moscot.utils.tagged_array.TaggedArray.from_adata¶
- classmethod TaggedArray.from_adata(adata, dist_key, attr, tag=Tag.POINT_CLOUD, key=None, cost='sq_euclidean', backend='ott', **kwargs)[source]¶
Create tagged array from
AnnData
.Warning
Sparse arrays will be densified except when
tag = 'graph'
.- Parameters:
adata (
AnnData
) – Annotated data object.dist_key (
Union
[Any
,Tuple
[Any
,Any
]]) – Key which determines into which source/target subsetadata
belongs.attr (
Literal
['X'
,'obsp'
,'obsm'
,'layers'
,'uns'
]) – Attribute ofAnnData
used when extracting/computing the cost.tag (
Tag
) – Tag used to interpret the extracted data.key (
Optional
[str
]) – Key in theattr
ofAnnData
used when extracting/computing the cost.cost (
Union
[str
,Literal
['barcode_distance'
,'leaf_distance'
,'custom'
],Literal
['euclidean'
,'sq_euclidean'
,'cosine'
,'pnorm_p'
,'sq_pnorm'
,'geodesic'
]]) –Cost function to apply to the extracted array, depending on
tag
:if
tag = 'point_cloud'
, it is extracted from thebackend
.if
tag = 'graph'
thecost
has to be'geodesic'
.if
tag = 'cost'
ortag = 'kernel'
, andcost = 'custom'
, the extracted array is already assumed to be a cost/kernel matrix. Otherwise,BaseCost
is used to compute the cost matrix.
backend (
Literal
['ott'
]) – Which backend to use, seeget_available_backends()
.kwargs (
Any
) – Keyword arguments for theBaseCost
or any backend-specific cost.
- Return type:
- Returns:
: The tagged array.