tacco.tools.fill_regions

fill_regions(adata, region_key='region', batch_key=None, position_key=('x', 'y'), result_key=Ellipsis, k=1)[source]

Fills the region annotation of not annotated observation (i.e. na values) with the majority vote of the annotations of the k annotated spatially closest observations.

Parameters:

  • adata – An AnnData including region and position annotation. Can also be a DataFrame which is then used in place of .obs.

  • region_key – The .obs key where the region annotation is stored.

  • batch_key – The .obs key with categorical batch information. If not None, the filling is performed per batch.

  • position_key – The .obsm key or array-like of .obs keys with the position space coordinates.

  • result_key – The .obs key of adata where to store the resulting annotation. If None, do not write to adata and return the annotation as Series instead. If Ellipsis (i.e. …) the result will overwritte the information contained in region_key. NOTE: The Ellipsis behaviour is kept for backwards compatibility and will be removed in a future release.

  • k – The k of the kNN classifier used for the task.

Returns:

Depending on result_key, either returns the original adata with annotation written in the corresponding .obs key, or just the annotation as a new Series.