gene length factor

genelength.R

library(TxDb.Hsapiens.UCSC.hg19.knownGene)
txdb <- TxDb.Hsapiens.UCSC.hg19.knownGene
g <- keys(txdb, "GENEID")
df <- select(txdb, keys=g, keytype="GENEID", columns="TXID")
ebt <- exonsBy(txdb, by="tx")
set.seed(1)
random.genes <- sample(g, 500, replace=FALSE)
res <- sapply(random.genes, function(gene) {
         txs <- df$TXID[df$GENEID == gene]
         if (length(txs) == 1) return(NA)
         lengths <- sum(width(ebt[txs]))
         idx <- sample(length(txs), 2)
         lengths[idx[1]] / lengths[idx[2]]
       })
round(2^quantile(abs(log2(res)),1:3/4,na.rm=TRUE),2)