adjusted_roc_curve: Obtain an adjusted ROC curve from rocdata

In RomeroLab/pudms: Positive-Unlabeled Learning for the Analysis of Deep Mutational Scanning Datasets

Description

Obtain an adjusted ROC curve from rocdata

Usage

adjusted_roc_curve(
  rocdata = NULL,
  coef = NULL,
  test_grouped_dat = NULL,
  Xprotein_test = NULL,
  order = 1,
  refstate = NULL,
  verbose = T,
  py1,
  plot = TRUE
)

Arguments

rocdata	NULL or an output from the rocdata function
coef	a named vector for the fitted coefficient vector
test_grouped_dat	a data table (sequence, labeled, unlabeled, seqId) containing validation examples
order	a considered order of effects
refstate	a character which will be used for the common reference state; the default is to use the most frequent amino acid as the reference state for each of the position.
verbose	a logical value
py1	the prevalence of positives in the unlabeled set (which will be used for a correction)
plot	a logical value. If TRUE, a plot will be returned

Value

a list containing a data frame for generating a roc plot and the plot

RomeroLab/pudms documentation built on Jan. 2, 2021, 5:10 a.m.