rapids_singlecell.dcg.aucell

Contents

rapids_singlecell.dcg.aucell#

rapids_singlecell.dcg.aucell = <rapids_singlecell.decoupler_gpu._method_aucell.AucellMethod object>[source]#

Area Under the Curve for set enrichment within single cells (AUCell).

Given a ranked list of features per observation, AUCell calculates the AUC by measuring how early the features in the set appear in this ranking. Specifically, the enrichment score \(ES\) is:

\[{ES}_{i, F} = \int_0^1 {RecoveryCurve}_{i, F}(r_i) \, dr\]

Where:

  • \(i\) is the observation

  • \(F\) is the feature set

  • \({RecoveryCurve}_{i, F}(r_i)\) is the proportion of features from \(F\) recovered in the top \(r_i\)-fraction of the ranked list for observation \(i\)

This method does not perform statistical testing on \(ES\) and therefore does not return \(p_{value}\).

Parameters:
data

AnnData instance, DataFrame or tuple of [matrix, samples, features].

net

Dataframe in long format. Must include source and target columns, and optionally a weight column.

tmin default: 5

Minimum number of targets per source. Sources with fewer targets will be removed.

layer

Layer key name of an anndata.AnnData instance.

raw default: False

Whether to use the .raw attribute of anndata.AnnData.

empty default: True

Whether to remove empty observations (rows) or features (columns).

bsize default: 100

For large datasets in sparse format, this parameter controls how many observations are processed at once. Increasing this value speeds up computation but uses more memory.

verbose default: False

Whether to display progress messages and additional execution details.

pre_load default: False

Whether to pre-load the data into memory. If True, the data will be pre-loaded into memory before processing.

adj_pv_gpu

Whether to use GPU for adjusting p-values.

n_up default: None

Number of features to include in the AUC calculation. If None, the top 5% of features based on their magnitude are selected.

Returns:

Enrichment scores \(ES\) and, if applicable, adjusted \(p_{value}\) by Benjamini-Hochberg.

Example

import decoupler as dc

adata, net = dc.ds.toy()
rsc.dcg.aucell(adata, net, tmin=3)
Contents