decoupler.mt.consensus#

decoupler.mt.consensus(result, verbose=False)#

Consensus score across methods.

For each method, enrichment scores are split into positive and negative subsets and transformed independently into z-scores.

Subset values based on sign (direction).
Mirror each subset into positive and negative values with the same magnitude.
Compute z-scores for each subset: $z_i = \frac{x_i - \mu}{\sigma}$ .
Restore the original signs to the z-scored values

This transformation ensures comparability across methods while preserving the biological interpretation of activation (positive) and inhibition (negative). The final consensus enrichment score $ES$ is computed as the mean of these signed z-scores across methods.

ES = \frac{\sum_{m=1}^{M} z_{i}^{(m)}}{M}

Where:

$M$ is the number of methods
$z_{i}^{(m)}$ is the z-score from method $m$ .

A two-sided $p_{value}$ is then calculated from the consensus score using the survival function $sf$ of the standard normal distribution.

p = 2 \times \mathrm{sf}\bigl(\lvert \mathrm{ES} \rvert \bigr)

Finally, the obtained $p_{value}$ are adjusted by Benjamini-Hochberg correction.

Parameters:

result (dict | AnnData) – Results from decoupler.mt.decouple.
verbose (bool (default: False)) – Whether to display progress messages and additional execution details.

Return type:

tuple[DataFrame, DataFrame] | None

Returns:

Consensus enrichment scores and p-values.

Example

import decoupler as dc

adata, net = dc.ds.toy()
dc.mt.decouple(adata, net, tmin=3)
dc.mt.consensus(adata)

decoupler.mt.consensus

Contents

decoupler.mt.consensus#