intro to python quiz.txt

# Question 1
# Price of one bottle of milk
milk_price = 1.50

# Prompt the user to enter an amount of money
money_needed = float(input("Enter the amount of money you have: "))

# Calculate the number of bottles they can afford
bottles = int(money_needed // milk_price)

# Calculate the extra money needed for another bottle
extra_money_needed = milk_price - (money_needed % milk_price)

# Output the results
print(f"You can afford {bottles} bottles of milk.")
if extra_money_needed <= 0:
    print("You have enough money for another bottle!")
else:
    print(f"You need £{extra_money_needed:.2f} more for another bottle.")


# Question 2

for j in range (100, -1, -2):
    print (j)

# Question 3

# To Calculate the GC percentage
sequence="ACTGCGCGTCAGTCTACGTAG"

# Create a variable to store the GC counts

GC_count = (sequence.count("G") + sequence.count("C"))

# Convert it to percentage
GC_percent = GC_count / len (sequence) * 100

# Print results in 2 dp
print(f"GC Percent: {GC_percent:.2f}%")
# Or
print(int(GC_percent))

# Questions 4

# To calculate the GC content of each sequence in the fasta file
with open("Downloads/workshop_data.fasta", "r") as fasta_file:
    # For Loop to iterate the headers
    for lines in fasta_file:
        # if statement to print only lines starting with ">"
        if lines.startswith(">"):
            print ("sequence name is", lines)
        # Else statement to calculate GC content of each sequence   
        else:
            GC_count = (lines.count("G") + lines.count("C"))
            print((GC_count/len(lines))*100)
       
# Question 5

# generate a list of sequence names which only contain the gene name (i.e. "AT1G04130")
with open("Downloads/workshop_data.fasta", "r") as fasta_file:
    # For loop
    for lines in fasta_file:
        # If statement to read only the headers
        if lines.startswith('>'):
            # to split the underscore 
            header = lines.split('_')
            # to split and strip the > and . symbols
            print(header[0].split('.')[0].lstrip('>'))

# Questions 6

# Define the function to make the query
def count_headers_with_phrase(fasta_file, phrase):
    # Create a variable counter
    count = 0
    # open the fasta file
    with open(fasta_file, 'r') as file:
        # Write a for loop
        for line in file:
            # To remove unwanted whitespace characters in the 'line' variable 
            line = line.strip()
            # If statement to check if the header contains the "pop3"
            if line.startswith(">") and phrase in line: 
                count += 1
    return count

# Function parameters
fasta_file = "Downloads/workshop_data.fasta"  
phrase = "pop3"

# Create result variable
result = count_headers_with_phrase(fasta_file, phrase)

# Print results
print(f"Number of headers containing '{phrase}': {result}")