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 and therefore does not return .
- Parameters:
- data
AnnData instance, DataFrame or tuple of [matrix, samples, features].
- net
Dataframe in long format. Must include
sourceandtargetcolumns, and optionally aweightcolumn.- tmin
Minimum number of targets per source. Sources with fewer targets will be removed.
- layer
Layer key name of an
anndata.AnnDatainstance.- raw
Whether to use the
.rawattribute ofanndata.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", orNonefor 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
bsizeobservations per batch, matching Decoupler; changing that batch size can change the scores.- Returns:
Enrichment scores and, if applicable, adjusted by Benjamini-Hochberg.