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

c(1,2,3,4,5)

## [1] 1 2 3 4 5

• Create a vector containing the values 1 to 100. Save it as the variable x.

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

• Multiply x by 2

x*2

##   [1]   2   4   6   8  10  12  14  16  18  20  22  24  26  28  30  32  34  36
##  [19]  38  40  42  44  46  48  50  52  54  56  58  60  62  64  66  68  70  72
##  [37]  74  76  78  80  82  84  86  88  90  92  94  96  98 100 102 104 106 108
##  [55] 110 112 114 116 118 120 122 124 126 128 130 132 134 136 138 140 142 144
##  [73] 146 148 150 152 154 156 158 160 162 164 166 168 170 172 174 176 178 180
##  [91] 182 184 186 188 190 192 194 196 198 200

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

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

## [1]  0  5 10 15 20

• Check the help page for the rep function

?rep

## Help on topic 'rep' was found in the following packages:
## 
##   Package               Library
##   base                  /usr/local/lib/R/library
##   S4Vectors             /usr/local/lib/R/host-site-library
## 
## 
## Using the first match ...

• Create a vector containing the values 1,1,2,2,3,3 using rep

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. Overwrite the variable x with this.

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

• Check the help page for the paste() function.

?paste

## Help on topic 'paste' was found in the following packages:
## 
##   Package               Library
##   base                  /usr/local/lib/R/library
##   BiocGenerics          /usr/local/lib/R/host-site-library
## 
## 
## Using the first match ...

• Combine the two characters: “A” and “B”

paste("A","B")

## [1] "A B"

• Change the separator to an underscore

paste("A","B", sep="_")

## [1] "A_B"

Exercise 4

• Create a vector with these gene names: “PKM”, “ADPRH”, “TDG”, “ATP4A”, “SLC6A4”, “CAPN3”, “TDG”, “ATP1A2”,“PKM”
• Subset to just the unique genes

my_genes <- c("PKM", "ADPRH", "TDG", "ATP4A", "SLC6A4", "CAPN3", "TDG", "ATP1A2","PKM")
my_genes <- unique(my_genes)
my_genes 

## [1] "PKM"    "ADPRH"  "TDG"    "ATP4A"  "SLC6A4" "CAPN3"  "ATP1A2"

• Create a second vector with these gene names: “SLC6A4”, “CAPN3”, “TDG”, “ATP1A2”, “IMPA1”, “PDXK”.
• Check which genes from vector 1 are present in vector 2.
• Subset vector 1 depending on whether the gene is present in vector 2.

my_genes_of_interest <- c("SLC6A4", "CAPN3", "TDG", "ATP1A2", "IMPA1", "PDXK")
idx <- my_genes %in% my_genes_of_interest
idx

## [1] FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE

my_genes[idx]

## [1] "TDG"    "SLC6A4" "CAPN3"  "ATP1A2"

my_genes_of_interest <- c("SLC6A4", "CAPN3", "TDG", "ATP1A2", "IMPA1", "PDXK")
idx <- my_genes %in% my_genes_of_interest
idx

## [1] FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE

my_genes[idx]

## [1] "TDG"    "SLC6A4" "CAPN3"  "ATP1A2"

• Create a vector with these gene names: “SMC1”, “SMC3”, “SCC1”, “SCC3”, “RAD21”, “NIPBL”, “SMC2”, “SMC4”,“CAPH”,“CAPD3”
• Subset to just the genes containing SMC

my_genes <- c("SMC1", "SMC3", "SCC1", "SCC3", "RAD21", "NIPBL", "SMC2", "SMC4","CAPH","CAPD3")
my_genes[grepl("SMC",my_genes)]

## [1] "SMC1" "SMC3" "SMC2" "SMC4"

Exercise 5

• 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"