spateo.alignment.methods.deprecated_morpho¶

Functions¶

`con_K`(→ Union[numpy.ndarray, torch.Tensor])	con_K constructs the Squared Exponential (SE) kernel, where K(i,j)=k(X_i,Y_j)=exp(-beta*\|\|X_i-Y_j\|\|^2).
`get_P`(→ Tuple[Any, Any, Any])	Calculating the generating probability matrix P.
`get_P_chunk`(→ Union[numpy.ndarray, torch.Tensor])	Calculating the generating probability matrix P.
`BA_align`(→ Tuple[Tuple[anndata.AnnData, ...)	Align two spatial transcriptomics AnnData objects using the Spateo alignment algorithm.

Module Contents¶

spateo.alignment.methods.deprecated_morpho.con_K(X: numpy.ndarray | torch.Tensor, Y: numpy.ndarray | torch.Tensor, beta: int | float = 0.01, use_chunk: bool = False) → numpy.ndarray | torch.Tensor[source]¶

con_K constructs the Squared Exponential (SE) kernel, where K(i,j)=k(X_i,Y_j)=exp(-beta*||X_i-Y_j||^2).

Parameters:

X: The first vector Xinmathbb{R}^{N imes d}
Y: The second vector Xinmathbb{R}^{M imes d}
beta: The length-scale of the SE kernel.
use_chunk bool, optional: Whether to use chunk to reduce the GPU memory usage. Note that if set to ``True’’ it will slow down the calculation. Defaults to False.

Returns:

The kernel Kinmathbb{R}^{N imes M}

Return type:

Calculating the generating probability matrix P.

Parameters:

XAHat: Current spatial coordinate of sample A. Shape: N x D.
XnB: spatial coordinate of sample B (reference sample). Shape: M x D.
sigma2: The spatial coordinate noise.
beta2: The gene expression noise.
alpha: A vector that encoding each probability generated by the spots of sample A. Shape: N x 1.
gamma: Inlier proportion of sample A.
Sigma: The posterior covariance matrix of Gaussian process. Shape: N x N or N x 1.
GeneDistMat: The gene expression distance matrix between sample A and sample B. Shape: N x M.
SpatialDistMat: The spatial coordinate distance matrix between sample A and sample B. Shape: N x M.
samples_s: The space size of each sample. Area size for 2D samples and volume size for 3D samples.

Returns:

Generating probability matrix P. Shape: N x M.

Return type:

Calculating the generating probability matrix P.

Parameters:

XAHat: Current spatial coordinate of sample A. Shape

spateo.alignment.methods.deprecated_morpho.BA_align(sampleA: anndata.AnnData, sampleB: anndata.AnnData, rep_layer: str | List[str] = 'X', rep_field: str | List[str] = 'layer', genes: List[str] | torch.Tensor | None = None, spatial_key: str = 'spatial', key_added: str = 'align_spatial', iter_key_added: str | None = None, save_concrete_iter: bool = False, vecfld_key_added: str | None = None, dissimilarity: str | List[str] = 'kl', probability_type: str | List[str] = 'gauss', probability_parameters: float | List[float] | None = None, label_transfer_dict: dict | List[dict] | None = None, nn_init: bool = True, allow_flip: bool = False, init_layer: str = 'X', init_field: str = 'layer', max_iter: int = 200, SVI_mode: bool = True, batch_size: int = 1000, pre_compute_dist: bool = True, sparse_calculation_mode: bool = False, lambdaVF: int | float = 100.0, beta: int | float = 0.01, K: int | float = 15, sigma2_init_scale: int | float | None = 0.1, partial_robust_level: float = 25, normalize_c: bool = True, normalize_g: bool = True, dtype: str = 'float32', device: str = 'cpu', verbose: bool = True, guidance_pair: List[numpy.ndarray] | numpy.ndarray | None = None, guidance_effect: bool | str | None = False, guidance_epsilon: float = 1) → Tuple[Tuple[anndata.AnnData, anndata.AnnData], numpy.ndarray][source]¶

Align two spatial transcriptomics AnnData objects using the Spateo alignment algorithm.

