cellHTS2 (version 2.36.0)

ROC: Creates an object of class "ROC" which can be plotted as a ROC curve

Description

The function ROC construct an object of S4 class ROC, which represents a receiver-operator-characteristic curve, from the data of the annotated positive and negative controls in a scored cellHTS object.

Usage

"ROC"(object, positives, negatives)
"plot"(x, col="darkblue", type="l", main = "ROC curve", ...)
"lines"(x, ...)

Arguments

object

a cellHTS object which replicate data have already been scored and summarized (see details).

positives

a list or vector of regular expressions specifying the name of the positive control(s). See the details for the argument posControls of writeReport function. The default is "^pos$".

negatives

a vector of regular expressions specifying the name of the negative control(s). See the details for the argument negControls of writeReport function. The default is "^neg$".

x

a ROC object obtained using function ROC.

col

the graphical parameter for color; see par for details.

type

the graphical parameter giving the type of plot desired; see par for details.

main

the graphical parameter giving the desired title of plot; see par for details.

...

other graphical parameters as in par may be also passed as arguments.

Value

ROC. There are methods show, plot and lines.

Details

The cellHTS object object must be already scored (state(object)["scored"]=TRUE), and selection proceeds from large to small values of this single per-probe score. Furthermore, object is expected to contain positive and negative controls annotated in the column controlStatus of the featureData slot - which can be accessed via wellAnno(object). The arguments positives and negatives should be given as regular expression patterns specifying the name of the positive(s) and negative(s) controls, respectivey. By default, if positives is not given, pos will be taken as the name for the wells containing positive controls. Similarly, if negatives is missing, by default neg will be considered as the name used to annotate the negative controls. The content of posControls and negControls are passed to regexpr for pattern matching within the well annotation (see examples for summarizeChannels). If the assay is a two-way experiment, positives should be a list with components act and inh, specifying the name of the activators, and inhibitors, respectively. In this case, the ROC curve is constructed based on the absolute values of Data(object).

Examples

    data(KcViabSmall)
    x <- normalizePlates(KcViabSmall, scale="multiplicative", log=FALSE, method="median", varianceAdjust="byExperiment")
    x <- scoreReplicates(x, sign="-", method="zscore")
    x <- summarizeReplicates(x, summary="mean")
    y <- ROC(x)
    plot(y)
    lines(y, col="green")
    show(y)