Lecture 2

String

Pattern matching

DNA_s= "ATTTGCATGCAAAGGGCATGCAG"
Pattern= "ATT"

Matches = grepl(Pattern, DNA_s)
print(Matches)

[1] TRUE

Matches = grepl("ATTTTCGG", DNA_s)
print(Matches)

[1] FALSE

Split

genes ="gene1,gene2,gene3"
split_genes=strsplit(genes, ",")
print(split_genes)

[[1]]
[1] "gene1" "gene2" "gene3"

paragraph = "This paragraph will be split for spaces"
split_paragraph=strsplit(paragraph, " ")
print(split_paragraph)

[[1]]
[1] "This"      "paragraph" "will"      "be"        "split"     "for"       "spaces"   

sentence= "this is sentence 1. second sentence. third sentence."
split_sentence=strsplit(sentence, "\\. ")
print(split_sentence)

[[1]]
[1] "this is sentence 1" "second sentence"    "third sentence."   

Reverse

library(stringi)
s1= "ABCDEFG"
rev_s1= stri_reverse(s1)
print(rev_s1)

[1] "GFEDCBA"

Number of occurences

DNA_s= "ATTTGCATGATTCAAAGGGCATGCAG"
Pattern= "ATT"

locations = gregexpr(Pattern, DNA_s)
locations =unlist(locations)
print(locations)

[1]  1 10

num_occ= sum(locations !=-1)
print(num_occ)

[1] 2

Vector

Create vector

ages= c(20, 25,18,65,18,45)
print(ages)

[1] 20 25 18 65 18 45

Indexing

ages[1]

[1] 20

ages[-1]

[1] 25 18 65 18 45

ages[70]

[1] NA

Append

ages= c(ages, 100, 25)
ages

[1]  20  25  18  65  18  45 100  25

Subset or slice

ages

[1]  20  25  18  65  18  45 100  25

print(ages[3:6])

[1] 18 65 18 45

print(ages[1:4])

[1] 20 25 18 65

print(ages[6:20])

 [1]  45 100  25  NA  NA  NA  NA  NA  NA  NA  NA  NA  NA  NA  NA

Length

print(length(ages))

[1] 8

Insert in a specific position

print(ages)

[1]  20  25  18  65  18  45 100  25

print(ages[1:2])

[1] 20 25

ages_extended=c

Vector Conditional

age= c(18,20,18,40,50,60)
print(age)

[1] 18 20 18 40 50 60

age_50=age[age<=50]
age_50

[1] 18 20 18 40 50

age_25_50=age[age>=25 & age<=50]
age_25_50

[1] 40 50

age_25_50[1]

[1] 40

ages[ages >=25 & ages<=50]

[1] 25 45 25

ages

[1]  20  25  18  65  18  45 100  25

Sorting

sorted_ages=sort(ages)


sort(sorted_ages, TRUE)

[1] 100  65  45  25  25  20  18  18

Simple Statistics

ages

[1]  20  25  18  65  18  45 100  25

max(ages)

[1] 100

max(ages[2:5])

[1] 65

min(ages)

[1] 18

mean(ages)

[1] 39.5

median(ages)

[1] 25

sum(ages)

[1] 316

sd(ages)

[1] 29.43759

var(ages)

[1] 866.5714

quantile(ages)

   0%   25%   50%   75%  100% 
 18.0  19.5  25.0  50.0 100.0 

mode(ages)

[1] "numeric"

length(ages)

[1] 8

scores= c(10, 20, 30,40,50,60,70,80)

length(scores)

[1] 8

cor(ages, scores)

[1] 0.4398222

Data frame

exam_score = data.frame(
  ID= c(1, 2, 3, 4, 5),
  Names= c("Amzad", "Kalam", "Subhan", "Chang", "Bran"),
  Age= c(20,22,23,24,25),
  Score= c(100, 92, 80,60,55)
)

print(exam_score)

exam_score[1:3, 3:4]

exam_score[2, 3:4]

exam_score[2, ]

exam_score[ , 4]

[1] 100  92  80  60  55

exam_score[3:4, 1]

[1] 3 4

exam_score[ , 2]

[1] "Amzad"  "Kalam"  "Subhan" "Chang"  "Bran"  

make table with only name and age

exam_score$Names

[1] "Amzad"  "Kalam"  "Subhan" "Chang"  "Bran"  

exam_score$Age

[1] 20 22 23 24 25

selected_columns= data.frame(
  Names= exam_score$Names,
  Age=exam_score$Age
)

print(selected_columns)

Alternative way

exam_score[c(1,2,3,4,5), c(2,3)]

exam_score[exam_score$Score>=80 & exam_score$Score<95, ]

when you have to select specific ID containing rows, use %in% . this operation will select only 1,5 in ID.

selected_ID= c(1,5)
exam_score[exam_score$ID %in% selected_ID, ]

selected_Age= c(20,22)
exam_score[exam_score$Age %in% selected_Age, ]

Adding new rows and columnsq

exam_score

new_row= c(10, "Sam", 55, 100)

exam_score2= rbind(exam_score, new_row)

exam_score2

Location = c("dhk", "ctg", "bars", "jfk", "mms", "cml")
exam_score3= cbind(exam_score2, Location)
exam_score3