spateo.tdr.interpolations

Subpackages

• spateo.tdr.interpolations.interpolation_deeplearn
  • spateo.tdr.interpolations.interpolation_deeplearn.deep_interpolation
  • spateo.tdr.interpolations.interpolation_deeplearn.interpolation_nn
  • spateo.tdr.interpolations.interpolation_deeplearn.nn_losses
• spateo.tdr.interpolations.interpolation_gaussianprocess
  • spateo.tdr.interpolations.interpolation_gaussianprocess.gp_models
  • spateo.tdr.interpolations.interpolation_gaussianprocess.gp_train

Submodules

• spateo.tdr.interpolations.interpolation_dl
• spateo.tdr.interpolations.interpolation_gp
• spateo.tdr.interpolations.interpolation_sparseVFC
• spateo.tdr.interpolations.interpolation_vtk
• spateo.tdr.interpolations.utils

Package Contents

Functions

deep_intepretation(→ anndata.AnnData)	Learn a continuous mapping from space to gene expression pattern with the deep neural net model.
gp_interpolation(→ anndata.AnnData)	Learn a continuous mapping from space to gene expression pattern with the Gaussian Process method.
kernel_interpolation(→ anndata.AnnData)	Learn a continuous mapping from space to gene expression pattern with Kernel method (sparseVFC).
vtk_interpolation(→ anndata.AnnData)	Learn a continuous mapping from space to gene expression pattern with the method contained in VTK.
get_X_Y_grid(→ Tuple[numpy.ndarray, numpy.ndarray, ...)	Prepare the X (spatial coordinates), Y (gene expression) and grid points for the kernel or deep model.

spateo.tdr.interpolations.deep_intepretation(source_adata: anndata.AnnData, target_points: numpy.ndarray | None = None, keys: str | list = None, spatial_key: str = 'spatial', layer: str = 'X', max_iter: int = 1000, data_batch_size: int = 2000, autoencoder_batch_size: int = 50, data_lr: float = 0.0001, autoencoder_lr: float = 0.0001, **kwargs) → anndata.AnnData

Learn a continuous mapping from space to gene expression pattern with the deep neural net model.

Parameters:

source_adata

AnnData object that contains spatial (numpy.ndarray) in the obsm attribute.

target_points

The spatial coordinates of new data point. If target_coords is None, generate new points based on grid_num.

keys

Gene list or info list in the obs attribute whose interpolate expression across space needs to learned.

spatial_key

The key in .obsm that corresponds to the spatial coordinate of each bucket.

layer

If 'X', uses .X, otherwise uses the representation given by .layers[layer].

max_iter

The maximum iteration the network will be trained.

data_batch_size

The size of the data sample batches to be generated in each iteration.

autoencoder_batch_size

The size of the auto-encoder training batches to be generated in each iteration. Must be no greater than batch_size. .

data_lr

The learning rate for network training.

autoencoder_lr

The learning rate for network training the auto-encoder. Will have no effect if network_dim equal data_dim.

**kwargs

Additional parameters that will be passed to the training step of the deep neural net.

Returns:

an anndata object that has interpolated expression.

Return type:

interp_adata

spateo.tdr.interpolations.gp_interpolation(source_adata: anndata.AnnData, target_points: numpy.ndarray | None = None, keys: str | list = None, spatial_key: str = 'spatial', layer: str = 'X', training_iter: int = 50, device: str = 'cpu', method: Literal[SVGP, ExactGP] = 'SVGP', batch_size: int = 1024, shuffle: bool = True, inducing_num: int = 512) → anndata.AnnData

Learn a continuous mapping from space to gene expression pattern with the Gaussian Process method.

Parameters:

source_adata

AnnData object that contains spatial (numpy.ndarray) in the obsm attribute.

target_points

The spatial coordinates of new data point. If target_coords is None, generate new points based on grid_num.

keys

Gene list or info list in the obs attribute whose interpolate expression across space needs to learned.

spatial_key

The key in .obsm that corresponds to the spatial coordinate of each bucket.

layer

If 'X', uses .X, otherwise uses the representation given by .layers[layer].

training_iter

Max number of iterations for training.

device

Equipment used to run the program. You can also set the specified GPU for running. E.g.: '0'.

Returns:

an anndata object that has interpolated expression.

