valsv's picture
Update README.md
a3d9c56 verified
metadata
license: cc-by-4.0
library_name: scvi-tools
tags:
  - biology
  - genomics
  - single-cell
  - model_cls_name:SCVI
  - scvi_version:1.0.4
  - anndata_version:0.9.1
  - modality:rna
  - annotated:True

Description

mmColon_single_cell_85K.mouse.h5ad

Model properties

Many model properties are in the model tags. Some more are listed below.

model_init_params:

{
    "n_hidden": 128,
    "n_latent": 10,
    "n_layers": 1,
    "dropout_rate": 0.1,
    "dispersion": "gene",
    "gene_likelihood": "nb",
    "latent_distribution": "normal"
}

model_setup_anndata_args:

{
    "layer": null,
    "batch_key": null,
    "labels_key": null,
    "size_factor_key": "total_counts",
    "categorical_covariate_keys": null,
    "continuous_covariate_keys": null
}

Training curve: image/png

Embedding plots: image/png

model_summary_stats:

  Summary Stat Key    Value 
  n_batch     1  
  n_cells    84612 
 n_extra_categorical_covs    0  
 n_extra_continuous_covs     0  
  n_labels     1  
  n_latent_qzm     10  
  n_latent_qzv     10  
  n_vars    18416 

model_data_registry:

  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['_scvi_observed_lib_size'] 
  size_factor     adata.obs['total_counts']  

model_parent_module: scvi.model

data_is_minified: True

Training data

This is an optional link to where the training data is stored if it is too large to host on the huggingface Model hub.

Training data url: N/A

Training code

This is an optional link to the code used to train the model.

Training code url: N/A

References

10.6084/m9.figshare.24670038.v1