Tools

Aggregate profiles and ask what the perturbations did.

Aggregation

tl.aggregate(adata[, by, func, min_cells, ...])	Aggregate adata to one profile per group.
tl.consensus(adata[, by, method, ...])	One profile per group, weighting replicates by how well they agree.

Replicates and reproducibility

tl.map(adata[, pos_sameby, pos_diffby, ...])	Mean average precision per group, with a permutation null.
tl.similarity(adata[, metric, use_rep, ...])	Store pairwise profile similarity in obsp[key_added].
tl.percent_replicating(adata[, groupby, ...])	Median replicate correlation against a non-replicate null.
tl.grit(adata[, groupby, reference, metric, ...])	Similarity of each replicate to its group, z-scored against its similarity to the controls.
tl.transport(adata[, by, groupby, ...])	Test whether each perturbation's effect reproduces across settings.
tl.replicate_saturation(adata[, groupby, ...])	Score how much a group's signature improves with each additional replicate.

Hits and effect sizes

tl.hit_calling(adata[, groupby, reference, ...])	Call hits by testing each group's distance from the controls.
tl.edistance(adata[, groupby, reference, ...])	Energy distance between each group and the controls, or between every pair.
tl.effect_size(adata[, groupby, reference, ...])	Per-feature effect size of each group against the reference.
tl.wasserstein_features(adata[, groupby, ...])	Wasserstein-1 distance per feature between each group and the reference.
tl.differential_features(adata[, groupby, ...])	Moderated t-test per feature, per group, with wells as the replicates.
tl.feature_signature(adata[, key, by, statistic])	Collapse a differential table into a perturbation-by-feature-family matrix.
tl.cytotoxicity(adata[, groupby, reference, ...])	Flag perturbations that both lost cells and moved away from the controls.

Dose response

tl.dose_response(adata[, compound_key, ...])	Test whether each compound's response grows with concentration.
tl.dose_features(adata[, compound_key, ...])	Which features respond to a compound's concentration, and at what concentration each one starts.
tl.dose_direction(adata[, compound_key, ...])	Whether a compound's phenotype only grows with concentration, or turns into a different one.
tl.dose_trajectory(adata[, compound_key, ...])	Each compound's whole path through its own responding window, on one comparable axis.

Mechanism of action

tl.nn_moa_classify(adata[, moa_key, metric, ...])	Leave-one-out nearest-neighbor mechanism assignment.
tl.moa_enrichment(adata[, moa_key, groupby, ...])	Test which mechanisms are over-represented among each profile's nearest neighbors.

Feature sets

tl.feature_sets(adata[, by])	Build a decoupler network from the parsed feature annotation.
tl.enrich(adata[, net, by, method, methods, ...])	Score every profile against every feature set.
tl.rank_features(adata, groupby[, method, ...])	Rank features by how well they separate each group, with the annotation attached.
tl.rank_sets(adata, groupby[, score_key, ...])	Rank feature sets by how far each group's score sits from the rest.

Clusters and gene sets

tl.cluster(adata[, use_rep, method, ...])	Cluster the profiles and store the labels, with the linkage tree for a dendrogram.
tl.gene_sets([source, organism])	Fetch a gene-set network, or read one from a GMT file.
tl.ora(adata[, groupby, net, gene_key, ...])	Test each group's genes for over-representation of gene sets.
tl.enrich_hits(adata, net[, gene_key, ...])	Test which gene sets are over-represented among the hits.
tl.pathway_coherence(adata, net[, gene_key, ...])	Score how similar the profiles of each gene set's genes are.
tl.network_enrichment(adata[, ...])	Test the most-similar perturbation pairs for enrichment of known interactions.

Single cells

tl.cluster_composition(adata[, cluster_key, ...])	Fraction of each well's cells in each cluster, as a well-level object.
tl.subpopulation_hits(adata[, cluster_key, ...])	Test each perturbation against the controls within each cluster.
tl.cell_cycle_phase(adata[, dna_feature, ...])	Assign G1, S or G2M from integrated DNA intensity.
tl.neighbors_local_density(adata[, k, by, ...])	Mean distance to the k nearest cells in the same field of view.