Tools: tl

This module provides various tools for analyzing proteomics data.

Clustering

tl.leiden_mito_sweep	Find optimal leiden clustering resolution based on mitochondrial protein clustering.
tl.knn_annotation	Annotate proteins based on their k-nearest neighbors.
tl.calculate_interfacialness_score	Calculate interfacialness scores for proteins based on their neighborhood annotations.
tl.get_n_nearest_neighbors	Get n nearest neighbors up to a specified order.
tl.silhouette_score	Calculate silhouette scores for clustered data.
tl.calinski_habarasz_score	Calculate Calinski-Harabasz score for clustered data.
tl.tagm_map_train	Train the TAGM MAP model on an AnnData object.
tl.tagm_map_predict	Predict subcellular localization for unknown proteins using MAP parameters.

Enrichment

tl.calculate_cluster_enrichment

Calculate cluster enrichment using gseapy.

Integration

tl.align_adatas	Align multiple AnnData objects by intersecting their observations and variables.
tl.aligned_umap	Calculate aligned UMAP embeddings for multiple datasets.
tl.remodeling_score	Get aligned UMAP embeddings from each AnnData object.