prcPlot will plot a Precision-Recall curve (and return the AUPRC) that describes how well a gene signature (as defined in a filterObject) classifies groups in a dataset (in the form of a datasetObject).
prcPlot(filterObject, datasetObject, title = datasetObject$formattedName,
subtitle = NULL, textSize = NULL, rounding = 3,
curveColors = "red", legend = TRUE, PRC.lty = 1, PRC.lwd = 1,
backgroundColor = "gray93", grid.marks = 0.1, grid.color = "white",
grid.lty = 1, grid.lwd = 0.9, legend.lty = 0, cex.main = 1,
cex.subtitle = 0.9)a metaFilter object containing the signature genes that will be used for calculating the score
a Dataset object for group comparison in the PRC plot. (At least, must have a $expr of probe-level data, $keys of probe:gene mappings, and $class of two-class labels.)
title of the plot (default: datasetObject$formattedName)
subtitle of the figure
use this to easily increase or decrease the size of all the text in the plot
how many digits to round the AUPRC and CI to (default: 3)
Graphical: the color for the PRC curves (default: "red")
Graphical: if TRUE, a legend will be included
Graphical: PRC curve line type
Graphical: PRC curve line width
Graphical: background color of the plot
Graphical: increment between grid lines
Graphical: grid line color
Graphical: grid line type
Graphical: grid line width
Graphical: legend style (0 is no box, 1 is boxed legend)
Graphical: title size
Graphical: subtitle size
Returns a standard PRC plot, plus AUPRC with 95% CI (calculated with the trapezoid method).
Evaluates the ability of a given gene set to separate two classes. As opposed to ROC curves, PRC curves are more sensitive to class imbalances. The gene set is evaluated as a Z-score of the difference in means between the positive genes and the negative genes (see calculateScore).
# NOT RUN {
prcPlot(tinyMetaObject$filterResults[[1]], tinyMetaObject$originalData[[1]])
# }
Run the code above in your browser using DataLab