metaseqR (version 1.12.2)

diagplot.avg.ftd: Create average False (or True) Discovery curves

Description

This function creates false (or true) discovery curves using a list containing several outputs from diagplot.ftd.

Usage

diagplot.avg.ftd(ftdr.obj, output = "x11",
        path = NULL, draw = TRUE, ...)

Arguments

ftdr.obj

a list with outputs from diagplot.ftd.

output

one or more R plotting device to direct the plot result to. Supported mechanisms: "x11" (default), "png", "jpg", "bmp", "pdf" or "ps".

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 TRUE (make plots).

...

further arguments to be passed to plot devices, such as parameter from par.

Value

• A named list with two members: the first member (avg.ftdr) contains a list with the means and the standard deviations of the averaged ftdr.obj and are used to create the plot. The second member (path) contains the path to the created figure graphic.

Examples

p11 <- 0.001*matrix(runif(300),100,3)
p12 <- matrix(runif(300),100,3)
p21 <- 0.001*matrix(runif(300),100,3)
p22 <- matrix(runif(300),100,3)
p31 <- 0.001*matrix(runif(300),100,3)
p32 <- matrix(runif(300),100,3)
p1 <- rbind(p11,p21)
p2 <- rbind(p12,p22)
p3 <- rbind(p31,p32)
rownames(p1) <- rownames(p2) <- rownames(p3) <-
    paste("gene",1:200,sep="_")
colnames(p1) <- colnames(p2) <- colnames(p3) <-
    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(p1)
ftd.obj.1 <- diagplot.ftd(truth,p1,N=100,draw=FALSE)
ftd.obj.2 <- diagplot.ftd(truth,p2,N=100,draw=FALSE)
ftd.obj.3 <- diagplot.ftd(truth,p3,N=100,draw=FALSE)
ftd.obj <- list(ftd.obj.1,ftd.obj.2,ftd.obj.3)
avg.ftd.obj <- diagplot.avg.ftd(ftd.obj)