spateo.segmentation.moran
=========================

.. py:module:: spateo.segmentation.moran

.. autoapi-nested-parse::

   Cell masking using Moran's I metric.

   Adapted from code written by @HailinPan.



Functions
---------

.. autoapisummary::

   spateo.segmentation.moran.moranI
   spateo.segmentation.moran.run_moran
   spateo.segmentation.moran.run_moran_and_mask_pixels
   spateo.segmentation.moran.binary_morani_result


Module Contents
---------------

.. py:function:: moranI(X: numpy.ndarray, kernel: numpy.ndarray, mask: Optional[numpy.ndarray] = None) -> Tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray]

   Compute Moran's I for cell masking.

   :param X: Numpy array containing (possibly smoothed) UMI counts or binarized
             values.
   :param kernel: 2D kernel containing weights
   :param mask: If provided, only consider pixels within the mask

   :returns: A 4-element tuple containing (z, c, i, pvalue).


.. py:function:: run_moran(X: numpy.ndarray, k: int = 7, p_threshold: float = 0.05, mask: Optional[numpy.ndarray] = None) -> numpy.ndarray

   Compute scores using Moran's I method.

   :param X: Numpy array containing (possibly smoothed) UMI counts or binarized
             values.
   :param k: Kernel size
   :param p_threshold: P-value threshold. Test. Test Test
   :param mask: If provided, only consider pixels within the mask

   :returns: A 2D Numpy array indicating pixel scores


.. py:function:: run_moran_and_mask_pixels(adata: anndata.AnnData, layer: str, k: int = 7, method: str = 'edge-watershed', mk: int = 3, mask: Optional[numpy.ndarray] = None, mask_layer: Optional[str] = None) -> numpy.ndarray

   Compute scores using Moran's I method.

   :param adata: Input Anndata
   :param layer: Layer that contains UMI counts to use
   :param k: Kernel size
   :param method: Method used for generating cell mask based on p value of Moran's I. 'edge-watershed' or 'otsu'
   :param mk: Kernel size of morphological open and close operations to reduce
              noise in the mask.
   :param mask: If provided, only consider pixels within the mask
   :param mask_layer: Layer to save the final mask. Defaults to `{layer}_mask`.

   :returns: A boolean mask.


.. py:function:: binary_morani_result(c: numpy.ndarray, p: numpy.ndarray, pvalue_cutoff: float = None, method: str = 'edge-watershed', c_cutoff: float = None, tissue_mask: Optional[numpy.ndarray] = None) -> numpy.ndarray

   Generate cell mask based on Moran's I.