Click here to download genesearch.py.

# Search for a small gene pattern in a larger genetic sequence

# Read in the contents of dna.txt to a single large string
fin = open('dna.txt')
dnaseq = fin.read().strip()
fin.close()

# This function finds the number of mismatches between
# the pattern and sequence at a single given position.
def mismatches(pattern, position):
    misses = 0
    for i in range(len(pattern)):
        if position + i >= len(dnaseq) or dnaseq[position + i] != pattern[i]:
            misses += 1
    return misses

# This function computes the smallest number of mismatches
# for any position between start_position and end_position.
def best_match(pattern, start_position, end_position):
    best = len(pattern)
    for position in range(start_position, end_position):
        mis = mismatches(pattern, position)
        if mis < best:
            best = mis
    return best

# Main gets the search pattern from the terminal and
# performs the search over the entire sequence.
if __name__ == '__main__':
    pattern = input('enter search pattern: ')
    closest = best_match(pattern, 0, len(dnaseq))
    print(closest)