Return type:

interp_adata

spateo.tdr.interpolations.kernel_interpolation(source_adata: anndata.AnnData, target_points: numpy.ndarray | None = None, keys: str | list = None, spatial_key: str = 'spatial', layer: str = 'X', lambda_: float = 0.02, lstsq_method: str = 'scipy', **kwargs) → anndata.AnnData

Learn a continuous mapping from space to gene expression pattern with Kernel method (sparseVFC).

Parameters:

source_adata

AnnData object that contains spatial (numpy.ndarray) in the obsm attribute.

target_points

The spatial coordinates of new data point. If target_coords is None, generate new points based on grid_num.

keys

Gene list or info list in the obs attribute whose interpolate expression across space needs to learned.

spatial_key

The key in .obsm that corresponds to the spatial coordinate of each bucket.

layer

If 'X', uses .X, otherwise uses the representation given by .layers[layer].

lambda

Represents the trade-off between the goodness of data fit and regularization. Larger Lambda_ put more weights on regularization.

lstsq_method

The name of the linear least square solver, can be either ‘scipy` or douin.

**kwargs

Additional parameters that will be passed to SparseVFC function.

Returns:

an anndata object that has interpolated expression.

Return type:

interp_adata

spateo.tdr.interpolations.vtk_interpolation(source_adata: anndata.AnnData, target_points: numpy.ndarray | None = None, keys: str | list = None, spatial_key: str = 'spatial', layer: str = 'X', radius: float | None = None, n_points: int | None = None, kernel: Literal[shepard, gaussian, linear] = 'shepard', null_strategy: Literal[0, 1, 2] = 1, null_value: int | float = 0) → anndata.AnnData

Learn a continuous mapping from space to gene expression pattern with the method contained in VTK.

Parameters:

source_adata

AnnData object that contains spatial (numpy.ndarray) in the obsm attribute.

target_points

The spatial coordinates of new data point. If target_coords is None, generate new points based on grid_num.

keys

Gene list or info list in the obs attribute whose interpolate expression across space needs to learned.

spatial_key

The key in .obsm that corresponds to the spatial coordinate of each bucket.

layer

If 'X', uses .X, otherwise uses the representation given by .layers[layer].

radius

Set the radius of the point cloud. If you are generating a Gaussian distribution, then this is the standard deviation for each of x, y, and z.

n_points

Specify the number of points for the source object to hold. If n_points (number of the closest points to use) is set then radius value is ignored.

kernel

The kernel of interpolations kernel. Available kernels are: * shepard: vtkShepardKernel is an interpolations kernel that uses the method of Shepard to perform

interpolations. The weights are computed as 1/r^p, where r is the distance to a neighbor point within the kernel radius R; and p (the power parameter) is a positive exponent (typically p=2).

• gaussian: vtkGaussianKernel is an interpolations kernel that simply returns the weights for all

  points found in the sphere defined by radius R. The weights are computed as: exp(-(s*r/R)^2) where r is the distance from the point to be interpolated to a neighboring point within R. The sharpness s simply affects the rate of fall off of the Gaussian.

• linear: vtkLinearKernel is an interpolations kernel that averages the contributions of all points in

  the basis.

null_strategy

Specify a strategy to use when encountering a “null” point during the interpolations process.

Null points occur when the local neighborhood(of nearby points to interpolate from) is empty.

• Case 0: an output array is created that marks points as being valid (=1) or null (invalid =0), and

  the nullValue is set as well

• Case 1: the output data value(s) are set to the provided nullValue

• Case 2: simply use the closest point to perform the interpolations.

null_value

see above.

Returns:

an anndata object that has interpolated expression.

Return type:

interp_adata

spateo.tdr.interpolations.get_X_Y_grid(adata: anndata.AnnData | None = None, genes: List | None = None, X: numpy.ndarray | None = None, Y: numpy.ndarray | None = None, grid_num: List = [50, 50, 50]) → Tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray]

Prepare the X (spatial coordinates), Y (gene expression) and grid points for the kernel or deep model.

Parameters:

adata

AnnData object that contains spatial (numpy.ndarray) in the obsm attribute.

genes

Gene list whose interpolate expression across space needs to learned. If Y is provided, genes will only be used to retrive the gene annotation info.

X

The spatial coordinates of each data point.

Y

The gene expression of the corresponding data point.

grid_num

Number of grid to generate. Default is 50 for each dimension. Must be non-negative.

Returns:

spatial coordinates. Y: gene expression of the associated spatial coordinates. Grid: grid points formed with the input spatial coordinates. grid_in_hull: A list of booleans indicates whether the current grid points is within the convex hull formed by

the input data points.

Return type:

X