#!/usr/bin/Rscript
DNA <- c("A", "C", "G", "T")
random.sequence <- paste(sample(rep(DNA, 100000)), collapse="")
distances <- nchar(strsplit(random.sequence, "GT")[[1]][-1])
cat("Number of bases between two consecutive GT sites in a random DNA sequence:\n")
cat(" - expectation: ", mean(distances), "\n")
cat(" - standard deviation: ", sd(distances), "\n")
hist(distances)