troutpy.tl.segmentation_free_clustering

troutpy.tl.segmentation_free_clustering#

troutpy.tl.segmentation_free_clustering(sdata, params=None, layer='transcripts', coord_keys=None, gene_key='feature_name', method='points2regions', transcript_id_key='transcript_id_key', copy=False)#

Clusters transcriptomic data without relying on pre-defined cell or tissue segmentations.It supports multiple clustering methods, with Points2Regions being the default.

Parameters:

  • sdata (spatialdata.SpatialData) – A spatial data object containing transcriptomic information.

  • params (Optional[dict] (default: None)) – A dictionary of parameters for the selected clustering method.For points2regions:

  • coord_keys (Optional[list] (default: None)) – List of x and y gene columns within sdata[layer]

  • y (str) – Column name for the y-coordinates of transcripts.

  • gene_key (str) – Column name for the feature names.

  • method (str) –

    Clustering method to use. Options:

    • ’points2regions’: Uses the Points2Regions algorithm for clustering.

    • ’sainsc’: Placeholder for another clustering method.

  • transcript_id_key (str) – Column name for the transcript IDs.

  • copy (bool) – If True, returns a copy of the clustering results. If False, updates sdata in-place.

Returns:

anndata.AnnData If copy is True, returns an AnnData object containing the clustering results.Otherwise, updates the sdata object in-place and returns None.

Contents