cs50/dna.py

import csv
import sys


def main():

    #  Check for command-line usage
    if len(sys.argv) != 3:
        print("Usage: python dna.py databases/*.csv sequences/*.txt")
        sys.exit(1)

    #  Read database file into a variable
    rows = []
    with open(sys.argv[1]) as db:
        for row in db:
            rows.append(row)

        #  Extract subsequences, removing name "pop(0)" and newline ".strip("n")"
        rows[0] = rows[0].strip("\n")
        subsequences = rows[0].split(',')
        subsequences.pop(0)

    #  Read DNA sequence file into a variable
    with open(sys.argv[2]) as seq:
        sequence = csv.DictReader(seq)
        sequence = sequence.fieldnames[0]

    #  Find longest match of each STR in DNA sequence
    longest_list = []
    for i in range(len(subsequences)):
        longest = longest_match(sequence, subsequences[i])
        longest_list.append(longest)

    #  Check database for matching profiles
    suspects = []
    suspect = []

    #  Create a list of "suspects"
    for s in range(1, len(rows)):
        suspects.append(rows[s].strip("\n"))

    #  Iterate over eachs "suspect"
    for s in range(len(suspects)):
        suspect.append(suspects[s].split(','))

    for m in range(len(suspects)):
        match = 0
    #  Iterate over each subsequence
        for n in range(len(longest_list)):
            if (int(suspect[m][n + 1]) == longest_list[n]):
                match += 1

        if (len(longest_list) == match):
            print(suspect[m][0])
            sys.exit()

    print("No match")

    return


def longest_match(sequence, subsequence):
    """Returns length of longest run of subsequence in sequence."""

    # Initialize variables
    longest_run = 0
    subsequence_length = len(subsequence)
    sequence_length = len(sequence)

    # Check each character in sequence for most consecutive runs of subsequence
    for i in range(sequence_length):

        # Initialize count of consecutive runs
        count = 0

        # Check for a subsequence match in a "substring" (a subset of characters) within sequence
        # If a match, move substring to next potential match in sequence
        # Continue moving substring and checking for matches until out of consecutive matches
        while True:

            # Adjust substring start and end
            start = i + count * subsequence_length
            end = start + subsequence_length

            # If there is a match in the substring
            if sequence[start:end] == subsequence:
                count += 1

            # If there is no match in the substring
            else:
                break

        # Update most consecutive matches found
        longest_run = max(longest_run, count)

    # After checking for runs at each character in seqeuence, return longest run found
    return longest_run


main()