1 | #!/usr/bin/env python
|
---|
2 | #Dan Blankenberg
|
---|
3 |
|
---|
4 | import sys, os
|
---|
5 |
|
---|
6 | assert sys.version_info[:2] >= ( 2, 4 )
|
---|
7 |
|
---|
8 | def __main__():
|
---|
9 | base_dir = os.path.join( os.getcwd(), "bacteria" )
|
---|
10 | try:
|
---|
11 | base_dir = sys.argv[1]
|
---|
12 | except:
|
---|
13 | pass
|
---|
14 | #print "using default base_dir:", base_dir
|
---|
15 |
|
---|
16 | organisms = {}
|
---|
17 | for result in os.walk(base_dir):
|
---|
18 | this_base_dir,sub_dirs,files = result
|
---|
19 | for file in files:
|
---|
20 | if file[-5:] == ".info":
|
---|
21 | dict = {}
|
---|
22 | info_file = open(os.path.join(this_base_dir,file),'r')
|
---|
23 | info = info_file.readlines()
|
---|
24 | info_file.close()
|
---|
25 | for line in info:
|
---|
26 | fields = line.replace("\n","").split("=")
|
---|
27 | dict[fields[0]]="=".join(fields[1:])
|
---|
28 | if 'genome project id' in dict.keys():
|
---|
29 | name = dict['genome project id']
|
---|
30 | if 'build' in dict.keys():
|
---|
31 | name = dict['build']
|
---|
32 | if name not in organisms.keys():
|
---|
33 | organisms[name] = {'chrs':{},'base_dir':this_base_dir}
|
---|
34 | for key in dict.keys():
|
---|
35 | organisms[name][key]=dict[key]
|
---|
36 | else:
|
---|
37 | if dict['organism'] not in organisms.keys():
|
---|
38 | organisms[dict['organism']] = {'chrs':{},'base_dir':this_base_dir}
|
---|
39 | organisms[dict['organism']]['chrs'][dict['chromosome']]=dict
|
---|
40 | for org in organisms:
|
---|
41 | org = organisms[org]
|
---|
42 | #if no gpi, then must be a ncbi chr which corresponds to a UCSC org, w/o matching UCSC designation
|
---|
43 | try:
|
---|
44 | build = org['genome project id']
|
---|
45 | except: continue
|
---|
46 | if 'build' in org:
|
---|
47 | build = org['build']
|
---|
48 | print "ORG\t%s\t%s\t%s\t%s\t%s\t%s\tUCSC" % ( build, org['name'], org['kingdom'], org['group'], org['chromosomes'], org['info url'] )
|
---|
49 | else:
|
---|
50 | print "ORG\t%s\t%s\t%s\t%s\t%s\t%s\tNone" % ( build, org['name'], org['kingdom'], org['group'], org['chromosomes'], org['info url'] )
|
---|
51 |
|
---|
52 | for chr in org['chrs']:
|
---|
53 | chr = org['chrs'][chr]
|
---|
54 | print "CHR\t%s\t%s\t%s\t%s\t%s\t%s\t%s" % ( build, chr['chromosome'], chr['name'], chr['length'], chr['gi'], chr['gb'], "http://www.ncbi.nlm.nih.gov/entrez/viewer.fcgi?db=nucleotide&val="+chr['refseq'] )
|
---|
55 | for feature in ['CDS','tRNA','rRNA']:
|
---|
56 | print "DATA\t%s_%s_%s\t%s\t%s\t%s\t%s\t%s" % ( build, chr['chromosome'], feature, build, chr['chromosome'], feature, "bed", os.path.join( org['base_dir'], "%s.%s.bed" % ( chr['chromosome'], feature ) ) )
|
---|
57 | #FASTA
|
---|
58 | print "DATA\t%s_%s_%s\t%s\t%s\t%s\t%s\t%s" % ( build, chr['chromosome'], "seq", build, chr['chromosome'], "sequence", "fasta", os.path.join( org['base_dir'], "%s.fna" % chr['chromosome'] ) )
|
---|
59 | #GeneMark
|
---|
60 | if os.path.exists( os.path.join( org['base_dir'], "%s.GeneMark.bed" % chr['chromosome'] ) ):
|
---|
61 | print "DATA\t%s_%s_%s\t%s\t%s\t%s\t%s\t%s" % ( build, chr['chromosome'], "GeneMark", build, chr['chromosome'], "GeneMark", "bed", os.path.join( org['base_dir'], "%s.GeneMark.bed" % chr['chromosome'] ) )
|
---|
62 | #GenMarkHMM
|
---|
63 | if os.path.exists( os.path.join( org['base_dir'], "%s.GeneMarkHMM.bed" % chr['chromosome'] ) ):
|
---|
64 | print "DATA\t%s_%s_%s\t%s\t%s\t%s\t%s\t%s" % ( build, chr['chromosome'], "GeneMarkHMM", build, chr['chromosome'], "GeneMarkHMM", "bed", os.path.join( org['base_dir'], "%s.GeneMarkHMM.bed" % chr['chromosome'] ) )
|
---|
65 | #Glimmer3
|
---|
66 | if os.path.exists( os.path.join( org['base_dir'], "%s.Glimmer3.bed" % chr['chromosome'] ) ):
|
---|
67 | print "DATA\t%s_%s_%s\t%s\t%s\t%s\t%s\t%s" % ( build, chr['chromosome'], "Glimmer3", build, chr['chromosome'], "Glimmer3", "bed", os.path.join( org['base_dir'], "%s.Glimmer3.bed" % chr['chromosome'] ) )
|
---|
68 |
|
---|
69 | if __name__ == "__main__": __main__()
|
---|