get_residuals: Return Pearson or deviance residuals of regularized models

In sctransform: Variance Stabilizing Transformations for Single Cell UMI Data

Return Pearson or deviance residuals of regularized models

Description

Return Pearson or deviance residuals of regularized models

Usage

get_residuals(
  vst_out,
  umi,
  residual_type = "pearson",
  res_clip_range = c(-sqrt(ncol(umi)), sqrt(ncol(umi))),
  min_variance = vst_out$arguments$min_variance,
  cell_attr = vst_out$cell_attr,
  bin_size = 256,
  verbosity = vst_out$arguments$verbosity
)

Arguments

vst_out	The output of a vst run
umi	The UMI count matrix that will be used
residual_type	What type of residuals to return; can be 'pearson' or 'deviance'; default is 'pearson'
res_clip_range	Numeric of length two specifying the min and max values the results will be clipped to; default is c(-sqrt(ncol(umi)), sqrt(ncol(umi)))
min_variance	Lower bound for the estimated variance for any gene in any cell when calculating pearson residual; default is vst_out$arguments$min_variance
cell_attr	Data frame of cell meta data
bin_size	Number of genes to put in each bin (to show progress)
verbosity	An integer specifying the verbosity level: 0 (silent, no messages), 1 (show messages only), or 2 (show messages and progress bars); default is 2

Value

A matrix of residuals

Examples

vst_out <- vst(pbmc, return_cell_attr = TRUE)
pearson_res <- get_residuals(vst_out, pbmc)
deviance_res <- get_residuals(vst_out, pbmc, residual_type = 'deviance')

sctransform documentation built on Jan. 10, 2026, 9:17 a.m.