问解释R码函数

EN

hyperg <- Category:::.doHyperGInternal

pVals.by.pathway<-t(sapply(genes.by.pathway, hyperg.test, significant.genes, all.geneIDs))

library(KEGGREST)
library(org.Hs.eg.db)

     # created named list, length 449, eg:
     # path:hsa00010: "Glycolysis / Gluconeogenesis"

pathways <- keggList("pathway", "hsa")

     # make them into KEGG-style human pathway identifiers
human.pathways <- sub("path:", "", names(pathways))

   # for demonstration, just use the first ten pathways

demo.pathway.ids <- head(human.pathways, 10)
demo.pathways <- setNames(keggGet(demo.pathway.ids), demo.pathway.ids)

genes.by.pathway <- lapply(demo.pathways, function(demo.pathway) {
     demo.pathway$GENE[c(TRUE, FALSE)]
      })

all.geneIDs <- keys(org.Hs.eg.db)

   # chose one of these for demonstration.  the first (a whole genome random
   # set of 100 genes)  has very little enrichment, the second, a random set
   # from the pathways themselves,  has very good enrichment in some pathways

set.seed(123)
significant.genes <- sample(all.geneIDs, size=100)
#significant.genes <- sample(unique(unlist(genes.by.pathway)), size=10)

   # the hypergeometric distribution is traditionally explained in terms of
   # drawing a sample of balls from an urn containing black and white balls.
   # to keep the arguments straight (in my mind at least), I use these terms
   # here also

hyperg <- Category:::.doHyperGInternal
hyperg.test <-
    function(pathway.genes, significant.genes, all.genes, over=TRUE)
{
    white.balls.drawn <- length(intersect(significant.genes, pathway.genes))
    white.balls.in.urn <- length(pathway.genes)
    total.balls.in.urn <- length(all.genes)
    black.balls.in.urn <- total.balls.in.urn - white.balls.in.urn
    balls.pulled.from.urn <- length(significant.genes)
    hyperg(white.balls.in.urn, black.balls.in.urn,
           balls.pulled.from.urn, white.balls.drawn, over)
}

pVals.by.pathway <-
    t(sapply(genes.by.pathway, hyperg.test, significant.genes, all.geneIDs))

print(pVals.by.pathway)