moscot.problems.spatiotemporal.SpatioTemporalProblem.prepare

SpatioTemporalProblem.prepare(time_key, spatial_key='spatial', joint_attr=None, normalize_spatial=True, policy='sequential', cost='sq_euclidean', cost_kwargs=mappingproxy({}), a=None, b=None, marginal_kwargs=mappingproxy({}), **kwargs)

Prepare the spatiotemporal problem problem.

See also

• See Spatiotemporal trajectory of mouse organogenesis on how to prepare and solve the SpatioTemporalProblem.

• See Creating marginals from proliferation and apoptosis markers in developmental processes on how to score genes for proliferation and apoptosis.

Parameters:

• time_key (str) – Key in obs where the time points are stored.

• spatial_key (str) – Key in obsm where the spatial coordinates are stored.

• joint_attr (Union[str, Mapping[str, Any], None]) –

  How to get the data for the linear term in the fused case:

  • None - PCA on X is computed.

  • str - key in obsm where the data is stored.

  • dict - it should contain 'attr' and 'key', the attribute and key in AnnData, and optionally 'tag' from the tags.

  By default, tag = 'point_cloud' is used.

• normalize_spatial (bool) – Whether to normalize the spatial coordinates. If True, the coordinates are normalized by standardizing them.

• policy (Literal['sequential', 'triu', 'tril', 'explicit']) –

  Rule which defines how to construct the subproblems using obs['{time_key}']. Valid options are:

  • 'sequential' - align subsequent time points [(t0, t1), (t1, t2), ...].

  • 'triu' - upper triangular matrix [(t0, t1), (t0, t2), ..., (t1, t2), ...].

  • 'tril' - lower triangular matrix [(t_n, t_n-1), (t_n, t0), ..., (t_n-1, t_n-2), ...].

  • 'explicit' - explicit sequence of subsets passed via subset = [(b3, b0), ...].

• cost (Union[Literal['euclidean', 'sq_euclidean', 'cosine', 'pnorm_p', 'sq_pnorm', 'elastic_l1', 'elastic_l2', 'elastic_stvs', 'elastic_sqk_overlap', 'geodesic'], Mapping[Literal['xy', 'x', 'y'], Literal['euclidean', 'sq_euclidean', 'cosine', 'pnorm_p', 'sq_pnorm', 'elastic_l1', 'elastic_l2', 'elastic_stvs', 'elastic_sqk_overlap', 'geodesic']]]) –

  Cost function to use. Valid options are:

  • str - name of the cost function for all terms, see get_available_costs().

  • dict - a dictionary with the following keys and values:

    • 'xy' - cost function for the linear term.

    • 'x' - cost function for the source quadratic term.

    • 'y' - cost function for the target quadratic term.

• cost_kwargs (Union[Mapping[str, Any], Mapping[Literal['x', 'y', 'xy'], Mapping[str, Any]]]) – Keyword arguments for the BaseCost or any backend-specific cost.

• a (Union[bool, str, None]) –

  Source marginals. Valid options are:

  • str - key in obs where the source marginals are stored.

  • bool - if True, estimate the marginals, otherwise use uniform marginals.

  • None - set to True if proliferation_key or apoptosis_key is not None.

• b (Union[bool, str, None]) –

  Target marginals. Valid options are:

  • str - key in obs where the target marginals are stored.

  • bool - if True, estimate the marginals, otherwise use uniform marginals.

  • None - set to True if proliferation_key or apoptosis_key is not None.

• marginal_kwargs (Mapping[str, Any]) – Keyword arguments for estimate_marginals(). It always contains proliferation_key and apoptosis_key, see score_genes_for_marginals() for more information.

• kwargs (Any) – Keyword arguments for prepare().

Return type:

SpatioTemporalProblem

Returns:

: Returns self and updates the following fields:

• problems - the prepared subproblems.

• solutions - set to an empty dict.

• spatial_key - key in obsm where spatial coordinates are stored.

• temporal_key - key in obs where time points are stored.

• stage - set to 'prepared'.

• problem_kind - set to 'quadratic'.