nico_annotations.utils package

Submodules

nico_annotations.utils.SCTransform module

nico_annotations.utils.SCTransform.SCTransform(adata, min_cells=5, gmean_eps=1, n_genes=2000, n_cells=None, bin_size=500, bw_adjust=3, inplace=True)

This is a port of SCTransform from the Satija lab. See the R package for original documentation.

Currently, only regression against the log UMI counts are supported.

The only significant modification is that negative Pearson residuals are zero’d out to preserve the sparsity structure of the data.

nico_annotations.utils.SCTransform.gmean(X, axis=0, eps=1)

nico_annotations.utils.SCTransform.is_outlier(y, x, th=10)

nico_annotations.utils.SCTransform.robust_scale_binned(y, x, breaks)

nico_annotations.utils.SCTransform.theta_ml(y, mu)

Module contents