Parameters:

sampleA AnnData: The first AnnData object that acts as the reference.
sampleB AnnData: The second AnnData object to be aligned.
rep_layer Union[str, List[str]], optional: Representation layer(s) in AnnData to be used for alignment. Defaults to “X”.
rep_field Union[str, List[str]], optional: Representation layer field(s) in AnnData to be used for alignment. “layer” means gene expression, “obsm” means embdedding like pca or VAE, “obs” means discrete label annotation. Note that Spateo only accept one label annotation. Defaults to “layer”.
genes Optional[Union[List[str], torch.Tensor]], optional: List or tensor of genes to be used for alignment. For example, you can input the genes you are interested or spatially variabe genes here. Defaults to None.
spatial_key str, optional: Key in .obsm of AnnData corresponding to the spatial coordinates. Defaults to “spatial”.
key_added str, optional: Key under which the aligned spatial coordinates are added in .obsm. Defaults to “align_spatial”.
iter_key_added Optional[str], optional: Key under which to store intermediate iteration results in .uns. Defaults to None.
vecfld_key_added Optional[str], optional: Key under which to store vector field results in .uns. Defaults to None.
dissimilarity Union[str, List[str]], optional: Measure(s) of pairwise dissimilarity of each observation to be used. Defaults to “kl”.
probability_type Union[str, List[str]], optional: Type(s) of probability distribution used. Defaults to “gauss”.
probability_parameters Optional[Union[float, List[float]]], optional: Parameters for the probability distribution. Defaults to None.
label_transfer_dict Optional[Union[dict, List[dict]]], optional: Dictionary that stores the label transfer probability. Defaults to None.
nn_init bool, optional: Whether to use nearest neighbor initialization. Defaults to True.
allow_flip bool, optional: Whether to allow flipping of coordinates. Defaults to False.
init_layer str, optional: Layer for init alignment. Defaults to “X”.
init_field str, optional: Layer field for init alignment. Defaults to ‘layer’.
max_iter int, optional: Maximum number of iterations. Defaults to 200.
SVI_mode bool, optional: Whether to use Stochastic Variational Inference mode. Defaults to True.
batch_size int, optional: Size of the mini-batch for SVI. Defaults to 1000.
pre_compute_dist bool, optional: Whether to pre-compute the gene similarity matrix. Defaults to True.
sparse_calculation_mode bool, optional: Whether to use sparse matrix calculations. Defaults to False.
lambdaVF Union[int, float], optional: Regularization parameter for vector field. Defaults to 1e2.
beta Union[int, float], optional: Length-scale of the SE kernel. Defaults to 0.01.
K Union[int, float], optional: Number of sparse inducing points for Nyström approximation. Defaults to 15.
sigma2_init_scale Optional[Union[int, float]], optional: Initial spatial dispersion scale. Defaults to 0.1.
partial_robust_level float, optional: Robust level for partial alignment. Defaults to 25.
normalize_c bool, optional: Whether to normalize spatial coordinates. Defaults to True.
normalize_g bool, optional: Whether to normalize gene expression. Defaults to True.
dtype str, optional: Data type for computations. Defaults to “float32”.
device str, optional: Device for computation, e.g., “cpu” or “0” for GPU. Defaults to “cpu”.
inplace #: Whether to modify adata inplace. Defaults to True.
verbose bool, optional: Whether to print verbose messages. Defaults to True.
guidance_pair Optional[Union[List[np.ndarray], np.ndarray]], optional: Guidance pairs for alignment. Defaults to None.
guidance_effect Optional[Union[bool, str]], optional: Effect of guidance. Defaults to False.
guidance_epsilon float, optional: Epsilon value for guidance. Defaults to 1.

Returns:

A tuple containing the aligned AnnData objects and assignment matrix.

Return type:

Tuple[Tuple[AnnData, AnnData], np.ndarray]