stereo.core.StPipeline

class stereo.core.StPipeline(data)

__init__(data)

A analysis tool sets for StereoExpData. include preprocess, filter, cluster, plot and so on.

Parameters:

data (Union[StereoExpData, AnnBasedStereoExpData]) – StereoExpData object.

Methods

__init__(data)	A analysis tool sets for StereoExpData.
adjusted_rand_score(cluster_res_key_a, ...)	Calculate Adjusted Rand index between two cluster results.
annotation(annotation_information[, ...])	Set annotation to clusters.
batches_integrate([pca_res_key, res_key])	integrate different experiments base on the pca result
cal_qc()	Calculate the key indicators of quality control.
disksmooth_zscore([r, inplace, res_key])	for each position, given a radius, calculate the z-score within this circle as final normalized value.
filter_by_clusters([cluster_res_key, ...])	Filter cells based on clustering result.
filter_by_hvgs([hvg_res_key, filter_raw, ...])	Filter genes based on the result of highly_variable_genes function.
filter_cells([min_gene, max_gene, ...])	Filter cells based on counts or the numbers of genes expressed.
filter_coordinates([min_x, max_x, min_y, ...])	Filter cells based on coordinate information.
filter_genes([min_cell, max_cell, ...])	Filter genes based on the numbers of cells or counts.
filter_marker_genes([marker_genes_res_key, ...])	Filters out genes based on log fold change and fraction of genes expressing the gene within and outside each group.
find_marker_genes(cluster_res_key[, method, ...])	A tool to find maker genes.
gaussian_smooth([n_neighbors, ...])	Smooth the express matrix by the algorithm of Gaussian smoothing [Shen22].
get_neighbors_res(neighbors_res_key)	get the neighbor result by the key.
highly_variable_genes([groups, method, ...])	Annotate highly variable genes, refering to Scanpy.
leiden([neighbors_res_key, res_key, ...])	Cluster cells into subgroups by Leiden algorithm [Traag18].
log1p([inplace, res_key])	Transform the express matrix logarithmically.
louvain([neighbors_res_key, res_key, ...])	Cluster cells into subgroups by Louvain algorithm [Blondel08].
lr_score(lr_pairs[, distance, spot_comp, ...])	calculate cci score for each LR pair and do permutation test
neighbors([pca_res_key, method, metric, ...])	Compute a spatial neighborhood graph over all cells.
normalize_total([target_sum, inplace, res_key])	Normalize total counts over all genes per cell such that each cell has the same total count after normalization.
pca([use_highly_genes, n_pcs, svd_solver, ...])	Principal component analysis.
phenograph([phenograph_k, pca_res_key, ...])	Cluster cells into subgroups by Phenograph.
quantile([inplace, res_key])	Normalize the columns of X to each have the same distribution.
raw_checkpoint()	Save current data to self.raw.
reset_raw_data()	Reset self.data to the raw data saved in self.raw when you want data get raw expression matrix.
scale([zero_center, max_value, inplace, res_key])	Scale express matrix to unit variance and zero mean.
sctransform([n_cells, n_genes, filter_hvgs, ...])	Normalization of scTransform, refering to Seurat [Hafemeister19].
silhouette_score(cluster_res_key[, metric, ...])	Calculate the mean Silhouette Coefficient for a cluster result.
spatial_hotspot([use_highly_genes, ...])	Identify informative genes or gene modules.
spatial_neighbors([neighbors_res_key, ...])	Create a graph from spatial coordinates using Squidpy.
spatial_pattern_score([use_raw, res_key])	calculate the spatial pattern score.
subset_by_hvg(hvg_res_key[, use_raw, inplace])	get the subset by the result of highly variable genes.
umap([pca_res_key, neighbors_res_key, ...])	Embed the neighborhood graph using UMAP [McInnes18].

Attributes

raw	get the StereoExpData whose exp_matrix is raw count.