The rank product is a biologically motivated test for the detection of differentially expressed genes in replicated microarray experiments. It is a simple nonparametric statistical method based on ranks of fold changes. In addition to its use in expression profiling, it can be used to combine ranked lists in various application domains, including proteomics, metabolomics, statistical metaanalysis, and general feature selection.
Given n genes and k replicates, let e_{g,i} be the fold change and r_{g,i} the rank of gene g in the ith replicate.
Compute the rank product via the geometric mean:
Simple permutationbased estimation is used to determine how
likely a given RP value or better is observed in a random
experiment.
1. step: generate p permutations of k rank lists of
length n
2. step: calculate the rank products of the n genes in the
p permutations
3. step: count how many times the rank products of the genes in the
permutations are smaller or equal to the observed rank product. Set
c to this value.
4. step: calculate the average expected value for the rank product
by E_{RP}(g)
= c / p
5. step: calculate the percentage of false positives as pfp(g) =
E_{RP}(g) /
rank(g)
where rank(g)
is the rank of gene g in a list of all n genes
sorted by increasing RP
