# Problem 1
# On the Golub et al. (1999) data set, we consider the correlation between the Zyxin gene
# expression values and each of the gene in the data set

library("multtest")
data(golub)
dim(golub)
# [1] 3051 38
golub <- data.frame(golub)
gol.fac <- factor( golub.cl, levels=0:1, labels=c("ALL","AML"))
# (a)How many of the genes have correlation values less than negative 0.5? (Those genes are
# highly negatively correlated with Zyxin gene).
golub.gnames[2124,]
# [1] "4847"    "Zyxin" "X95735_at"
correlations <- apply(golub,1,cor, as.numeric( golub[2124,] ))
correlations.less.than.05 <- correlations < 0.5
sum(correlations.less.than.05)
# [1] 2941
# 2941 gnes

# (b)Find the gene names for the top five genes that are most negatively correlated with
# Zyxin gene.
o <- order(correlations)
golub.gnames[o,][1:5,2]
# [1] "Macmarcks"
# [2] "Inducible protein mRNA"
# [3] "C-myb gene extracted from Human (c-myb) gene, complete primary cds, and five complete alternatively spliced cds"
# [4] "Oncoprotein 18 (Op18) gene"
# [5] "54 kDa protein mRNA"

Problems 1. A system with three independent components works corr...