hmms_clean

发表于 分类于

用于获取结构域内以半胱氨酸为标记

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
import sys
import re

domalist = []

id = ""
seq = ""
domain = ""
file = sys.argv[1]
file2 = sys.argv[2]
infile = open(file,'r')
for line in infile:
	tmp = line.replace('\n','').split()
	id = tmp[0]
	seq = tmp[1].replace('-','')
	domadict = {}
	domadict[id] = seq
	domalist.append(domadict)
#print(domalist)

infile.close()
outfile = open(file2,'w')
newlist = []
for dict in domalist:
	for i,j in dict.items():
		#print(i,j)
		elem = re.findall(r'C|[^C]+',j)
#		print(elem)
		newlist = []
		for x in elem:
			if x == "C":
				newlist.append(x)
			else:
				x = (f"X[{len(x)}]")
				newlist.append(x)
#				if newlist[0] != "C":
#					newlist = newlist[1:]
				domain = "".join(newlist)			
		outfile.write(f"{domain}\n")
		print(domain)
outfile.close()