell of lymphatic vessel | 0.76 | 3.07 | 0.62 | 0.77 | 0.52 | 0.78 | 86.00 |
| epithelial cell | 0.68 | 2.06 | 0.65 | 0.90 | 0.59 | 0.87 | 68.00 |
| mature NK T cell | 0.76 | 4.83 | 0.64 | 0.70 | 0.36 | 0.67 | 53.00 |
| ciliated epithelial cell | 0.54 | 3.57 | 0.64 | 0.81 | 0.52 | 0.78 | 31.00 |
| leukocyte | 0.44 | 4.20 | 0.66 | 0.71 | 0.45 | 0.69 | 17.00 |
# Model Properties
We provide here key parameters used to setup and train the model.
Model Parameters
These provide the settings to setup the original model:
```json
{
"n_hidden": 128,
"n_latent": 20,
"n_layers": 3,
"dropout_rate": 0.05,
"dispersion": "gene",
"gene_likelihood": "nb",
"latent_distribution": "normal",
"use_batch_norm": "none",
"use_layer_norm": "both",
"encode_covariates": true
}
```
Setup Data Arguments
Arguments passed to setup_anndata of the original model:
```json
{
"layer": null,
"batch_key": "donor_assay",
"labels_key": "cell_ontology_class",
"size_factor_key": null,
"categorical_covariate_keys": null,
"continuous_covariate_keys": null
}
```
Data Registry
Registry elements for AnnData manager:
| Registry Key | scvi-tools Location |
|-------------------|--------------------------------------|
| X | adata.X |
| batch | adata.obs['_scvi_batch'] |
| labels | adata.obs['_scvi_labels'] |
| latent_qzm | adata.obsm['scvi_latent_qzm'] |
| latent_qzv | adata.obsm['scvi_latent_qzv'] |
| minify_type | adata.uns['_scvi_adata_minify_type'] |
| observed_lib_size | adata.obs['observed_lib_size'] |
- **Data is Minified**: False
Summary Statistics
| Summary Stat Key | Value |
|--------------------------|-------|
| n_batch | 2 |
| n_cells | 7114 |
| n_extra_categorical_covs | 0 |
| n_extra_continuous_covs | 0 |
| n_labels | 13 |
| n_latent_qzm | 20 |
| n_latent_qzv | 20 |
| n_vars | 3000 |
Training
**Training data url**: Not provided by uploader
If provided by the original uploader, for those interested in understanding or replicating the
training process, the code is available at the link below.
**Training Code URL**: https://github.com/YosefLab/scvi-hub-models/blob/main/src/scvi_hub_models/TS_train_all_tissues.ipynb
# References
The Tabula Sapiens Consortium. The Tabula Sapiens: A multiple-organ, single-cell transcriptomic atlas of humans. Science, May 2022. doi:10.1126/science.abl4896