#!/usr/bin/env python3

name1 = input('Protein name 1: ')
name2 = input('Protein name 2: ')

path1 = name1.lower() + '_' + name2.lower() + '.needle'
file1 = open(path1)
seq_whole_1 = ''
seq_whole_2 = ''

for line in file1:
    if not line.startswith('#'):
        if line.startswith(name1.upper() + '_ECOLI'):
            seq_whole_1 += line.split()[2]
        elif line.startswith(name2.upper() + '_ECOLI'):
            seq_whole_2 += line.split()[2]
file1.close()



path2 = name1.lower() + '_' + name2.lower() + '.water'
file2 = open(path2)
seq_fragm_1 = ''
seq_fragm_2 = ''

for line in file2:
    if not line.startswith('#'):
        if line.startswith(name1.upper() + '_ECOLI'):
            seq_fragm_1 += line.split()[2]
        elif line.startswith(name2.upper() + '_ECOLI'):
            seq_fragm_2 += line.split()[2]
file2.close()

coverage1 = (len(seq_fragm_1) - seq_fragm_1.count('-')) / (len(seq_whole_1) - seq_whole_1.count('-')) * 100
coverage2 = (len(seq_fragm_2) - seq_fragm_2.count('-')) / (len(seq_whole_2) - seq_whole_2.count('-')) * 100
print(f'Coverage {name1} (E. coli): {coverage1:.01f}')
print(f'Coverage {name2} (E. coli): {coverage2:.01f}')