aboutsummaryrefslogtreecommitdiff
path: root/wqflask/maintenance/dataset/specials.py
blob: 4ff8533316b1c536734cf0a2ca233c90e7c56479 (plain)
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
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
import utilities
import datastructure
import genotypes
import probesets
import calculate

"""
For:    Rob, GeneNetwork
Date:   2014-02-04
Function:
    For BXD group, fetch probesets with given locus (mapping info).

locus="rs3663871"
"""
def bxd_probesets_locus(locus):
    #
    inbredsetid=1
    #
    file = open('probesets_%s.txt' % (locus), 'w+')
    file.write("GN Dataset ID\t")
    file.write("Dataset Full Name\t")
    file.write("ProbeSet Name\t")
    file.write("Symbol\t")
    file.write("ProbeSet Description\t")
    file.write("Probe Target Description\t")
    file.write("ProbeSet Chr\t")
    file.write("ProbeSet Mb\t")
    file.write("Mean\t")
    file.write("LRS\t")
    file.write("Geno Chr\t")
    file.write("Geno Mb\t")
    file.write("\n")
    file.flush()
    #
    results = get_normalized_probeset(locus=locus, inbredsetid=inbredsetid)
    for row in results:
        file.write("%s\t" % (row[0]))
        file.write("%s\t" % (utilities.clearspaces(row[2], default='')))
        file.write("%s\t" % (utilities.clearspaces(row[3], default='')))
        file.write("%s\t" % (utilities.clearspaces(row[4], default='')))
        file.write("%s\t" % (utilities.clearspaces(row[5], default='')))
        file.write("%s\t" % (utilities.clearspaces(row[6], default='')))
        file.write("%s\t" % (utilities.clearspaces(row[7], default='')))
        file.write("%s\t" % (row[8]))
        file.write("%s\t" % (row[9]))
        file.write("%s\t" % (row[10]))
        file.write("%s\t" % (utilities.clearspaces(row[11], default='')))
        file.write("%s\t" % (row[12]))
        file.write('\n')
        file.flush()
    file.close()

"""
For:    Ash
Date:   2014-02-05
Function:
    For BXD group, calculate correlations with genotypes and probesets.
Running History:
    2014-02-05  /home/leiyan/gn2/wqflask/maintenance/dataset/datadir/20140205_Ash_correlations/output
"""
def bxd_correlations():
    #
    inbredsetid = 1
    genofile = "/home/leiyan/gn/web/genotypes/BXD.geno"
    outputdir = "/home/leiyan/gn2/wqflask/maintenance/dataset/datadir/20140205_Ash_correlations/output"
    #
    t = genotypes.load_genos(genofile)
    genostrains = t[0]
    genos = t[1]
    print "From geno file, get %d strains" % (len(genostrains))
    print "From geno file, get %d genos" % (len(genos))
    #
    probesetfreezes = datastructure.get_probesetfreezes(inbredsetid)
    print "From DB, get %d probesetfreezes" % (len(probesetfreezes))
    #
    for probesetfreeze in probesetfreezes:
        #
        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()
        
bxd_correlations()