squidpy.tl.var_by_distance
- squidpy.tl.var_by_distance(adata, groups, cluster_key, library_key=None, design_matrix_key='design_matrix', covariates=None, metric='euclidean', spatial_key='spatial', copy=False)[source]
Build a design matrix consisting of distance measurements to selected anchor point(s) for each observation.
- Parameters:
adata (
AnnData
) – Annotated data object.groups (
str
|list
[str
] |ndarray
[Any
,dtype
[Any
]]) – Anchor points to calculate distances from, can be a single gene, a list of genes or a set of coordinates.cluster_key (
str
) – Annotation column in .obs that is used as anchor.library_key (
Optional
[str
]) – If multiple library_id, column inanndata.AnnData.obs
which stores mapping betweenlibrary_id
and obs.design_matrix_key (
str
) – Name of the design matrix saved to .obsm.covariates (
Union
[list
[str
],str
,None
]) – Additional covariates from .obs to include in the design matrix.metric (
str
) – Distance metric, defaults to “euclidean”.spatial_key (
str
) – Key inanndata.AnnData.obsm
where spatial coordinates are stored.copy (
bool
) – IfTrue
, return the result, otherwise save it to theadata
object.
- Return type:
- Returns:
: If
copy = True
, returns the design_matrix with the distances to an anchor point Otherwise, stores design_matrix in .obsm.