Preprocessing

Data

pp.extract(data[, layer, raw, empty, ...])

Extracts matrix, rownames and colnames from data.

Network

pp.read_gmt(path)	Read a GMT file and return the feature sets as a network.
pp.prune(features, net[, tmin, verbose])	Removes sources of a net with less than tmin targets shared with mat.
pp.adjmat(features, net[, verbose])	Converts a network in long format into a regulatory adjacency matrix (targets x sources).
pp.idxmat(features, net[, verbose])	Indexes and returns feature sets as a decomposed sparse matrix.
pp.shuffle_net(net[, target, weight, seed, ...])	Shuffle a network to make it random.
pp.net_corr(net[, data, tmin, verbose])	Checks the correlation across the sources in a network.

AnnData

pp.get_obsm(adata, key)	Extracts values stored in .obsm as a new AnnData object.
pp.swap_layer(adata, key[, X_key, inplace])	Swaps an AnnData.X for a given layer key.
pp.pseudobulk(adata, sample_col, groups_col)	Summarizes omic profiles across cells, grouped by sample and optionally by group categories.
pp.filter_samples(adata[, min_cells, ...])	Remove pseudobulked samples with insufficient number of cells and total counts.
pp.filter_by_expr(adata[, group, lib_size, ...])	Determine which genes have sufficiently large counts to be retained in a statistical analysis.
pp.filter_by_prop(adata[, min_prop, ...])	Determine which genes are expressed in a sufficient proportion of cells across samples.
pp.knn(adata[, key, bw, max_nn, cutoff])	Adds K-Nearest Neighbors similarities based on spatial distances.
pp.bin_order(adata, order[, names, label, nbins])	Bins features along a continuous, ordered process such as pseudotime.