comparison rtrnKEGGpthwfENSEMBLTc.py @ 0:2c498d40ecde

Uploaded
author miller-lab
date Mon, 09 Apr 2012 12:03:06 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:2c498d40ecde
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3 #
4 # calclenchange.py
5 #
6 # Copyright 2011 Oscar Bedoya-Reina <oscar@niska.bx.psu.edu>
7 #
8 # This program is free software; you can redistribute it and/or modify
9 # it under the terms of the GNU General Public License as published by
10 # the Free Software Foundation; either version 2 of the License, or
11 # (at your option) any later version.
12 #
13 # This program is distributed in the hope that it will be useful,
14 # but WITHOUT ANY WARRANTY; without even the implied warranty of
15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16 # GNU General Public License for more details.
17 #
18 # You should have received a copy of the GNU General Public License
19 # along with this program; if not, write to the Free Software
20 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
21 # MA 02110-1301, USA.
22
23 import argparse,os,sys
24
25
26 def main():
27 parser = argparse.ArgumentParser(description='Adds the fields KEGG gene codes and KEGG pathways to an input table of ENSEMBL transcript codes.')
28 parser.add_argument('--loc_file',metavar='correlational database',type=str,help='correlational database')
29 parser.add_argument('--species',metavar='species name',type=str,help='the species of interest in loc_file')
30 parser.add_argument('--output',metavar='output TXT file',type=str,help='the output file with the table in txt format. The output will have two more fields: KEGG gene codes and KEGG pathways of each ENSEMBL code' )
31 parser.add_argument('--posENSEMBLclmn',metavar='column number',type=int,help='the column with the ENSEMBLE transcript code')
32 parser.add_argument('--input',metavar='input TXT file',type=str,help='the input file with the table in txt format')
33 #~
34 #~Open arguments
35 class C(object):
36 pass
37 fulargs=C()
38 parser.parse_args(sys.argv[1:],namespace=fulargs)
39 #test input vars
40 inputf,loc_file,species,output,posENSEMBLclmn=fulargs.input,fulargs.loc_file,fulargs.species,fulargs.output,fulargs.posENSEMBLclmn
41 posENSEMBLclmn-=1#correct pos
42 #~ Get the extra variables
43 crDB=[x.split() for x in open(loc_file).read().splitlines() if x.split()[0]==species][0]
44 sppPrefx,dinput=crDB[0],crDB[1]#X should be replaced by the position in which the Conversion Dictionary File (CDF) is placed
45 #make a dictionary of the input CDF
46 dKEGGcPthws=dict([(x.split('\t')[0],'\t'.join(x.split('\t')[1:])) for x in open(dinput).read().splitlines() if x.strip()])
47 #~ add the two new columns
48 sall=[]
49 #lENSEMBLTc=[x.split('\t') for x in open(inputf).read().splitlines() if x.strip()]
50 lENSEMBLTc = []
51 with open(inputf) as fh:
52 for line in fh:
53 if line.startswith('#'):
54 continue
55 lENSEMBLTc.append(line.rstrip('\r\n').split('\t'))
56 nLines=len(lENSEMBLTc)
57 cLines=0
58 sall=[]#the output list for with additional fields
59 #~
60 while cLines<nLines:
61 cLines+=1
62 lENSEMBLTcKEGGgKEGGpth=lENSEMBLTc.pop(0)
63 ENSEMBLTc=lENSEMBLTcKEGGgKEGGpth[posENSEMBLclmn]
64 try:
65 KEGGgKEGGpth=dKEGGcPthws[ENSEMBLTc]
66 except:
67 KEGGgKEGGpth='\t'.join(['U','N'])
68 sall.append('\t'.join(['\t'.join(lENSEMBLTcKEGGgKEGGpth),KEGGgKEGGpth]))
69 #~
70 salef=open(output,'w')
71 salef.write('\n'.join(sall))
72 salef.close()
73 return 0
74
75
76 if __name__ == '__main__':
77 main()
78