Commit
·
4556b2b
1
Parent(s):
52b2e60
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
library_name: scvi-tools
|
| 4 |
+
tags:
|
| 5 |
+
- biology
|
| 6 |
+
- genomics
|
| 7 |
+
- single-cell
|
| 8 |
+
- model_cls_name:SCANVI
|
| 9 |
+
- scvi_version:0.20.0
|
| 10 |
+
- anndata_version:0.8.0
|
| 11 |
+
- modality:rna
|
| 12 |
+
- tissue:Fat
|
| 13 |
+
- annotated:True
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# Description
|
| 17 |
+
|
| 18 |
+
Tabula sapiens. An across organ dataset of cell-types in human tissues.
|
| 19 |
+
|
| 20 |
+
# Model properties
|
| 21 |
+
|
| 22 |
+
Many model properties are in the model tags. Some more are listed below.
|
| 23 |
+
|
| 24 |
+
**model_init_params**:
|
| 25 |
+
```json
|
| 26 |
+
{
|
| 27 |
+
"n_hidden": 128,
|
| 28 |
+
"n_latent": 20,
|
| 29 |
+
"n_layers": 3,
|
| 30 |
+
"dropout_rate": 0.05,
|
| 31 |
+
"dispersion": "gene",
|
| 32 |
+
"gene_likelihood": "nb",
|
| 33 |
+
"latent_distribution": "normal",
|
| 34 |
+
"use_batch_norm": "none",
|
| 35 |
+
"use_layer_norm": "both",
|
| 36 |
+
"encode_covariates": true
|
| 37 |
+
}
|
| 38 |
+
```
|
| 39 |
+
|
| 40 |
+
**model_setup_anndata_args**:
|
| 41 |
+
```json
|
| 42 |
+
{
|
| 43 |
+
"labels_key": "cell_ontology_class",
|
| 44 |
+
"unlabeled_category": "unknown",
|
| 45 |
+
"layer": null,
|
| 46 |
+
"batch_key": "donor_assay",
|
| 47 |
+
"size_factor_key": null,
|
| 48 |
+
"categorical_covariate_keys": null,
|
| 49 |
+
"continuous_covariate_keys": null
|
| 50 |
+
}
|
| 51 |
+
```
|
| 52 |
+
|
| 53 |
+
**model_summary_stats**:
|
| 54 |
+
| Summary Stat Key | Value |
|
| 55 |
+
|--------------------------|-------|
|
| 56 |
+
| n_batch | 3 |
|
| 57 |
+
| n_cells | 20259 |
|
| 58 |
+
| n_extra_categorical_covs | 0 |
|
| 59 |
+
| n_extra_continuous_covs | 0 |
|
| 60 |
+
| n_labels | 13 |
|
| 61 |
+
| n_latent_qzm | 20 |
|
| 62 |
+
| n_latent_qzv | 20 |
|
| 63 |
+
| n_vars | 4000 |
|
| 64 |
+
|
| 65 |
+
**model_data_registry**:
|
| 66 |
+
| Registry Key | scvi-tools Location |
|
| 67 |
+
|-------------------|----------------------------------------|
|
| 68 |
+
| X | adata.X |
|
| 69 |
+
| batch | adata.obs['_scvi_batch'] |
|
| 70 |
+
| labels | adata.obs['_scvi_labels'] |
|
| 71 |
+
| latent_qzm | adata.obsm['_scanvi_latent_qzm'] |
|
| 72 |
+
| latent_qzv | adata.obsm['_scanvi_latent_qzv'] |
|
| 73 |
+
| minify_type | adata.uns['_scvi_adata_minify_type'] |
|
| 74 |
+
| observed_lib_size | adata.obs['_scanvi_observed_lib_size'] |
|
| 75 |
+
|
| 76 |
+
**model_parent_module**: scvi.model
|
| 77 |
+
|
| 78 |
+
**data_is_minified**: True
|
| 79 |
+
|
| 80 |
+
# Training data
|
| 81 |
+
|
| 82 |
+
This is an optional link to where the training data is stored if it is too large
|
| 83 |
+
to host on the huggingface Model hub.
|
| 84 |
+
|
| 85 |
+
<!-- If your model is not uploaded with any data (e.g., minified data) on the Model Hub, then make
|
| 86 |
+
sure to provide this field if you want users to be able to access your training data. See the scvi-tools
|
| 87 |
+
documentation for details. -->
|
| 88 |
+
|
| 89 |
+
Training data url: https://zenodo.org/api/files/c676cd14-97a7-4ea6-ba70-2c7faa1d61d8/Fat_training_data.h5ad
|
| 90 |
+
|
| 91 |
+
# Training code
|
| 92 |
+
|
| 93 |
+
This is an optional link to the code used to train the model.
|
| 94 |
+
|
| 95 |
+
Training code url: https://github.com/scvi-hub-references/tabula_sapiens/main.py
|
| 96 |
+
|
| 97 |
+
# References
|
| 98 |
+
|
| 99 |
+
The Tabula Sapiens: A multi-organ, single-cell transcriptomic atlas of humans. The Tabula Sapiens Consortium. Science 2022.05.13; doi: https: //doi.org/10.1126/science.abl4896
|