scvi-tools
/

tabula-sapiens-blood-scvi

@@ -6,8 +6,8 @@ tags:
 - genomics
 - single-cell
 - model_cls_name:SCVI
-- scvi_version:1.2.0
-- anndata_version:0.11.1
 - modality:rna
 - tissue:various
 - annotated:True
@@ -20,7 +20,7 @@ The learned low-dimensional latent representation of the data can be used for vi
 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).
@@ -28,7 +28,7 @@ We provide an extensive [user guide](https://docs.scvi-tools.org/en/1.2.0/user_g
 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
@@ -49,24 +49,14 @@ space might still be useful for analysis.
 **Cell-wise Coefficient of Variation**:
-| Metric                  | Training Value | Validation Value |
-|-------------------------|----------------|------------------|
-| Mean Absolute Error | 1.20  | 1.32           |
-| Pearson Correlation | 0.99  | 0.99  |
-| Spearman Correlation | 0.96 | 0.96  |
-| R² (R-Squared) | 0.98  | 0.98      |
 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 | 24.12   |
-| Pearson Correlation | 0.73  |
-| Spearman Correlation | 0.77 |
-| R² (R-Squared) | -0.74  |
 </details>
@@ -81,26 +71,7 @@ cell-type.
 **Differential expression**:
-| Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
-| --- | --- | --- | --- | --- | --- | --- | --- |
-| erythrocyte | 0.96 | 1.13 | 0.68 | 0.86 | 0.09 | 0.98 | 10061.00 |
-| neutrophil | 0.97 | 1.12 | 0.71 | 0.93 | 0.22 | 0.90 | 8432.00 |
-| classical monocyte | 0.92 | 0.54 | 0.74 | 0.97 | 0.62 | 0.95 | 7211.00 |
-| mature NK T cell | 0.96 | 1.35 | 0.64 | 0.92 | 0.62 | 0.93 | 2332.00 |
-| naive B cell | 0.97 | 1.74 | 0.62 | 0.86 | 0.47 | 0.87 | 1526.00 |
-| CD8-positive, alpha-beta cytokine secreting effector T cell | 0.94 | 1.51 | 0.65 | 0.87 | 0.64 | 0.93 | 1493.00 |
-| CD4-positive, alpha-beta memory T cell | 0.95 | 1.57 | 0.59 | 0.86 | 0.58 | 0.88 | 949.00 |
-| memory B cell | 0.98 | 2.14 | 0.61 | 0.84 | 0.54 | 0.88 | 597.00 |
-| type I NK T cell | 0.92 | 2.37 | 0.60 | 0.79 | 0.62 | 0.89 | 518.00 |
-| plasma cell | 0.81 | 1.29 | 0.74 | 0.94 | 0.61 | 0.94 | 487.00 |
-| naive thymus-derived CD4-positive, alpha-beta T cell | 0.94 | 2.49 | 0.63 | 0.80 | 0.46 | 0.82 | 412.00 |
-| CD8-positive, alpha-beta T cell | 0.95 | 2.20 | 0.63 | 0.81 | 0.57 | 0.87 | 376.00 |
-| platelet | 0.76 | 2.71 | 0.70 | 0.82 | 0.40 | 0.83 | 239.00 |
-| hematopoietic stem cell | 0.93 | 2.90 | 0.64 | 0.77 | 0.65 | 0.90 | 47.00 |
-| T cell | 0.93 | 3.83 | 0.62 | 0.51 | 0.54 | 0.77 | 31.00 |
-| basophil | 0.86 | 2.97 | 0.69 | 0.78 | 0.61 | 0.88 | 29.00 |
-| CD141-positive myeloid dendritic cell | 0.88 | 4.58 | 0.61 | 0.62 | 0.49 | 0.75 | 15.00 |
-| plasmacytoid dendritic cell | 0.90 | 4.96 | 0.58 | 0.52 | 0.47 | 0.72 | 11.00 |
 </details>
@@ -120,6 +91,7 @@ These provide the settings to setup the original model:
     "dropout_rate": 0.05,
     "dispersion": "gene",
     "gene_likelihood": "nb",
     "latent_distribution": "normal",
     "use_batch_norm": "none",
     "use_layer_norm": "both",
@@ -135,9 +107,9 @@ These provide the settings to setup the original model:
 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
@@ -150,15 +122,15 @@ Arguments passed to setup_anndata of the original model:
 <summary><strong>Data Registry</strong></summary>
 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
@@ -167,16 +139,16 @@ Registry elements for AnnData manager:
 <details>
 <summary><strong>Summary Statistics</strong></summary>
-|     Summary Stat Key     | Value |
 |--------------------------|-------|
-|         n_batch          |   6   |
-|         n_cells          | 34766 |
-| n_extra_categorical_covs |   0   |
-| n_extra_continuous_covs  |   0   |
-|         n_labels         |  18   |
-|       n_latent_qzm       |  20   |
-|       n_latent_qzv       |  20   |
-|          n_vars          | 3000  |
 </details>

 - genomics
 - single-cell
 - model_cls_name:SCVI
+- scvi_version:1.4.2
+- anndata_version:0.12.7
 - modality:rna
 - tissue:various
 - annotated:True
 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/stable/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).
 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/stable/tutorials/notebooks/scrna/scarches_scvi_tools.html).
 # Model Description
 **Cell-wise Coefficient of Variation**:
+Not provided by uploader
 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**:
+Not provided by uploader
 </details>
 **Differential expression**:
+Not provided by uploader
 </details>
     "dropout_rate": 0.05,
     "dispersion": "gene",
     "gene_likelihood": "nb",
+    "use_observed_lib_size": true,
     "latent_distribution": "normal",
     "use_batch_norm": "none",
     "use_layer_norm": "both",
 Arguments passed to setup_anndata of the original model:
 ```json
 {
+    "layer": "counts",
     "batch_key": "donor_assay",
+    "labels_key": "cell_type",
     "size_factor_key": null,
     "categorical_covariate_keys": null,
     "continuous_covariate_keys": null
 <summary><strong>Data Registry</strong></summary>
 Registry elements for AnnData manager:
+| Registry Key             | scvi-tools Location                  |
+|--------------------------|--------------------------------------|
+| X                         | adata.layers['counts']               |
+| 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
 <details>
 <summary><strong>Summary Statistics</strong></summary>
+| Summary Stat Key          | Value |
 |--------------------------|-------|
+| n_batch                   | 17 |
+| n_cells                   | 85233 |
+| n_extra_categorical_covs  | 0 |
+| n_extra_continuous_covs   | 0 |
+| n_labels                  | 22 |
+| n_latent_qzm              | 20 |
+| n_latent_qzv              | 20 |
+| n_vars                    | 3000 |
 </details>