API

Import decoupler as:

import decoupler as dc

Preprocessing:

`extract`(mat[, use_raw, verbose, dtype])	Processes different input types so that they can be used downstream.
`filt_min_n`(c, net[, min_n])	Removes sources of a net with less than min_n targets.
`match`(c, r, net)	Matches mat with a regulatory adjacency matrix.
`rename_net`(net[, source, target, weight])	Renames input network to match decoupler's format (source, target, weight).
`get_net_mat`(net)	Transforms a given network to a regulatory adjacency matrix (targets x sources).
`break_ties`(m, c, seed)

Methods:

`run_aucell`(mat, net[, source, target, n_up, ...])	AUCell.
`run_gsea`(mat, net[, source, target, times, ...])	Gene Set Enrichment Analysis (GSEA).
`run_gsva`(mat, net[, source, target, kcdf, ...])	Gene Set Variation Analysis (GSVA).
`run_mdt`(mat, net[, source, target, weight, ...])	Multivariate Decision Tree (MDT).
`run_mlm`(mat, net[, source, target, weight, ...])	Multivariate Linear Model (MLM).
`run_ora`(mat, net[, source, target, n_up, ...])	Over Representation Analysis (ORA).
`run_udt`(mat, net[, source, target, weight, ...])	Univariate Decision Tree (UDT).
`run_ulm`(mat, net[, source, target, weight, ...])	Univariate Linear Model (ULM).
`run_viper`(mat, net[, source, target, ...])	Virtual Inference of Protein-activity by Enriched Regulon (VIPER).
`run_wmean`(mat, net[, source, target, ...])	Weighted mean (WMEAN).
`run_wsum`(mat, net[, source, target, weight, ...])	Weighted sum (WSUM).
`run_consensus`(mat, net[, source, target, ...])	Consensus score from top methods.

Running multiple methods:

`decouple`(mat, net[, source, target, weight, ...])	Decouple function.
`cons`(res)	Consensus score between methods.
`dense_run`(func, mat, net[, source, target, ...])	Run a method without zero values.

General utils:

`melt`(df)	Function to generate a long format dataframe similar to the one obtained in the R implementation of decoupler.
`show_methods`()	Shows available methods.
`check_corr`(net[, source, target, weight, ...])	Checks the correlation across the regulators in a network.
`get_toy_data`([n_samples, seed])	Generate a toy mat and net for testing.
`summarize_acts`(acts, groupby[, obs, mode, ...])	Summarizes activities obtained per group by their mean or median and removes features that do not change across samples.
`assign_groups`(summary)	Assigns group labels based on summary activities.
`dense_run`(func, mat, net[, source, target, ...])	Run a method without zero values.
`p_adjust_fdr`(p)	Benjamini-Hochberg p-value correction for multiple hypothesis testing.
`shuffle_net`(net[, target, weight, seed, ...])	Shuffle network to make it random.
`read_gmt`(path)	Read a GMT file and return a `pd.DataFrame`.

AnnData utils:

`get_acts`(adata, obsm_key[, dtype])	Extracts activities as AnnData object.
`swap_layer`(adata, layer_key[, X_layer_key, ...])	Swaps an `adata.X` for a given layer.
`get_pseudobulk`(adata, sample_col, groups_col)	Summarizes expression profiles across cells per sample and group.
`get_contrast`(adata, group_col, ...[, ...])	Computes Differential Expression Analysis using scanpy's rank_genes_groups function between two conditions from pseudo-bulk profiles.
`get_top_targets`(logFCs, pvals, contrast[, ...])	Return significant target features for a given source and contrast.
`format_contrast_results`(logFCs, pvals)	Formats the results from get_contrast into a long format data-frame.
`filter_by_expr`(adata[, obs, group, ...])	Determine which genes have sufficiently large counts to be retained in a statistical analysis.
`filter_by_prop`(adata[, min_prop, min_smpls])	Determine which genes are expressed in a sufficient proportion of cells across samples.
`get_metadata_associations`(data[, obs_keys, ...])	Associate the data to sample metadata using ANOVA.
`rank_sources_groups`(adata, groupby[, ...])	Rank sources for characterizing groups.

