ΘΕΜΑ: Προγραμμα υπολογισμού ομοιότητας ακολουθιών

#!/usr/bin/env python
# -*- coding: utf-8 -*-
 
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
from __future__ import absolute_import
 
import sys
import random
 
 
def chunkify(iterable, n):
    """ Yield successive n-sized chunks from the given iterable. """
    chunks = []
    for i in range(0, len(iterable), n):
        chunks.append(iterable[i:i+n])
    return chunks
 
 
def find_common_items(seq_a, seq_b):
    common = 0
    for item in seq_a:
        if item in seq_b:
            common += 1
    return common
 
 
def calc_tanimoto_coeff(chunks_a, chunks_b):
    common = find_common_items(chunks_a, chunks_b)
    coeff = common / (len(chunks_a) + len(chunks_b) - common)
    return coeff
 
 
def main(dna1, dna2):
    # initial calculation
    n = 1
    chunks1 = chunkify(dna1, 6)
    chunks2 = chunkify(dna2, 6)
    coeff = calc_tanimoto_coeff(chunks1, chunks2)
    print("Iter %d Tanimoto Coeff: %f" % (n, coeff))
 
    while coeff == 0.0:
        n += 1
        random.shuffle(dna2)
        chunks2 = chunkify(dna2, 6)
        coeff = calc_tanimoto_coeff(chunks1, chunks2)
        print("Iter %d Tanimoto Coeff: %f" % (n, coeff))
    print("done")
 
 
if __name__ == "__main__":
    # read input
    with open('C:\Users\Desktop\Python\\alist.txt', 'r') as fd:
        dna1 = fd.read()
    with open('C:\Users\Desktop\Python\\blist.txt', 'r') as fd:
        dna2 = fd.read()
 
    # check that the provided proteins can be divided into chunks of 6
    if len(dna1) % 6 != 0:
        print("dna1 not divisible by 6. Remainder:", len(dna1) % 6)
        sys.exit()
        1/0
    if len(dna2) % 6 != 0:
        print("dna2 not divisible by 6. Remainder:", len(dna2) % 6)
        sys.exit()
 
    main(dna1, dna2)