COSIE.downstream_analysis

Functions

cluster_and_visualize	Cluster cell embeddings and visualize the results for each tissue section at the spot level.
cluster_and_visualize_superpixel	Perform clustering on superpixel embeddings across multiple tissue sections and visualize the results.
create_normalized_adata	Create a new AnnData object by min-max scaling the expression matrix of the input adata.
highlight_joint_clusters_all_sections	Visualize and highlight specified clusters across all tissue sections.
merge_clusters_to_new_ids	Merge specified cluster IDs into new classes with IDs starting from current max + 1.
perform_prediction	Perform KNN-based prediction for a specific modality in a target tissue section.
plot_histology_clusters	Visualize cluster maps from 2D cluster masks.
plot_marker_comparison	Compare the spatial expression pattern of a specified molecule (e.g., gene, protein..) across two tissue sections at the spot level, each represented by an AnnData object.
plot_marker_comparison_superpixel	Plot side-by-side spatial expression comparison of a target molecule at the superpixel level.
prepare_image	Prepare a 2D image from molecule expression and spatial coordinates in an AnnData object.
relabel_clusters_sequentially	Relabel all cluster IDs across sections to contiguous integers starting from 0.
truncate_gene_expression_smartclip	Truncate expression data based on non-zero values to reduce the impact of extreme outliers in visualization.
visualize_global_cluster_centroid_dendrogram	Visualize dendrogram for clusters shared across sections.
visualize_section_cluster_centroids_dendrogram	Visualize hierarchical clustering dendrogram within a single section.