spateo.tools.cluster._stagate
=============================

.. py:module:: spateo.tools.cluster._stagate

.. autoapi-nested-parse::

   Module providing a encapsulation of pySTAGATE.



Classes
-------

.. autoapisummary::

   spateo.tools.cluster._stagate.pySTAGATE


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

.. py:class:: pySTAGATE(adata: anndata.AnnData, num_batch_x, num_batch_y, basis='spatial', spatial_key: list = ['X', 'Y'], batch_size: int = 1, rad_cutoff: int = 200, num_epoch: int = 1000, lr: float = 0.001, weight_decay: float = 0.0001, hidden_dims: list = [512, 30], device: str = 'cuda:0')

   Class representing the object of pySTAGATE.


   .. py:attribute:: device


   .. py:attribute:: loader


   .. py:attribute:: num_epoch
      :value: 1000



   .. py:attribute:: lr
      :value: 0.001



   .. py:attribute:: weight_decay
      :value: 0.0001



   .. py:attribute:: hidden_dims
      :value: [512, 30]



   .. py:attribute:: adata


   .. py:attribute:: data


   .. py:attribute:: model


   .. py:attribute:: optimizer


   .. py:method:: train()

      Train the STAGATE model.



   .. py:method:: predicted()

      Predict the STAGATE representation and ReX values for all cells.



   .. py:method:: cal_pSM(n_neighbors: int = 20, resolution: int = 1, max_cell_for_subsampling: int = 5000, psm_key='pSM_STAGATE')

      Calculate the pseudo-spatial map using diffusion pseudotime (DPT) algorithm.

      :param n_neighbors: Number of neighbors for constructing the kNN graph.
      :type n_neighbors: int
      :param resolution: Resolution for clustering.
      :type resolution: float
      :param max_cell_for_subsampling: Maximum number of cells for subsampling.
                                       If the number of cells is larger than this value, the subsampling will be performed.
      :type max_cell_for_subsampling: int

      :returns: **pSM_values** -- The pseudo-spatial map values.
      :rtype: numpy.ndarray