abd (version 0.1-22)

HumanGeneLengths: Human Gene Lengths

Description

Lengths in number of nucleotides (gene.length) for 20,290 human genes

Usage

data(HumanGeneLengths)

source

Hubbard, T., D. Andrews, M. Caccamo, G. Cameron, Y. Chen, M. Clamp, L. Clarke, G. Coates, T. Cox, F. Cunningham, V. Curwen, T. Cutts, T. Down, R. Durbin, X. M. Fernandez-Suarez, J. Gilbert, M. Hammond, J. Herrero, H. Hotz, K. Howe, V. Iyer, K. Jekosch, A. Kahari, A. Kasprzyk, D. Keefe, S. Keenan, F. Kokocinsci, D. London, I. Longden, G. McVicker, C. Melsopp, P. Meidl, S. Potter, G. Proctor, M. Rae, D. Rios, M. Schuster, S. Searle, J. Severin, G. Slater, D. Smedley, J. Smith, W. Spooner, A. Stabenau, J. Stalker, R. Storey, S. Trevanion, A. Ureta-Vidal, J. Vogel, S. White, C. Woodwark, and E. Birne. 2005. Ensembl 2005. Nucleic Acids Research 33: D447-D453.

References

http://www.ncbi.nlm.nih.gov/pmc/articles/PMC540092/

http://www.ensembl.org/

Examples

data(HumanGeneLengths)
str(HumanGeneLengths)
histogram(~gene.length, HumanGeneLengths, subset=gene.length<15000)

if (require(manipulate)){
  ## Resampled mean, sd, SE
  genes <- function(n){
    nreps = 1000
    sample.mean <- numeric(nreps) # vector for sample means
    sample.se <- numeric(nreps)   # vector for sample standard errors
    sample.sd <- numeric(nreps)   # vector for sample standard deviations
    for (i in 1:nreps){
      random.sample <- sample(HumanGeneLengths$gene.length, size = n)
      sample.mean[i] <- mean(random.sample)
      sample.sd[i] <- sd(random.sample)
      sample.se[i] <- se(random.sample)
    }
    hist.bins <- hist(sample.mean, breaks = 30, plot = FALSE)
    hist(sample.mean,
      breaks = 30, xlim = c(1000, 4000),
      xlab = "Sample mean length (nucleotides)",
      col = "red", main = "")
    abline(v = mean(sample.mean), col = "blue", lwd = 2)
    text(x = 3200, y = 0.6 * max(hist.bins$counts), 
      pos = 4, cex = 1.25,
      paste("n = ", n, 
        "mean = ", round(mean(sample.mean), digits = 1), 
        "sd = ", round(mean(sample.sd), digits = 1), 
        "se = ", round(mean(sample.se), digits = 1), sep = ""))
}
manipulate(genes(nreps), nreps = slider(1, 500))
}