scglue.models.configure_dataset
- scglue.models.configure_dataset(adata, prob_model, use_highly_variable=True, use_layer=None, use_rep=None, use_batch=None, use_cell_type=None, use_dsc_weight=None, use_obs_names=False)[source]
Configure dataset for model training
- Parameters
adata (
AnnData
) – Dataset to be configuredprob_model (
str
) – Probabilistic generative model used by the decoder, must be one of{"Normal", "ZIN", "ZILN", "NB", "ZINB"}
.use_highly_variable (
bool
) – Whether to use highly variable featuresuse_layer (
typing.Optional
[str
]) – Data layer to use (key inadata.layers
)use_rep (
typing.Optional
[str
]) – Data representation to use as the first encoder transformation (key inadata.obsm
)use_batch (
typing.Optional
[str
]) – Data batch to use (key inadata.obs
)use_cell_type (
typing.Optional
[str
]) – Data cell type to use (key inadata.obs
)use_dsc_weight (
typing.Optional
[str
]) – Discriminator sample weight to use (key inadata.obs
)use_obs_names (
bool
) – Whether to useobs_names
to mark paired cells across different datasets
Note
The
use_rep
option applies to encoder inputs, but not the decoders, which are always fitted on data in the original space.- Return type