squidpy.im.calculate_image_features

squidpy.im.calculate_image_features(adata, img, layer=None, library_id=None, features='summary', features_kwargs=mappingproxy({}), key_added='img_features', copy=False, n_jobs=None, backend='loky', show_progress_bar=True, **kwargs)

Calculate image features for all observations in adata.

Parameters:

• adata (AnnData) – Annotated data object.

• img (ImageContainer) – High-resolution image.

• layer (str | None) – Image layer in img that should be processed. If None and only 1 layer is present, it will be selected.

• library_id (str | Sequence[str] | None) –

  • If None, there should only exist one entry in anndata.AnnData.uns ['{spatial_key}'].

  • If a str, first search anndata.AnnData.obs ['{library_id}'] which contains the mapping from observations to library ids, then search anndata.AnnData.uns ['{spatial_key}'].

• features (str | Sequence[str]) –

  Features to be calculated. Valid options are:

  • ’texture’ - summary stats based on repeating patterns squidpy.im.ImageContainer.features_texture().

  • ’summary’ - summary stats of each image channel squidpy.im.ImageContainer.features_summary().

  • ’histogram’ - counts in bins of image channel’s histogram squidpy.im.ImageContainer.features_histogram().

  • ’segmentation’ - stats of a cell segmentation mask squidpy.im.ImageContainer.features_segmentation().

  • ’custom’ - extract features using a custom function squidpy.im.ImageContainer.features_custom().

• features_kwargs (Mapping[str, Mapping[str, Any]]) – Keyword arguments for the different features that should be generated, such as { 'texture': { ... }, ... }.

• key_added (str) – Key in anndata.AnnData.obsm where to store the calculated features.

• copy (bool) – If True, return the result, otherwise save it to the adata object.

• n_jobs (int | None) – Number of parallel jobs to use. For backend="loky", the number of cores used by numba for each job spawned by the backend will be set to 1 in order to overcome the oversubscription issue in case you run numba in your function to parallelize. To set the absolute maximum number of threads in numba for your python program, set the environment variable: NUMBA_NUM_THREADS before running the program.

• backend (str) – Parallelization backend to use. See joblib.Parallel for available options.

• show_progress_bar (bool) – Whether to show the progress bar or not.

• kwargs (Any) – Keyword arguments for squidpy.im.ImageContainer.generate_spot_crops().

Return type:

DataFrame | None

Returns:

If copy = True, returns a pandas.DataFrame where columns correspond to the calculated features.

Otherwise, modifies the adata object with the following key:

• anndata.AnnData.uns ['{key_added}'] - the above mentioned dataframe.

Raises:

ValueError – If a feature is not known.