ehrapy.preprocessing.regress_out

Contents

ehrapy.preprocessing.regress_out#

ehrapy.preprocessing.regress_out(edata, *, keys, n_jobs=None, layer=None, copy=False)[source]#

Regress out (mostly) unwanted sources of variation.

Uses simple linear regression. This is inspired by Seurat’s regressOut function in R [Satija15]. Note that this function tends to overcorrect in certain circumstances.

Parameters:

  • edata (EHRData) – Central data object.

  • keys (str | Sequence[str]) – Keys for observation annotation on which to regress on.

  • n_jobs (int | None, default: None) – Number of jobs for parallel computation.

  • layer (str | None, default: None) – The layer to operate on.

  • copy (bool, default: False) – Determines whether a copy of adata is returned.

Return type:

EHRData | None

Returns:

Depending on copy returns or updates the data object with the corrected data matrix.

Contents