findUncertainLabels: Find uncertain labels

In PFPrzytycki/CellWalkR: An R Package for Integrating and Visualizing Single-Cell and Bulk Data to Resolve Regulatory Elements

Find uncertain labels

Description

findUncertainLabels() generates an l-by-l matrix for how often each label is confused for each other label at a given threshold, optinally normalized for total counts of cells for each label (default FALSE)

Usage

findUncertainLabels(
  cellWalk,
  cellTypes,
  threshold = 0.1,
  labelThreshold,
  plot = FALSE,
  normalize = FALSE
)

Arguments

cellWalk	a cellWalk object
cellTypes	character, vector of labels to use, all labels used by default
threshold	numeric, quantile threshold for uncertain label
labelThreshold	numeric, set a threshold below which cells aren't labeled (e.g. 0)
plot	boolean, plot output matrix
normalize	boolean, normalize plot scale

Value

cellWalk object with label uncertainty matrix (l-by-l) stored in "uncertaintyMatrix"

Examples

data("SampleCellWalkRData")
cellWalk <- findUncertainLabels(SampleCellWalkRData$cellWalk, threshold = .5)

PFPrzytycki/CellWalkR documentation built on Oct. 26, 2023, 1:50 p.m.