Session 1 - Data Types

 

These exercises are about the vector sections of Introduction to R.

Exercise 1

• Create a vector containing the values 1,2,3,4,5

x <- c(1,2,3,4,5)
x

## [1] 1 2 3 4 5

• Create a vector containing the values 1 to 100

x <- 1:100
x

##   [1]   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17  18
##  [19]  19  20  21  22  23  24  25  26  27  28  29  30  31  32  33  34  35  36
##  [37]  37  38  39  40  41  42  43  44  45  46  47  48  49  50  51  52  53  54
##  [55]  55  56  57  58  59  60  61  62  63  64  65  66  67  68  69  70  71  72
##  [73]  73  74  75  76  77  78  79  80  81  82  83  84  85  86  87  88  89  90
##  [91]  91  92  93  94  95  96  97  98  99 100

• Create a vector containing the values 0,5,10,15,20

x <- seq(0,20,5)
x

## [1]  0  5 10 15 20

• Create a new vector, with all but the first and last value of the previous vector.

y <- x[-c(1,length(x))]
y

## [1]  5 10 15

Exercise 2

• Create data frame called Annotation with a column of gene names (“Gene_1”, “Gene_2”, “Gene_3”,“Gene_4”,“Gene_5”), ensembl gene names (“Ens001”, “Ens003”, “Ens006”, “Ens007”, “Ens010”), pathway information (“Glycolysis”, “TGFb”, “Glycolysis”, “TGFb”, “Glycolysis”) and gene lengths (100, 3000, 200, 1000,1200).

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))

• Add a column with the expression data: (1000, 3000, 10000,5000, 50)

Annotation$expression <- c(1000, 3000, 10000,5000,50) 

• Subset the data frame to only the first 2 genes and remove the ensembl IDs.

Annotation_subset <- Annotation[1:2,-2]
Annotation_subset

##   geneNames    pathway geneLengths expression
## 1    Gene_1 Glycolysis         100       1000
## 2    Gene_2       TGFb        3000       3000

• Subset the data frame to the last 2 genes and remove the fourth and fifth column. Try do this so the code would work, whatever size the data frame is.

Annotation_subset2 <- Annotation[(nrow(Annotation)-1):nrow(Annotation),-c(4,5)]
Annotation_subset2

##   geneNames ensembl    pathway
## 4    Gene_4  Ens007       TGFb
## 5    Gene_5  Ens010 Glycolysis

• Calculate the length normalized expression and add it to a new column

Annotation$len_norm_exp <- Annotation$expression / Annotation$geneLengths
Annotation

##   geneNames ensembl    pathway geneLengths expression len_norm_exp
## 1    Gene_1  Ens001 Glycolysis         100       1000  10.00000000
## 2    Gene_2  Ens003       TGFb        3000       3000   1.00000000
## 3    Gene_3  Ens006 Glycolysis         200      10000  50.00000000
## 4    Gene_4  Ens007       TGFb        1000       5000   5.00000000
## 5    Gene_5  Ens010 Glycolysis        1200         50   0.04166667