scvi-tools
/

tabula-sapiens-thymus-condscvi

@@ -6,8 +6,8 @@ tags:
 - genomics
 - single-cell
 - model_cls_name:CondSCVI
-- scvi_version:1.2.0
-- anndata_version:0.11.1
 - modality:rna
 - tissue:various
 - annotated:True
@@ -22,7 +22,7 @@ in the spatial data.
 CondSCVI takes as input a scRNA-seq gene expression matrix with cells and genes as well as a
 cell-type annotation for all cells.
-We provide an extensive [user guide](https://docs.scvi-tools.org/en/1.2.0/user_guide/models/destvi.html)
 for DestVI including a description of CondSCVI.
 - See our original manuscript for further details of the model:
@@ -49,24 +49,14 @@ space might still be useful for analysis.
 **Cell-wise Coefficient of Variation**:
-| Metric                  | Training Value | Validation Value |
-|-------------------------|----------------|------------------|
-| Mean Absolute Error | 5.83  | 5.84           |
-| Pearson Correlation | 0.16  | 0.16  |
-| Spearman Correlation | 0.43 | 0.44  |
-| R² (R-Squared) | -1.16  | -1.12      |
 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 | 4.25   |
-| Pearson Correlation | 0.83  |
-| Spearman Correlation | 0.97 |
-| R² (R-Squared) | 0.39  |
 </details>
@@ -81,29 +71,7 @@ cell-type.
 **Differential expression**:
-| Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
-| --- | --- | --- | --- | --- | --- | --- | --- |
-| CD4-positive helper T cell | 0.92 | 3.54 | 0.66 | 0.80 | 0.18 | 0.89 | 3356.00 |
-| fibroblast | 0.92 | 1.58 | 0.70 | 0.94 | 0.46 | 0.92 | 3251.00 |
-| innate lymphoid cell | 0.85 | 2.35 | 0.60 | 0.75 | 0.23 | 0.83 | 2594.00 |
-| B cell | 0.81 | 3.13 | 0.54 | 0.68 | 0.21 | 0.84 | 1919.00 |
-| DN3 thymocyte | 0.86 | 3.62 | 0.62 | 0.75 | 0.17 | 0.82 | 1788.00 |
-| plasma cell | 0.80 | 2.53 | 0.62 | 0.84 | 0.30 | 0.95 | 1465.00 |
-| vein endothelial cell | 0.95 | 2.05 | 0.74 | 0.87 | 0.36 | 0.87 | 1442.00 |
-| vascular associated smooth muscle cell | 0.91 | 2.17 | 0.73 | 0.88 | 0.38 | 0.89 | 1439.00 |
-| DN1 thymic pro-T cell | 0.91 | 4.21 | 0.60 | 0.72 | 0.23 | 0.83 | 985.00 |
-| naive regulatory T cell | 0.90 | 4.09 | 0.68 | 0.75 | 0.21 | 0.84 | 761.00 |
-| CD8-positive, alpha-beta cytotoxic T cell | 0.93 | 4.28 | 0.67 | 0.72 | 0.22 | 0.85 | 501.00 |
-| T follicular helper cell | 0.82 | 4.60 | 0.63 | 0.68 | 0.23 | 0.81 | 398.00 |
-| capillary endothelial cell | 0.88 | 3.46 | 0.68 | 0.75 | 0.37 | 0.82 | 383.00 |
-| endothelial cell of artery | 0.93 | 3.62 | 0.65 | 0.75 | 0.39 | 0.84 | 355.00 |
-| macrophage | 0.87 | 3.13 | 0.67 | 0.76 | 0.37 | 0.84 | 303.00 |
-| endothelial cell of lymphatic vessel | 0.92 | 3.48 | 0.69 | 0.78 | 0.42 | 0.85 | 256.00 |
-| medullary thymic epithelial cell | 0.79 | 3.14 | 0.72 | 0.85 | 0.50 | 0.90 | 140.00 |
-| monocyte | 0.85 | 4.79 | 0.62 | 0.62 | 0.37 | 0.81 | 88.00 |
-| mature NK T cell | 0.78 | 5.68 | 0.52 | 0.47 | 0.35 | 0.69 | 80.00 |
-| erythrocyte | 0.70 | 6.17 | 0.46 | 0.39 | 0.31 | 0.89 | 39.00 |
-| DN4 thymocyte | 0.74 | 5.80 | 0.56 | 0.57 | 0.44 | 0.79 | 32.00 |
 </details>
@@ -133,9 +101,12 @@ These provide the settings to setup the original model:
 Arguments passed to setup_anndata of the original model:
 ```json
 {
-    "labels_key": "cell_ontology_class",
-    "layer": null,
-    "batch_key": null
 }
 ```
@@ -145,10 +116,11 @@ 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          |
-|    labels    | adata.obs['_scvi_labels'] |
 - **Data is Minified**: False
@@ -157,11 +129,12 @@ Registry elements for AnnData manager:
 <details>
 <summary><strong>Summary Statistics</strong></summary>
-| Summary Stat Key | Value |
-|------------------|-------|
-|     n_cells      | 21575 |
-|     n_labels     |  21   |
-|      n_vars      | 3000  |
 </details>

 - genomics
 - single-cell
 - model_cls_name:CondSCVI
+- scvi_version:1.4.2
+- anndata_version:0.12.7
 - modality:rna
 - tissue:various
 - annotated:True
 CondSCVI takes as input a scRNA-seq gene expression matrix with cells and genes as well as a
 cell-type annotation for all cells.
+We provide an extensive [user guide](https://docs.scvi-tools.org/en/stable/user_guide/models/destvi.html)
 for DestVI including a description of CondSCVI.
 - See our original manuscript for further details of the model:
 **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>
 Arguments passed to setup_anndata of the original model:
 ```json
 {
+    "batch_key": null,
+    "labels_key": "cell_type",
+    "fine_labels_key": null,
+    "layer": "counts",
+    "unlabeled_category": "unlabeled",
+    "size_factor_key": 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']            |
 - **Data is Minified**: False
 <details>
 <summary><strong>Summary Statistics</strong></summary>
+| Summary Stat Key          | Value |
+|--------------------------|-------|
+| n_batch                   | 1 |
+| n_cells                   | 42729 |
+| n_labels                  | 33 |
+| n_vars                    | 3000 |
 </details>