Omnipath wrappers:

`show_resources`()	Shows available resources in Omnipath.
`get_resource`(name[, organism, ...])	Wrapper to access resources inside Omnipath.
`get_progeny`([organism, top, genesymbol_resource])	Pathway RespOnsive GENes for activity inference (PROGENy).
`get_dorothea`([organism, levels, ...])	DoRothEA gene regulatory network.
`get_collectri`([organism, split_complexes, ...])	CollecTRI gene regulatory network.
`translate_net`(net[, columns, ...])	Translate networks between species by orthology.

Plotting

`plot_volcano`(logFCs, pvals, contrast[, ...])	Plot logFC and p-values.
`plot_violins`(mat[, thr, log, use_raw, ...])	Plot distribution of features' values per sample.
`plot_barplot`(acts, contrast[, top, ...])	Plot barplots showing the top absolute value activities.
`plot_metrics_scatter`(df[, x, y, groupby, ...])	Plot scatter plot of metrics across two different axes.
`plot_metrics_scatter_cols`(df, col[, x, y, ...])	Extension of the function plot_metrics_scatter to group metrics by two categories at the same time.
`plot_metrics_boxplot`(df, metric[, groupby, ...])	Plot boxplots showing the distribution of scores between methods for a metric.
`plot_psbulk_samples`(adata, groupby[, ...])	Quality Control plot to assess the quality of the obtained pseudobulk samples.
`plot_filter_by_expr`(adata[, obs, group, ...])	Plot to help determining the thresholds of the `decoupler.filter_by_expr` function.
`plot_filter_by_prop`(adata[, min_prop, ...])	Plot to help determining the thresholds of the `decoupler.filter_by_prop` function.
`plot_volcano_df`(data, x, y[, top, sign_thr, ...])	Plot logFC and p-values from a long formated data-frame.
`plot_targets`(data, stat, source_name, net[, ...])	Plot the weight and statistic of the target genes of a given source.
`plot_running_score`(df, stat, net, set_name)	Plot the running score of GSEA.
`plot_barplot_df`(df, x, y[, color, thr, ...])	Plot results of enrichment analysis as bars.
`plot_dotplot`(df, x, y, c, s[, scale, cmap, ...])	Plot results of enrichment analysis as dots.
`plot_associations`(data, uns_key[, ...])	Create a composite plot displaying association results between scores (bottom) and summary statistics (top) using a clustermap.
`plot_network`(net[, obs, act, n_sources, ...])	Plot results of enrichment analysis as network.

Metrics

`metric_auroc`(y_true, y_score)	Area Under the Receiver Operating characteristic Curve (AUROC)
`metric_auprc`(y_true, y_score[, pi0])	Area Under the Precision-Recall Curve (AUPRC)
`metric_mcauroc`(y_true, y_score[, n_iter, seed])	Monte-Carlo Area Under the Receiver Operating characteristic Curve (AUROC)
`metric_mcauprc`(y_true, y_score[, n_iter, seed])	Monte-Carlo Area Under the Precision-Recall Curve (AUPRC)

Benchmark utils

`get_toy_benchmark_data`([n_samples, seed, ...])	Generate a toy mat, net and obs for testing the benchmark pipeline.
`show_metrics`()	Shows available evaluation metrics.

Benchmark

`benchmark`(mat, obs, net, perturb, sign[, ...])	Benchmark methods or networks on a given set of perturbation experiments using activity inference with decoupler.
`format_benchmark_inputs`(mat, obs, perturb, ...)
`get_performances`(res, obs, groupby, by, metrics)

Other

`get_ora_df`(df, net[, source, target, ...])	Wrapper to run ORA for results of differential analysis (long format dataframe).
`get_gsea_df`(df, stat, net[, source, target, ...])	Wrapper to run GSEA for results of differential analysis (long format dataframe).