metadata

license: cc-by-4.0
library_name: scvi-tools
tags:
  - biology
  - genomics
  - single-cell
  - model_cls_name:SCANVI
  - scvi_version:1.0.0
  - anndata_version:0.9.1
  - modality:rna
  - annotated:True

Description

Human scANVI reference model

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": 2,
    "dropout_rate": 0.1,
    "dispersion": "gene",
    "gene_likelihood": "nb",
    "linear_classifier": false,
    "latent_distribution": "normal"
}

model_setup_anndata_args:

{
    "labels_key": "ct_fine",
    "unlabeled_category": "Unknown",
    "layer": "counts",
    "batch_key": "batch",
    "size_factor_key": null,
    "categorical_covariate_keys": null,
    "continuous_covariate_keys": null
}

model_summary_stats:

[1m [0m[1m Summary Stat Key [0m[1m [0m	[1m [0m[1mValue[0m[1m [0m
[94m [0m[94m n_batch [0m[94m [0m	[35m [0m[35m 6 [0m[35m [0m
[94m [0m[94m n_cells [0m[94m [0m	[35m [0m[35m2323 [0m[35m [0m
[94m [0m[94mn_extra_categorical_covs[0m[94m [0m	[35m [0m[35m 0 [0m[35m [0m
[94m [0m[94mn_extra_continuous_covs [0m[94m [0m	[35m [0m[35m 0 [0m[35m [0m
[94m [0m[94m n_labels [0m[94m [0m	[35m [0m[35m 15 [0m[35m [0m
[94m [0m[94m n_vars [0m[94m [0m	[35m [0m[35m3000 [0m[35m [0m

model_data_registry:

[1m [0m[1mRegistry Key[0m[1m [0m	[1m [0m[1m scvi-tools Location [0m[1m [0m
[94m [0m[94m X [0m[94m [0m	[35m [0m[35m adata.layers['counts'] [0m[35m [0m
[94m [0m[94m batch [0m[94m [0m	[35m [0m[35madata.obs['_scvi_batch'] [0m[35m [0m
[94m [0m[94m labels [0m[94m [0m	[35m [0m[35madata.obs['_scvi_labels'][0m[35m [0m

model_parent_module: https://zenodo.org/records/10669600/files/32_human_adata.h5ad?download=1

data_is_minified: False

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: https://github.com/brickmanlab/proks-salehin-et-al

Training code

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

Training code url: N/A

References

Proks, Salehin et al., biorXiv