These exercises are about the factors and data framessections of Introduction to R.

These exercises cover the factors and data frames sections of Introduction to R.

Exercise 1 - Factors

ordinalFactor <- factor(c("high", "low", "mid", "low", "mid", "low", "mid", "high", "mid", "high"),ordered=T,levels=c("low", "mid", "high"))
ordinalFactor
##  [1] high low  mid  low  mid  low  mid  high mid  high
## Levels: low < mid < high
filteredFactor <- ordinalFactor[ordinalFactor > "low"]
filteredFactor
## [1] high mid  mid  mid  high mid  high
## Levels: low < mid < high
newFactor <- factor(ordinalFactor,ordered=T,levels=c("low", "mid", "high","veryHigh"))
newFactor[length(newFactor)] <- "veryHigh"
newFactor[newFactor > "mid"]
## [1] high     high     veryHigh
## Levels: low < mid < high < veryHigh

Exercise 2 - Data frames

Annotation <- data.frame(geneNames=c("Gene_1", "Gene_2", "Gene_3","Gene_4","Gene_5"), ensembl=c("Ens001", "Ens003", "Ens006", "Ens007", "Ens010"),pathway=c("Glycolysis", "TGFb", "Glycolysis", "TGFb", "Glycolysis"),geneLengths=c(100, 3000, 200, 1000,1200))
Sample1 <- data.frame(ensembl=c("Ens001", "Ens003", "Ens006","Ens010"),expression=c(1000, 3000, 10000,5000))
Sample2 <- data.frame(ensembl=c("Ens001", "Ens003", "Ens006","Ens007","Ens010"),expression=c(1500, 1500, 17000,500,10000))
AnnoSample1 <- merge(Annotation,Sample1,by.x=2,by.y=1,all=F) 
AnnoSample1And2 <- merge(AnnoSample1,Sample2,by=1,all=F) 
AnnoSample1And2
##   ensembl geneNames    pathway geneLengths expression.x expression.y
## 1  Ens001    Gene_1 Glycolysis         100         1000         1500
## 2  Ens003    Gene_2       TGFb        3000         3000         1500
## 3  Ens006    Gene_3 Glycolysis         200        10000        17000
## 4  Ens010    Gene_5 Glycolysis        1200         5000        10000
AnnoSample1And2$Sample1_lne <- AnnoSample1And2$expression.x/AnnoSample1And2$geneLengths
AnnoSample1And2$Sample2_lne <- AnnoSample1And2$expression.y/AnnoSample1And2$geneLengths
AnnoSample1And2
##   ensembl geneNames    pathway geneLengths expression.x expression.y
## 1  Ens001    Gene_1 Glycolysis         100         1000         1500
## 2  Ens003    Gene_2       TGFb        3000         3000         1500
## 3  Ens006    Gene_3 Glycolysis         200        10000        17000
## 4  Ens010    Gene_5 Glycolysis        1200         5000        10000
##   Sample1_lne Sample2_lne
## 1   10.000000   15.000000
## 2    1.000000    0.500000
## 3   50.000000   85.000000
## 4    4.166667    8.333333
rownames(AnnoSample1And2) <- AnnoSample1And2$ensembl
mean(c(AnnoSample1And2["Ens006","Sample1_lne"],AnnoSample1And2["Ens006","Sample2_lne"]))
## [1] 67.5
log2FoldChange <- log2(AnnoSample1And2$Sample2_lne) - log2(AnnoSample1And2$Sample1_lne)
names(log2FoldChange) <- AnnoSample1And2$geneNames
log2FoldChange
##     Gene_1     Gene_2     Gene_3     Gene_5 
##  0.5849625 -1.0000000  0.7655347  1.0000000
sum(AnnoSample1And2[AnnoSample1And2$pathway == "Glycolysis","geneLengths"])
## [1] 1500