bioinformatics-python/lab02.py at main · wavetearz/bioinformatics-python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
import math

f = open("toeprint.rdat")
c = [a.split("\t") for a in f.readlines()]

# delete unnecessary text
for i in range(len(c)):
    del c[i][0:3]
# delete \n
for i in range(len(c) - 1):
    c[i][len(c[0]) - 1] = c[0][len(c[i]) - 1].rstrip()

for i in range(len(c)):
    c[i] = (list(map(int, c[i])))

sums = [sum(c[0]), sum(c[1])]

# a)
norm = []
for i in range(len(c)):
    norm.append([])
    for j in range(len(c[i])):
        norm[i].append(round((c[i][j] * 1000000) / sums[i], 4))

# b)
norm2 = []
avgs = [sum(c[0]) / len(c[0]), sum(c[1]) / len(c[1])]

for i in range(len(c)):
    norm2.append([])
    for j in range(len(c[i])):
        if c[i][j] != 0:
            norm2[i].append(round(math.log(c[i][j] / avgs[i], 2), 4))

# task 2

#first normalization:
result = []

for i in range(len(norm[0])):
    try:
        result.append(norm[0][i] / norm[1][i])
    except:
        result.append(0)

print(result.index(max(result)) + 1)

#second normalization:
result = []

for i in range(len(norm2[0])):
    try:
        result.append(norm2[0][i] - norm2[1][i])
    except:
        result.append(0)

print(result.index(max(result)) + 1)