python functionality workshop.txt

# Question 1

## Write a programme (or script) that will produce a list of sequence headers from a multi-fasta file.
# Creates a function to extract headers
def extract_headers(fasta_file):
    # creates a variable called Header
    headers = []
    # Use with function to access file
    with open(fasta_file, 'r') as file:
        for line in file:
            # If statement to select the lines starting with ">"
            if line.startswith('>'):
                headers.append(line.strip().lstrip('>'))  # Remove whitespaces and > sign
    return headers

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

# Apply function to the header variable
headers = extract_headers(fasta_file)

# Print the list
print(headers)

# Question 2

## Using the header list you created in question 1, number the sequence headers alphabetically.
# Create a counter variable
count = 0
# For loop to check each line in the list
for items in sorted(headers):
    # Statement to ensure that the counter iterates over itself, with the lowest value been 0
    count = count + 1
    # Print results
    print(count, items)

# Question 3

# Create an empty dictionary to store the sequences
seq_dict = {}

# Access the fasta file
with open("Downloads/workshop_data.fasta", "r") as fastafile:
    # Create a variable to hold the current header
    header = None
    # Create a list to hold the sequence lines
    sequence = []  

    # For statement to examine each line in the file
    for line in fastafile:
        # Remove any whitespace
        line = line.strip() 
        # If statement to check if the line is a header
        if line.startswith(">"):  
            # If the line is an header, save the sequence to the header variable
            if header is not None:  
                # Join the sequence list into a string
                seq_dict[header] = ''.join(sequence)  
            # remove the '>' character
            header = line[1:] 
            # Reset the sequence list for the new header
            sequence = []  
        # Else statement
        else:
            # Add the line to the sequence list
            sequence.append(line)  

    # Add the last sequence after the loop
    if header is not None:
        seq_dict[header] = ''.join(sequence)

# Now seq_dict contains the headers and their corresponding sequences
# Print the dictionary to verify its contents
print(seq_dict) 

# Question 4

## Re-write your code from question 3, so that it takes the form of a function.

# Create a function to convert fasta files into a dictionary
def fasta_to_dict(fasta_file):
    """
    Reads a FASTA file and creates a dictionary with headers as keys and sequences as values.

    Function Parameters:
    fasta_file (str): Where "str" is the FASTA file path.

    Returns:
    dict: A dictionary with headers as keys and sequences as values.
    """
    # Create an empty dictionary to store the sequences
    seq_dict = {}

    # Access the fasta file
    with open(fasta_file, "r") as fastafile:
        # create a variable to hold the current header
        header = None  
        # Create a list to hold the sequence lines
        sequence = []  

        # For Loop to read the lines
        for line in fastafile:
            # Remove any whitespace
            line = line.strip() 
            # If statement to check if the line is a header
            if line.startswith(">"):
                # If the line is an header, save the sequence to the header variable
                if header is not None: 
                    # Join the sequence list into a string
                    seq_dict[header] = ''.join(sequence)  
                # Remove the '>' character
                header = line[1:]
                # Reset the sequence list for the new header
                sequence = [] 
            # Else statement
            else:
                # Add the line variables to the sequence list
                sequence.append(line)  

        # Add the last sequence after the loop
        if header is not None:
            seq_dict[header] = ''.join(sequence)

    # Return the dictionary
    return seq_dict  

# Test function 
fasta_dict = fasta_to_dict("Downloads/workshop_data.fasta")
print(fasta_dict) 

# Question 5

## How would you access individual elements of a dictionary created through the function you wrote in question 4?

# The fasta-file-into-dictionary function has been used to create a variable "fasta_dict"

# Method 1
# Use For loop to access the keys
for elements in fasta_dict.keys():
    # Print results, which includes the keys and values
    print(elements, fasta_dict[items])
	
# Method 2
# Use dict.items function to access the dictionary as a tuple
print(fasta_dict.items())

# Method 3
# Use for loop to access both keys and values of the dictionary via the dict.item function.
for k, v in fasta_dict.items():
    # Print statement which uses an equal to sign to join keys and values
    print(k, "=", v)