cellflow.external.CFJaxSCVI.get_reconstructed_expression

CFJaxSCVI.get_reconstructed_expression(data, use_rep='X_scVI', indices=None, give_mean=False, batch_size=1024)[source]

Return the reconstructed expression for each cell.

Parameters:

  • data (ndarray[tuple[Any, ...], dtype[float64]] | AnnData) – AnnData or array-like with the data to reconstruct.

  • use_rep (str) – Key for obsm that contains the latent representation to use.

  • indices (Sequence[int] | None) – Indices of cells in adata to use. If None, all cells are used.

  • give_mean (bool) – Whether to return the mean of the negative binomial distribution or the unscaled expression.

  • batch_size (int | None) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.

Return type:

ndarray[tuple[Any, ...], dtype[float64]]

Returns:

: reconstructed_expression