Generation of random sequences

Here is the code provided in the article with the additional feature of converting random sequences into Fasta format. 

#To begin, let us use the code developed by Schuster & Hirth (DOI: 10.1126/sciadv.ade8259)

import random

with open('sequences.txt', 'w') as f:

    for length in [365, 247, 373]:

        for i in range(50):

            f.write("".join(random.choices(["G", "C", "A", "T"], weights=(0.2, 0.2, 0.4, 0.4), k=length)))

            f.write("\n")

# Open the input file and output files

with open('sequences.txt', 'r') as input_file, \

     open('sv_PAX2_random.txt', 'w') as sv_pax2, \

     open('inv_EN2_random.txt', 'w') as inv_en2, \

     open('dac_DACH1_random.txt', 'w') as dac_dach1:

    for i, line in enumerate(input_file):

        if i < 50 and len(line.strip()) == 365:  # Check for first 50 lines with 365 characters

            sv_pax2.write(line)

        elif 50 <= i < 100 and len(line.strip()) == 247:  # Lines 51–100

            dac_dach1.write(line)

        elif 100 <= i < 150 and len(line.strip()) == 373:  # Lines 101–150

            inv_en2.write(line)

#Now to make these sequences identifiable, we are going to turn these into a FASTA format. This will be done for each new .txt file

# Open the input text file containing genes

with open('dac_DACH1_random.txt', 'r') as input_file:

    # Open an output file in FASTA format

    with open('dac_DACH1_random_FASTA.txt', 'w') as output_file:

        for i, sequence in enumerate(input_file):

            sequence = sequence.strip()  # Remove any extra whitespace or newline characters

            if sequence:  # Ensure it's not an empty line

                # Write a header (e.g., >Gene_1, >Gene_2, etc.)

                output_file.write(f">random_dac_DACH1_Sequence_{i+1}\n")

                # Write the gene sequence

                output_file.write(sequence + "\n")

with open('inv_EN2_random.txt', 'r') as input_file:

    # Open an output file in FASTA format

    with open('inv_EN2_random_FASTA.txt', 'w') as output_file:

        for i, sequence in enumerate(input_file):

            sequence = sequence.strip()  # Remove any extra whitespace or newline characters

            if sequence:  # Ensure it's not an empty line

                # Write a header (e.g., >Gene_1, >Gene_2, etc.)

                output_file.write(f">random_inv_EN2_Sequence_{i+1}\n")

                # Write the gene sequence

                output_file.write(sequence + "\n")

with open('sv_PAX2_random.txt', 'r') as input_file:

    # Open an output file in FASTA format

    with open('sv_PAX2_random_FASTA.txt', 'w') as output_file:

        for i, sequence in enumerate(input_file):

            sequence = sequence.strip()  # Remove any extra whitespace or newline characters

            if sequence:  # Ensure it's not an empty line

                # Write a header (e.g., >Gene_1, >Gene_2, etc.)

                output_file.write(f">random_sv_PAX2_Sequence_{i+1}\n")

                # Write the gene sequence

                output_file.write(sequence + "\n")