DeltaTopic.nn.modelhub.BALSAM

class DeltaTopic.nn.modelhub.BALSAM(adata_seq: anndata.AnnData, n_latent: int = 32, **model_kwargs)[source]

Bayesian Latent topic analysis with Sparse Association Matrix (BALSAM).

Parameters:

adata – AnnData object that has been registered via setup_anndata().
n_latent – Dimensionality of the latent space
**model_kwargs – Keyword args for BALSAM_module

Examples

>>> adata = anndata.read_h5ad(path_to_anndata)
>>> DeltaTopic.nn.util.setup_anndata(adata)
>>> model = DeltaTopic.nn.modelhub.BALSAM(adata)
>>> model.train(100)

__init__(adata_seq: anndata.AnnData, n_latent: int = 32, **model_kwargs)[source]

Methods

`__init__`(adata_seq[, n_latent])
`get_latent_representation`
`get_parameters`
`load`(dir_path[, adata, use_gpu])	Instantiate a model from the saved output.
`save`(dir_path[, overwrite, save_anndata])	Save model parameters to the specified directory.
`to_device`(device)	Move model to device.
`train`([max_epochs, lr, use_gpu, train_size, ...])	Trains the model using amortized variational inference.

Attributes

`device`	Device model is on.
`history`	Returns computed metrics during training.
`is_trained`
`test_indices`
`train_indices`
`validation_indices`