This function creates basic ROC curves using a
matrix of pvalues (such a matrix can be
derived for example from the result table of
metaseqr
by subsetting the table
to get the pvalues from several algorithms)
given a ground truth vector for differential
expression and a significance level.
1 2 3  diagplot.roc(truth, p, sig = 0.05, x = "fpr",
y = "tpr", output = "x11", path = NULL,
draw = TRUE, ...)

truth 
the ground truth differential
expression vector. It should contain only
zero and nonzero elements, with zero denoting
nondifferentially expressed genes and nonzero,
differentially expressed genes. Such a vector
can be obtained for example by using the

p 
a pvalue matrix whose rows correspond
to each element in the 
sig 
a significance level (0 < 
x 
what to plot on xaxis, can be one of

y 
what to plot on yaxis, same as

output 
one or more R plotting device to
direct the plot result to. Supported mechanisms:

path 
the path to create output files. 
draw 
boolean to determine whether to
plot the curves or just return the calculated
values (in cases where the user wants the
output for later averaging for example).
Defaults to 
... 
further arguments to be passed to plot
devices, such as parameter from 
A named list with two members. The first member is
a list containing the ROC statistics: TP
(True Postives), FP
(False Positives),
FN
(False Negatives), TN
(True Negatives), FPR
(False Positive Rate),
FNR
(False Negative Rate), TPR
(True
Positive Rate), TNR
(True Negative Rate),
AUC
(Area Under the Curve). The second is
the path to the created figure graphic.
Panagiotis Moulos
1 2 3 4 5 6 7 8 9  p1 < 0.001*matrix(runif(300),100,3)
p2 < matrix(runif(300),100,3)
p < rbind(p1,p2)
rownames(p) < paste("gene",1:200,sep="_")
colnames(p) < paste("method",1:3,sep="_")
truth < c(rep(1,40),rep(1,40),rep(0,20),rep(1,10),
rep(2,10),rep(0,80))
names(truth) < rownames(p)
roc.obj < diagplot.roc(truth,p)

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.
Please suggest features or report bugs with the GitHub issue tracker.
All documentation is copyright its authors; we didn't write any of that.