marcovarrone/scvi-dlpfc-full-visium

Description

scVI model trained on the full DLPFC Visium data (including the pilot samples).

Model properties

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

model_init_params:

{
    "n_hidden": 128,
    "n_latent": 5,
    "n_layers": 1,
    "dropout_rate": 0.1,
    "dispersion": "gene",
    "gene_likelihood": "zinb",
    "latent_distribution": "normal"
}

model_setup_anndata_args:

{
    "layer": "counts",
    "batch_key": "patient",
    "labels_key": null,
    "size_factor_key": null,
    "categorical_covariate_keys": [
        "sample",
        "study"
    ],
    "continuous_covariate_keys": null
}

model_summary_stats:

Summary Stat Key	Value
n_batch	13
n_cells	166443
n_extra_categorical_covs	2
n_extra_continuous_covs	0
n_labels	1
n_vars	5000

model_data_registry:

Registry Key	scvi-tools Location
X	adata.layers['counts']
batch	adata.obs['_scvi_batch']
extra_categorical_covs	adata.obsm['_scvi_extra_categorical_covs']
labels	adata.obs['_scvi_labels']

model_parent_module: scvi.model

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: N/A

Training code

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

Training code url: N/A

References

1. Maynard, Kristen R., et al. "Transcriptome-scale spatial gene expression in the human dorsolateral prefrontal cortex." Nature neuroscience 24.3 (2021): 425-436.
2. Huuki-Myers, Louise A., et al. "Integrated single cell and unsupervised spatial transcriptomic analysis defines molecular anatomy of the human dorsolateral prefrontal cortex." BioRxiv (2023): 2023-02.