GetStabilityOverlap {GeneSelector} | R Documentation |
The similarity of two ordered genelists is assessed by counting the size of the intersection ('overlap') for each position in the list and by computing a weighted cumulative sum of the number of overlaps up to a position in the list ('overlap score'), as suggested by Yang et al. (2006) and Lottaz et al. (2006).
GetStabilityOverlap(RR, scheme = c("original", "pairwise"), decay = c("linear", "quadratic", "exponential"), alpha = 1, ...)
RR |
An object of class |
scheme |
If |
decay |
Argument controlling the weight decay of the weights
necessary for the computation of the overlap score. If |
alpha |
s. |
... |
Currently unused argument. |
An object of class StabilityOverlap
Contrary to Yang et al. (2006), Lottaz et al. (2006), we consider differential expression without distinguishing between over- and underexpression.
Both intersection count and overlap score are suitably normalized to fall into the unit interval for the sake of better interpretability, with zero corresponding to maximal instability.
Martin Slawski
Anne-Laure Boulesteix
Qiu, X., Xiao, Y., Gordon, A., Yakovlev, A. (2006)
Assessing stability of gene selection in microarray data
analysis. BMC Bioinformatics 7, 50
Yang, X., Bentink, S., Scheid, S., Spang, R. (2006)
Similarities of ordered gene lists. Journal of Bioinformatics
and Computational Biology 4, 693-708
Lottaz, C., Yang, X., Scheid, S., Spang, R. (2006)
OrderedList - a Bioconductor package for detecting
similarity in ordered gene lists.
Bioinformatics, 22, 2315-2316
## Load toy gene expression data data(toydata) ### class labels yy <- toydata[1,] ### gene expression xx <- toydata[-1,] ### get ranking ordT <- RankingTstat(xx, yy, type="unpaired") ### Generate Leave-One-Out loo <- GenerateFoldMatrix(y = yy, k=1) ### Repeat Ranking with t-statistic loor_ordT <- RepeatRanking(ordT, loo) ### assess stability stab_ov_ordT <- GetStabilityOverlap(loor_ordT, scheme = "original", decay="linear") ### for a short summary summary(stab_ov_ordT, measure = "intersection", display = "all", position = 10) ### for a graphical display plot(stab_ov_ordT)