HackBio-BioCoding-Intership/Stage 1 code at main · mkromah/HackBio-BioCoding-Intership · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
# HackBio Internship
#Task 1 Team BioCoders
# Github link https://github.com/mkromah/HackBio-BioCoding-Intership/blob/main/Task%201

#install packages
install.packages("BiocManager")
library(BiocManager)#loads the BiocManager package
BiocManager::install("Biostrings")#installs the Biostring package
library(Biostrings)#loads the Biostrings package
#Translate dna to protein
translate_dna_to_protein <- function(dna_sequence_string){
  dna_sequence <- DNAString(dna_sequence_string)
  protein <- translate(dna_sequence, if.fuzzy.codon = "solve")
  return(protein)
}
#calling the translate_dna_to_protein function
protein_sequence <- translate_dna_to_protein("ATGCCTGAGGAGTAA")
print(protein_sequence)

#task2
# logistic growth curve
logistic_growth_curve <- function(growth_rate, midpoint, time_taken=1:160, max_population= 200){
  #equation
  y <- max_population/(1 + exp((-growth_rate*(time_taken - midpoint))))
  return(y)
}
bacterial_growth_rate <- logistic_growth_curve(0.1, 100)
plot(x = 1:160, y = bacterial_growth_rate)
#Randomize the lenght of the   exponential phase(growth rate)
random_growth_rate <- sample(seq(from = 0, to = 10, by = 0.01), size = 200, replace = TRUE)
#Randomize the legnth of the lag phase (midpoints)
random_midpoints <- sample(seq(from = 20, to = 100, by = 0.2), size = 200, replace=TRUE)
#data frame with100 different growth curves
curves <- 1:100
growth_curve <- list()


for (index in curves){
  new <- logistic_growth_curve(random_growth_rate[index], random_midpoints[index])
growth_curve[[index]] <- new
}
#convert to data frame
growth_curve <- as.data.frame(growth_curve)
colnames(growth_curve) <- paste0("curve_", curves)
tail(growth_curve)


#task3
#function to determine carrying capacity
capacity <- function(growth_rate, midpoint, carrying_capacity =80, max_population = 200){
  time <- midpoint - (log(((max_population/carrying_capacity) -1))/growth_rate)
  return(time)
}
#To cornfirm carrying capacity
test <- capacity(0.5, 40)
print(test)
#To check if carrying capacity is at 80%
check <- logistic_growth_curve(0.5, 40, time = 39.18907)
print(check)

#task 4
#Hamming distance(distance between two words)
hamming_distance <- function(string_a, string_b){
  #check if the number of characters are same in both strings
string_a <- strsplit(string_a, split = "")[[1]]#Extract the string from the list
  string_b <- strsplit(string_b, split = "")[[1]]#Extract the string from the list

hamming_distance <- 0
#recapitulate through the length of the shorter string
for(i in 1:min(length(string_a), length(string_b))){
if(string_a[i] != string_b[i]){
   hamming_distance <- hamming_distance + 1
}

}
if(length(string_a) !=length(string_b)){
   paste("number of character in string a different from string b")
  }
return(hamming_distance)
}
#testing the function
tested <- hamming_distance("Julian", "Nina06")
  print(tested)