Mercurial > repos > estrain > seqsero_v1

comparison SeqSero/libs/Initial_functions.py @ 0:c577b57b7c74 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author estrain
date Wed, 06 Dec 2017 15:59:29 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:c577b57b7c74
1 #!/usr/bin/env python
2
3
4 def To_list(L):
5 import string
6 New_list=[]
7 for x in L:
8 x1=x[:-1]
9 x1=string.atoi(x1)
10 New_list.append(x1)
11 return New_list
12
13
14 def Uniq(L): #return the uniq list and the count number
15 Old=L
16 L.sort()
17 L = [L[i] for i in range(len(L)) if L[i] not in L[:i]]
18 count=[]
19 for j in range(len(L)):
20 y=0
21 for x in Old:
22 if L[j]==x:
23 y+=1
24 count.append(y)
25 return (L,count)
26
27
28 def Parse_seros_in_genome_trakr(L): #return the sero names in the sra_result.xlsx, the next step is usually "Uniq" in above
29 names2=[]
30 for x in L:
31 if "serovar" in x:
32 key_word=x.split("serovar")[1].split("_")[1] #the seronames
33 if key_word!="str." and key_word!="group": #to eliminate some "serovar_str." and "serovar_group"
34 if key_word in ["I","II","III","IIIa","IIIb","IV","VI","B"]: #the serovar is behind those letters
35 if x.split("serovar")[1].split("_")[2]!="str.":
36 names2.append(x.split("serovar")[1].split("_")[2])
37 else:
38 names2.append(x.split("serovar")[1].split("_")[1])
39 return names2
40
41
42