Vectors

 

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 vector containing the values 1,1,2,2,3,3

x <- c(rep(1,2),rep(2,2),rep(3,2))
x

## [1] 1 1 2 2 3 3

• Create a vector containing the values 1,1,5,7,9,10

x <- c(rep(1,2),seq(5,9,2),10)
x

## [1]  1  1  5  7  9 10

Exercise 2

• Create a vector containing the values 1 to 10.

x <- 1:10
x

##  [1]  1  2  3  4  5  6  7  8  9 10

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

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

## [1] 2 3 4 5 6 7 8 9

• Create a new vector with all but the second and fifth value.

y <- x[-c(2,5)]
y

## [1]  1  3  4  6  7  8  9 10

• Create a new vector of square root of the sixth and seventh position.

y <- sqrt(x[6:7])
y

## [1] 2.449490 2.645751

• Create a new vector of alternating positions in the vector using another vector.

y <- x[seq(1,10,2)]
y

## [1] 1 3 5 7 9

Exercise 3

• Find the number of files in the present working directory.

# Depend on current working directory..
length(dir())

## [1] 10

• List the first file in the present working directory.

x <- dir()
x[1]

## [1] "_course.yml"

Exercise 4

• Create a vector of the gene names Gene_1, Gene_2, Gene_3 Gene_4
• Create a vector of the expression values 1000, 3000, 10000, 12000
• Create a vector of the gene lengths 100, 3000, 200, 1000

geneNames <- c("Gene_1", "Gene_2", "Gene_3","Gene_4")
expression <- c(1000, 3000, 10000, 12000)
geneLengths <- c(100, 3000, 200, 1000)
names(expression) <- geneNames
names(geneLengths) <- geneNames
expression

## Gene_1 Gene_2 Gene_3 Gene_4 
##   1000   3000  10000  12000

geneLengths

## Gene_1 Gene_2 Gene_3 Gene_4 
##    100   3000    200   1000

• Find the longest gene.

names(geneLengths[geneLengths == max(geneLengths)])

## [1] "Gene_2"

names(geneLengths[which.max(geneLengths)])

## [1] "Gene_2"

• Identify genes which have a length greater than 100 and expression greater than 10000

geneNames[geneLengths > 100 & expression > 10000]

## [1] "Gene_4"

Bonus Questions

• Calculate the expression over the gene length for all genes (Length normalised expression).

lne <- expression/geneLengths
lne

## Gene_1 Gene_2 Gene_3 Gene_4 
##     10      1     50     12

• Identify genes with a length normalised expression greater than the average

geneNames[lne > mean(lne)]

## [1] "Gene_3"