https://bioinformaticsonline.com/snippets/view/44740/python-script-to-find-all-possible-repeats-in-a-dna-string? https://bioinformaticsonline.com/snippets/view/44740/python-script-to-find-all-possible-repeats-in-a-dna-string Mon, 16 Dec 2024 07:54:38 -0600 https://bioinformaticsonline.com/snippets/view/44740/python-script-to-find-all-possible-repeats-in-a-dna-string from collections import defaultdict def find_repeats_in_genome(genome, min_length=2, max_length=None): """ Finds all repeating sequences in a genome within a specified length range. Parameters: genome (str): The genome sequence. min_length (int): Minimum length of repeats to scan for (default: 2). max_length (int): Maximum length of repeats to scan for (default: None, meaning entire genome). Returns: dict: A dictionary where keys are repeating sequences and values are lists of starting positions. """ if max_length is None: max_length = len(genome) repeats = defaultdict(list) # Iterate over all possible lengths of substrings for length in range(min_length, max_length + 1): seen = defaultdict(list) # Tracks occurrences of substrings of the current length # Sliding window approach for i in range(len(genome) - length + 1): substring = genome[i:i + length] seen[substring].append(i) # Filter substrings that appear more than once for substring, positions in seen.items(): if len(positions) > 1: repeats[substring].extend(positions) return repeats # Example usage def main(): genome = "ATCGATCGAATTCGATCG" # Example genome sequence min_length = 2 max_length = 5 repeats = find_repeats_in_genome(genome, min_length, max_length) print("Repeating sequences:") for seq, positions in repeats.items(): print(f"Sequence: {seq}, Positions: {positions}") if __name__ == "__main__": main()]]> LEGE