Tools: tl

Any transformation of the data matrix that is not preprocessing. In contrast to a preprocessing function, a tool usually adds an easily interpretable annotation to the data matrix, which can then be visualized with a corresponding plotting function.

Embeddings

tl.spectral(adata[, n_comps, features, ...])	Compute a spectral embedding with Laplacian Eigenmaps.
tl.multi_spectral(adatas[, n_comps, ...])	Compute one spectral embedding from multiple modalities.
tl.umap(adata[, n_comps, use_dims, use_rep, ...])	Compute a UMAP embedding from an existing representation.

Clustering

tl.leiden(adata[, resolution, ...])	Cluster cells with the Leiden community detection algorithm.
tl.kmeans(adata, n_clusters[, n_iterations, ...])	Cluster cells with k-means.
tl.dbscan(adata[, eps, min_samples, ...])	Cluster cells with DBSCAN.
tl.hdbscan(adata[, min_cluster_size, ...])	Cluster cells with HDBSCAN.

Peak calling

tl.macs3(adata, *[, groupby, qvalue, ...])	Call open chromatin peaks with MACS3.
tl.merge_peaks(peaks, chrom_sizes[, half_width])	Merge group-specific peak calls into a non-overlapping peak set.

Differential analysis

tl.marker_regions(data, groupby[, pvalue])	Select marker regions for each group by z-score enrichment.
tl.diff_test(data, cell_group1, cell_group2)	Test regions for differential accessibility between two cell groups.

Motif analysis

tl.motif_enrichment(motifs, regions, ...[, ...])

Test transcription factor motifs for enrichment in region sets.

Network analysis (beta)

tl.init_network_from_annotation(regions, ...)	Build a region-to-gene network from gene annotations.
tl.add_cor_scores(network, *[, gene_mat, ...])	Add Spearman correlation scores to network edges.
tl.add_regr_scores(network, *[, peak_mat, ...])	Add regression-based importance scores to network edges.
tl.add_tf_binding(network, *, motifs, ...[, ...])	Add motif-to-region edges to a regulatory network.
tl.link_tf_to_gene(network)	Create a transcription-factor-to-gene network.
tl.prune_network(network[, node_filter, ...])	Filter nodes and edges from a network.

Utilities

tl.aggregate_X(adata[, groupby, normalize, file])	Aggregate .X values across cells or cell groups.
tl.aggregate_cells(adata[, use_rep, ...])	Assign cells to pseudo-cell groups by iterative clustering.