get_model_var: Return average variance under negative binomial model

In ChristophH/sctransform: Variance Stabilizing Transformations for Single Cell UMI Data

Return average variance under negative binomial model

Description

This is based on the formula var = mu + mu^2 / theta

Usage

get_model_var(
  vst_out,
  cell_attr = vst_out$cell_attr,
  use_nonreg = FALSE,
  bin_size = 256,
  verbosity = 2,
  verbose = NULL,
  show_progress = NULL
)

Arguments

vst_out	The output of a vst run
cell_attr	Data frame of cell meta data
use_nonreg	Use the non-regularized parameter estimates; boolean; default is FALSE
bin_size	Number of genes to put in each bin (to show progress)
verbosity	An integer specifying whether to show only messages (1), messages and progress bars (2) or nothing (0) while the function is running; default is 2
verbose	Deprecated; use verbosity instead
show_progress	Deprecated; use verbosity instead

Value

A named vector of variances (the average across all cells), one entry per gene.

Examples

vst_out <- vst(pbmc, return_cell_attr = TRUE)
res_var <- get_model_var(vst_out)

ChristophH/sctransform documentation built on Oct. 22, 2023, 3:28 p.m.