liana.multi.to_tensor_c2c¶
- liana.multi.to_tensor_c2c(adata: ~anndata._core.anndata.AnnData | None = None, sample_key: str | None = None, score_key: str | None = None, liana_res: ~pandas.core.frame.DataFrame | None = None, source_key: str = 'source', target_key: str = 'target', ligand_key: str = 'ligand_complex', receptor_key: str = 'receptor_complex', uns_key: str = 'liana_res', non_expressed_fill: float | None = None, inverse_fun: callable = <function DefaultValues.inverse_fun>, non_negative: bool = True, return_dict: bool = False, **kwargs)¶
Function to convert a LIANA result to a tensor for cell2cell analysis.
- Parameters:
- adata
Annotated data object.
- sample_key
key in adata.obs to use for grouping by sample or context.
- score_key
Column name of the score in liana_res. If None, the score is inferred from the method.
- liana_res
A dataframe with the LIANA results. If None, it will be taken from adata.uns[uns_key].
- source_key
Column name of the sender/source cell types in liana_res.
- target_key
Column name of the receiver/target cell types in liana_res.
- ligand_key
Column name of the ligand in liana_res.
- receptor_key
Column name of the receptor in liana_res.
- uns_key
Key in adata.uns that contains the LIANA results. Default is ‘liana_res’.
- inverse_fun
Function that is applied to the scores before building the views. Default is lambda x: 1 - x which is used to invert the scores reflect probabilities (e.g. magnitude_rank), i.e. such for which lower values reflect higher relevance. This is handled automatically for the scores in liana.
- non_expressed_fillfloat, optional (default: None)
Value to fill for non-expressed ligand-receptor pairs.
- non_negativebool, optional (default: True)
Whether to make the tensor non-negative.
- return_dictbool, optional (default: False)
Whether to return a dictionary of tensors.
- **kwargskeyword arguments to pass to Tensor-cell2cell’s cell2cell.tensor.external_scores.dataframes_to_tensor function.
- Returns:
- Returns a tensor of shape (n_samples, n_senders, n_receivers, n_interactions) or a dictionary of tensors if return_dict is True.