--- 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 | 2.44 | 2.57 | | Pearson Correlation | 0.72 | 0.67 | | Spearman Correlation | 0.66 | 0.62 | | R² (R-Squared) | 0.07 | -0.08 | 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 | 17.51 | | Pearson Correlation | 0.58 | | Spearman Correlation | 0.60 | | R² (R-Squared) | -2.35 |
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 | | --- | --- | --- | --- | --- | --- | --- | --- | | luminal epithelial cell of mammary gland | 0.91 | 0.61 | 0.80 | 0.97 | 0.47 | 0.91 | 5378.00 | | T cell | 0.93 | 2.10 | 0.57 | 0.82 | 0.19 | 0.83 | 2324.00 | | fibroblast of breast | 0.92 | 1.19 | 0.69 | 0.93 | 0.43 | 0.89 | 2066.00 | | basal cell | 0.91 | 3.17 | 0.58 | 0.75 | 0.33 | 0.72 | 476.00 | | vein endothelial cell | 0.85 | 3.44 | 0.63 | 0.78 | 0.39 | 0.79 | 263.00 | | macrophage | 0.77 | 3.77 | 0.59 | 0.73 | 0.34 | 0.79 | 219.00 | | plasma cell | 0.77 | 3.64 | 0.55 | 0.69 | 0.20 | 0.86 | 194.00 | | endothelial cell of artery | 0.79 | 3.99 | 0.62 | 0.73 | 0.40 | 0.76 | 168.00 | | pericyte | 0.78 | 4.85 | 0.57 | 0.61 | 0.37 | 0.71 | 106.00 | | vascular associated smooth muscle cell | 0.78 | 5.37 | 0.55 | 0.55 | 0.38 | 0.71 | 71.00 | | B cell | 0.51 | 7.88 | 0.40 | 0.37 | 0.35 | 0.73 | 43.00 | | endothelial cell of lymphatic vessel | 0.55 | 6.35 | 0.52 | 0.45 | 0.40 | 0.70 | 32.00 | | mature NK T cell | 0.47 | 6.09 | 0.44 | 0.44 | 0.30 | 0.78 | 19.00 | | mast cell | 0.27 | 7.18 | 0.38 | 0.32 | 0.39 | 0.75 | 16.00 |
# 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 | 11375 | | n_extra_categorical_covs | 0 | | n_extra_continuous_covs | 0 | | n_labels | 14 | | 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