rapids_singlecell.dcg.gsva#

rapids_singlecell.dcg.gsva = <rapids_singlecell.decoupler_gpu._helper._Method.Method object>#

Gene Set Variation Analysis (GSVA).

Transform features with a Gaussian, Poisson, or empirical cumulative distribution, then calculate feature-set enrichment with a random walk.

This method does not perform statistical testing on ES and therefore does not return pvalue.

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

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

layer

Layer key name of an anndata.AnnData instance.

raw

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

empty

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

bsize

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. If omitted, uses the method’s default batch size.

verbose

Whether to display progress messages and additional execution details.

pre_load

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.

kcdf

Density transformation. One of "gaussian", "poisson", or None for the empirical cumulative distribution.

maxdiff

Whether to combine the maximum positive and negative deviations.

absrnk

If maxdiff=True, whether enrichment at either extreme is positive.

tau

Exponent applied to the rank statistic.

Notes

In-memory and Dask inputs use all observations together for density estimation. Backed inputs use bsize observations per batch, matching Decoupler; changing that batch size can change the scores.

Returns:

Enrichment scores ES and, if applicable, adjusted pvalue by Benjamini-Hochberg.