Tools: tl

This module provides various tools for analyzing proteomics data.

Clustering

tl.leiden_mito_sweep	Automated sweep to pick a Leiden resolution that keeps mitochondria intact.
tl.markov_clustering	Run Markov Clustering (MCL) on the neighbour graph.
tl.calculate_interfacialness_score	Quantify interfacialness of proteins across compartment boundaries.
tl.silhouette_score	Per-group silhouette scores.
tl.calinski_habarasz_score	Calinski–Harabasz score of cluster compactness vs separation.
tl.qsep_score	QSep cluster-separation metric for spatial proteomics.
tl.tagm_map_train	Train a TAGM-MAP (T-Augmented Gaussian Mixture, MAP variant) model.
tl.tagm_map_predict	Predict sub-cellular localization for unlabelled proteins using a fitted TAGM-MAP model.
tl.knn_f1_score	F1 score.
tl.class_balance	Return a balanced subset with equally sized clusters.

Cluster Merging

Consolidate overclustered Leiden solutions using PAGA connectivity and ontology enrichment.

tl.merge_clusters_go	Iteratively merge overclustered Leiden clusters using PAGA and GO enrichment.
tl.merge_small_clusters	Iteratively merge small clusters into their most-connected neighbor.
tl.paga_dendrogram	Build a dendrogram from PAGA connectivity and store it in adata.uns.
tl.dendrogram_cherry_pairs	Return all candidate merge pairs from the dendrogram, expanding ties.

Semi-supervised Localization

Propagate mutually exclusive labels (markers) along the k-NN graph, or train a classifier on them.

tl.competitive_propagation	Propagate categorical annotations along the k-NN graph.
tl.knn_annotation	Deprecated alias for competitive_propagation().
tl.soft_cluster_annotation	Soft, uncertainty-aware version of the cluster-annotation pipeline.
tl.resolve_soft_labels	Resolve soft propagated probabilities into single / multi / unresolved labels.
tl.svm_train	Train SVM classifier with hyperparameter tuning using marker proteins.
tl.svm_annotation	Classify proteins using SVM with marker-based training.

Ontology-aware Annotation

Propagate overlapping / hierarchical labels (GO-CC, UniProt-SL) one-vs-rest, which yields per-term membership probabilities rather than a simplex.

tl.independent_diffusion	Annotate a map with overlapping / hierarchical labels by one-vs-rest diffusion.
tl.resolve_diffusion	(Re)resolve stored diffusion probabilities into a per-protein label, in place.

Ontology Enrichment

tl.calculate_cluster_enrichment	Gene-set enrichment for each cluster.
tl.enrichment_to_cluster_distribution	Turn a per-cluster enrichment table into soft label distributions.

Model-based Gene Set Analysis

MGSA explains an observed protein set with a sparse set of ontology terms, rather than testing each term independently.

tl.mgsa	Run model-based gene set analysis.
tl.calculate_mgsa	Model-based gene-set analysis (MGSA) per cluster.
tl.mgsa_to_cluster_distribution	Convert a per-cluster MGSA posterior matrix into a soft-label distribution.
tl.MgsaResult	Container for MGSA posterior summaries and diagnostics.
tl.load_gmt	Resolve a gene-set source into a {term: [gene, ...]} dict.

C-COMPASS

Neural-network compartment prediction, provided by the optional ccompass extra (pip install grassp[ccompass]).

tl.ccompass	Predict compartment class contributions with the C-COMPASS neural network.
tl.ccompass_default_params	Return (and optionally save) the default C-COMPASS hyperparameters used by ccompass().

Integration

tl.align_adatas	Return copies of several AnnData objects with matching index/columns.
tl.aligned_umap	Aligned UMAP embedding for matched datasets.
tl.remodeling_score	Compute per-protein remodeling score from two aligned datasets.
tl.mr_score	M/R score for detecting protein translocation.

Graph analysis

tl.to_knn_graph	Convert the k-NN graph stored in AnnData to a networkx graph.
tl.get_n_nearest_neighbors	Return the set of closest neighbours for a node in a graph.