Question

I have a dataframe in R like this:

dat = data.frame(Sample = c(1,1,2,2,3), Start = c(100,300,150,200,160), Stop = c(180,320,190,220,170))

And I would like to plot it such that the x-axis is the position and the y-axis is the number of samples at that position, with each sample in a different colour. So in the above example you would have some positions with height 1, some with height 2 and one area with height 3. The aim being to find regions where there are a large number of samples and what samples are in that region.

i.e. something like:

      &
     ---
********-  --       **

where * = Sample 1, – = Sample 2 and & = Sample 3

Answer 1

This hack may be what you’re looking for, however I’ve greatly increased the size of the dataframe in order to take advantage of stacking by geom_histogram.

library(ggplot2)
dat = data.frame(Sample = c(1,1,2,2,3), 
                 Start = c(100,300,150,200,160), 
                 Stop = c(180,320,190,220,170))

# Reformat the data for plotting with geom_histogram.
dat2 = matrix(ncol=2, nrow=0, dimnames=list(NULL, c("Sample", "Position")))

for (i in seq(nrow(dat))) {
    Position = seq(dat[i, "Start"], dat[i, "Stop"])
    Sample = rep(dat[i, "Sample"], length(Position))
    dat2 = rbind(dat2, cbind(Sample, Position))
}

dat2 = as.data.frame(dat2)
dat2$Sample = factor(dat2$Sample)

plot_1 = ggplot(dat2, aes(x=Position, fill=Sample)) +
         theme_bw() +
         opts(panel.grid.minor=theme_blank(), panel.grid.major=theme_blank()) +
         geom_hline(yintercept=seq(0, 20), colour="grey80", size=0.15) +
         geom_hline(yintercept=3, linetype=2) +
         geom_histogram(binwidth=1) +
         ylim(c(0, 20)) +
         ylab("Count") +
         opts(axis.title.x=theme_text(size=11, vjust=0.5)) +
         opts(axis.title.y=theme_text(size=11, angle=90)) +
         opts(title="Segment Plot")

png("plot_1.png", height=200, width=650)
print(plot_1)
dev.off()

Note that the way I’ve reformatted the dataframe is a bit ugly, and will not scale well (e.g. if you have millions of segments and/or large start and stop positions).