stlearn.spatial.trajectory.pseudotime

stlearn.spatial.trajectory.pseudotime(adata: AnnData, use_label: str = 'leiden', eps: float = 20, n_neighbors: int = 25, use_rep: str = 'X_pca', threshold: float = 0.01, radius: int = 50, method: Literal['mean', 'median', 'sum'] = 'mean', threshold_spots: int = 5, use_sme: bool = False, reverse: bool = False, pseudotime_key: str = 'dpt_pseudotime', max_nodes: int = 4, run_knn: bool = False, copy: bool = False) → AnnData | None[source]

Perform pseudotime analysis.

Parameters:

  • adata – Annotated data matrix.

  • use_label – Use label result of cluster method.

  • eps – The maximum distance between two samples for one to be considered as in the neighborhood of the other. This is not a maximum bound on the distances of points within a cluster. This is the most important DBSCAN parameter to choose appropriately for your data set and distance function.

  • threshold – Threshold to find the significant connection for PAGA graph.

  • radius – radius to adjust data for diffusion map

  • method – method to adjust the data.

  • use_sme – Use adjusted feature by SME normalization or not

  • reverse – Reverse the pseudotime score

  • pseudotime_key – Key to store pseudotime

  • max_nodes – Maximum number of node in available paths

  • copy – Return a copy instead of writing to adata.

Notes

Each run clears any previously computed values for: X_diffmap, X_draw_graph_fr, X_diffmap_morphology, split_node, global_graph, centroid_dict, available_paths, threshold_spots, and sub_cluster_labels.

Return type:

Anndata