crested.pp.filter_regions_on_specificity

crested.pp.filter_regions_on_specificity#

crested.pp.filter_regions_on_specificity(adata, gini_std_threshold=1.0, model_name=None, inplace=True)#

Filter bed regions & targets/predictions based on high Gini score.

This function filters regions based on their specificity using Gini scores. The regions with high Gini scores are retained. If model_name is provided, will look for the corresponding predictions in the adata.layers[model_name] layer. Else, it will use the values in adata.X to decide which regions to keep. To get an idea for the impact of different possible gini_std_threshold values, see filter_cutoff().

Parameters:

  • adata (AnnData) – The AnnData object containing the matrix (celltypes, regions) to be filtered.

  • gini_std_threshold (float (default: 1.0)) – The number of standard deviations above the mean Gini score used to determine the threshold for high variability.

  • model_name (str | None (default: None)) – The name of the model to look for in adata.layers[model_name] for predictions. If None or ‘truth’/’groundtruth’/’X’, will use the values in adata.X to select specific regions.

  • inplace (bool (default: True)) – Perform computation and modify adata in-place or return a resulting copy of the adata instead.

Return type:

AnnData | None

Returns:

If inplace=True (default), returns nothing and modifies the AnnData in-place with the filtered matrix and updated variable names. If inplace=False, returns a modified copy of the AnnData object instead.

See also

crested.pl.qc.filter_cutoff

Example

>>> crested.pp.filter_regions_on_specificity(
...     adata,
...     gini_std_threshold=1.0,
... )