decoupler.decouple
- decoupler.decouple(mat, net, source='source', target='target', weight='weight', methods=None, args={}, consensus=True, cns_metds=None, min_n=5, verbose=True, use_raw=True, dense=False)
Decouple function.
Runs simultaneously several methods of biological activity inference.
- Parameters:
- matlist, DataFrame or AnnData
List of [features, matrix], dataframe (samples x features) or an AnnData instance.
- netDataFrame
Network in long format.
- sourcestr
Column name in net with source nodes.
- targetstr
Column name in net with target nodes.
- weightstr
Column name in net with weights.
- methodslist, str, None
List of methods to run. If none are provided use weighted top performers (mlm, ulm and wsum). To run all methods set to “all”.
- argsdict
A dict of argument-dicts.
- consensusbool
Boolean whether to run a consensus score between methods.
- cns_metdslist
List of estimate names to use for the calculation of the consensus score. If empty it will use all the estimates obtained after running the different methods. If methods is also None, it will use mlm, ulm and norm_wsum instead.
- min_nint
Minimum of targets per source. If less, sources are removed.
- verbosebool
Whether to show progress.
- use_rawbool
If mat is AnnData, use its raw attribute.
- densebool
Whether to run methods ignoring zero values per observation. See
decoupler.dense_runfor more information.
- Returns:
- resultsdict
Dictionary of activity estimates and p-values. If mat is AnnData, results for each method are stored in .obsm[‘method_estimate’] and if available in .obsm[‘method_pvals’].