aboutsummaryrefslogtreecommitdiff
path: root/wqflask/maintenance/dataset/probesets.py
blob: 23257f7e814ebd539fa4aa58072d30e4067ddefb (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
import sys

import utilities
import datastructure
import genotypes

def get_probesetxref(probesetfreezeid):
    cursor = utilities.get_cursor()
    sql = """
        SELECT ProbeSetXRef.`ProbeSetId`, ProbeSetXRef.`DataId`
        FROM ProbeSetXRef
        WHERE ProbeSetXRef.`ProbeSetFreezeId`=%s
        """
    cursor.execute(sql, (probesetfreezeid))
    return cursor.fetchall()
    
def get_probeset(probesetid):
    cursor = utilities.get_cursor()
    sql = """
        SELECT ProbeSet.`Id`, ProbeSet.`Name`, ProbeSet.`Symbol`, ProbeSet.`description`, ProbeSet.`Probe_Target_Description`, ProbeSet.`Chr`, ProbeSet.`Mb`
        FROM ProbeSet
        WHERE ProbeSet.`Id`=%s
        """
    cursor.execute(sql, (probesetid))
    return cursor.fetchone()
    
def get_probesetdata(probesetdataid):
    cursor = utilities.get_cursor()
    sql = """
        SELECT Strain.`Id`, Strain.`Name`, ProbeSetData.`value`
        FROM ProbeSetData, Strain
        WHERE ProbeSetData.`Id`=%s
        AND ProbeSetData.`StrainId`=Strain.`Id`;
        """
    cursor.execute(sql, (probesetdataid))
    return cursor.fetchall()

def get_probesetxref_probesetfreezeid(locus, probesetfreezeid):
    cursor = utilities.get_cursor()
    sql = """
        SELECT ProbeSetXRef.`ProbeSetId`
        FROM ProbeSetXRef
        WHERE ProbeSetXRef.`ProbeSetFreezeId`=%s
        AND ProbeSetXRef.`Locus` LIKE %s
        """
    cursor.execute(sql, (probesetfreezeid, locus))
    return cursor.fetchall()
    
def get_probesetxref_inbredsetid(locus, inbredsetid):
    cursor = utilities.get_cursor()
    sql = """
        SELECT ProbeSetXRef.`ProbeSetId`, ProbeSetXRef.`mean`, ProbeSetXRef.`LRS`, ProbeSetXRef.`Locus`, ProbeSetXRef.`ProbeSetFreezeId`
        FROM (ProbeSetXRef, ProbeSetFreeze, ProbeFreeze)
        WHERE ProbeSetXRef.`ProbeSetFreezeId`=ProbeSetFreeze.`Id`
        AND ProbeSetFreeze.`ProbeFreezeId`=ProbeFreeze.`Id`
        AND ProbeFreeze.`InbredSetId`=%s
        AND ProbeSetXRef.`Locus` LIKE %s
        """
    cursor.execute(sql, (inbredsetid, locus))
    return cursor.fetchall()

def get_normalized_probeset(locus, inbredsetid):
    normalized_probesets = []
    probesetxrefs = get_probesetxref_inbredsetid(locus, inbredsetid)
    for probesetxref in probesetxrefs:
        normalized_probeset = []
        #
        probesetfreezeid = probesetxref[4]
        probesetfreeze = datastructure.get_probesetfreeze(probesetfreezeid)
        normalized_probeset.append(probesetfreeze[0])
        normalized_probeset.append(probesetfreeze[1])
        normalized_probeset.append(probesetfreeze[2])
        #
        probesetid = probesetxref[0]
        probeset = get_probeset(probesetid)
        normalized_probeset.append(probeset[1])
        normalized_probeset.append(probeset[2])
        normalized_probeset.append(probeset[3])
        normalized_probeset.append(probeset[4])
        normalized_probeset.append(probeset[5])
        normalized_probeset.append(probeset[6])
        #
        normalized_probeset.append(probesetxref[1])
        normalized_probeset.append(probesetxref[2])
        #
        locus = probesetxref[3]
        geno = genotypes.get_geno(inbredsetid=inbredsetid, name=locus)
        normalized_probeset.append(geno[2])
        normalized_probeset.append(geno[3])
        #
        normalized_probesets.append(normalized_probeset)
    return normalized_probesets

locus="rs3663871"
inbredsetid=1

results = get_normalized_probeset(locus=locus, inbredsetid=inbredsetid)
file = open('probesets_%s.txt' % (locus), 'w+')
file.write("GN dataset ID\t")
file.write('\n')
file.flush()
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()