scglue.data.metacell_regr
- scglue.data.metacell_regr(*adatas, use_rep=None, n_meta=None, skeleton=None, model='Lasso', **kwargs)[源代码]
Metacell-based regression
- 参数:
*adatas (
AnnData
) – Datasets to be correlated, where.X
are raw counts (indexed by modality name)use_rep (
typing.Optional
[str
]) – Data representation based on which to cluster meta-cellsn_meta (
typing.Optional
[int
]) – Number of metacells to useskeleton (
typing.Optional
[DiGraph
]) – Skeleton graph determining which pair of features to correlatemodel (
str
) – Regression model (should be a class name undersklearn.linear_model
)**kwargs – Additional keyword arguments are passed to the regression model
- 返回类型:
- 返回:
regr – A skeleton-based graph containing regression weights as edge attribute “regr”