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
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
|
import utilities
import datastructure
import genotypes
import probesets
import calculate
def correlations(outputdir, genos, probesetfreeze):
print probesetfreeze
probesetfreezeid = probesetfreeze[0]
probesetfreezename = probesetfreeze[1]
probesetfreezefullname = probesetfreeze[2]
#
outputfile = open("%s/%d_%s.txt" % (outputdir, probesetfreezeid, probesetfreezename), "w+")
outputfile.write("%s\t" % "ProbeSet Id")
outputfile.write("%s\t" % "ProbeSet Name")
outputfile.write("%s\t" % "Geno Name")
outputfile.write("%s\t" % "Overlap Number")
outputfile.write("%s\t" % "Pearson r")
outputfile.write("%s\t" % "Pearson p")
outputfile.write("%s\t" % "Spearman r")
outputfile.write("%s\t" % "Spearman p")
outputfile.write("\n")
outputfile.flush()
#
probesetxrefs = probesets.get_probesetxref(probesetfreezeid)
print "Get %d probesetxrefs" % (len(probesetxrefs))
#
for probesetxref in probesetxrefs:
#
probesetid = probesetxref[0]
probesetdataid = probesetxref[1]
probeset = probesets.get_probeset(probesetid)
probesetname = probeset[1]
probesetdata = probesets.get_probesetdata(probesetdataid)
probesetdata = zip(*probesetdata)
probesetdata = utilities.to_dic([strain.lower() for strain in probesetdata[1]], probesetdata[2])
#
for geno in genos:
genoname = geno['locus']
outputfile.write("%s\t" % probesetid)
outputfile.write("%s\t" % probesetname)
outputfile.write("%s\t" % genoname)
#
dic1 = geno['dicvalues']
dic2 = probesetdata
keys, values1, values2 = utilities.overlap(dic1, dic2)
rs = calculate.correlation(values1, values2)
#
outputfile.write("%s\t" % len(keys))
outputfile.write("%s\t" % rs[0][0])
outputfile.write("%s\t" % rs[0][1])
outputfile.write("%s\t" % rs[1][0])
outputfile.write("%s\t" % rs[1][1])
outputfile.write("\n")
outputfile.flush()
#
outputfile.close()
"""
For: Ash
Date: 2014-02-12
Function:
Generate probeset data files.
given probesetfreeze list.
"""
def generate_probesets(probesetfreezesfile, outputdir):
file = open(probesetfreezesfile, 'r')
for line in file:
line = line.strip()
cells = line.split()
probesetfreezeid = cells[0]
probesetfreeze = datastructure.get_probesetfreeze(probesetfreezeid)
probesetfreezeid = probesetfreeze[0]
probesetfreezename = probesetfreeze[1]
inbredset = datastructure.get_inbredset(probesetfreezeid)
inbredsetid = inbredset[0]
strains = datastructure.get_strains(inbredsetid)
#
outputfile = open("%s/%d_%s.txt" % (outputdir, probesetfreezeid, probesetfreezename), "w+")
outputfile.write("%s\t" % "ProbeSet Id")
outputfile.write("%s\t" % "ProbeSet Name")
outputfile.write('\t'.join([strain[1].upper() for strain in strains]))
outputfile.write("\n")
outputfile.flush()
#
probesetxrefs = probesets.get_probesetxref(probesetfreezeid)
print probesetfreeze
print len(probesetxrefs)
for probesetxref in probesetxrefs:
probesetid = probesetxref[0]
probesetdataid = probesetxref[1]
probeset = probesets.get_probeset(probesetid)
probesetname = probeset[1]
probesetdata = probesets.get_probesetdata(probesetdataid)
probesetdata = zip(*probesetdata)
probesetdata = utilities.to_dic([strain.lower() for strain in probesetdata[1]], probesetdata[2])
#
for strain in strains:
strainname = strain[1]
strainname = strainname.lower()
if strainname in probesetdata:
value = probesetdata[strainname]
else:
value = 'x'
outputfile.write("%s\t" % value)
outputfile.write("\n")
outputfile.flush()
#
outputfile.close()
file.close()
probesetfreezesfile = "/home/leiyan/gn2/wqflask/maintenance/dataset/datadir/20140205_Ash_correlations/output2/probesetfreezes_filter.txt"
outputdir = "/home/leiyan/gn2/wqflask/maintenance/dataset/datadir/20140205_Ash_correlations/output2"
generate_probesets(probesetfreezesfile, outputdir)
|
