aboutsummaryrefslogtreecommitdiff
path: root/wqflask/maintenance/gen_select_dataset.py
blob: 3381305100c93bac34170f7da0456dabd6b75816 (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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
# Copyright (C) University of Tennessee Health Science Center, Memphis, TN.
#
# This program is free software: you can redistribute it and/or modify it
# under the terms of the GNU Affero General Public License
# as published by the Free Software Foundation, either version 3 of the
# License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
# See the GNU Affero General Public License for more details.
#
# This program is available from Source Forge: at GeneNetwork Project
# (sourceforge.net/projects/genenetwork/).
#
# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010)
# at rwilliams@uthsc.edu and xzhou15@uthsc.edu
#
#
#
# This module is used by GeneNetwork project (www.genenetwork.org)

# This script is to generate the data for the main menus on the home page
# It needs to be run manually when database has been changed .

from __future__ import print_function, division

import sys

sys.path.insert(0, "..")

import MySQLdb

import simplejson as json

from pprint import pformat as pf

from base import webqtlConfig


# build MySql database connection
Con = MySQLdb.Connect(db=webqtlConfig.DB_NAME,host=webqtlConfig.MYSQL_SERVER,
                      user=webqtlConfig.DB_USER,
                      passwd=webqtlConfig.DB_PASSWD)
Cursor = Con.cursor()


def get_species():
    """Build species list"""
    Cursor.execute("select Name, MenuName from Species order by OrderId")
    species = list(Cursor.fetchall())
    return species


def get_groups(species):
    """Build groups list"""
    groups = {}
    for species_name, _species_full_name in species:
        Cursor.execute("""select InbredSet.Name, InbredSet.FullName from InbredSet,
                       Species,
                       ProbeFreeze, GenoFreeze, PublishFreeze where Species.Name = %s
                       and InbredSet.SpeciesId = Species.Id and InbredSet.Name != 'BXD300' and
                       (PublishFreeze.InbredSetId = InbredSet.Id
                            or GenoFreeze.InbredSetId = InbredSet.Id
                            or ProbeFreeze.InbredSetId = InbredSet.Id)
                        group by InbredSet.Name
                        order by InbredSet.Name""", (species_name))
        groups[species_name] = list(Cursor.fetchall())
    return groups


def get_types(groups):
    """Build types list"""
    types = {}
    for species, group_dict in groups.iteritems():
        types[species] = {}
        for group_name, _group_full_name in group_dict:
            # make group an alias to shorten the code
            group = types[species][group_name] = [("Phenotypes", "Phenotypes"),
                                                  ("Genotypes", "Genotypes")]           
            Cursor.execute("""select distinct Tissue.Name, concat(Tissue.Name, ' mRNA') from
                       ProbeFreeze,
                       ProbeSetFreeze, InbredSet, Tissue where ProbeFreeze.TissueId = Tissue.Id and
                       ProbeFreeze.InbredSetId = InbredSet.Id and
                       InbredSet.Name = %s and ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id and
                       ProbeSetFreeze.public > %s
                       order by Tissue.Name""", (group_name, webqtlConfig.PUBLICTHRESH))
            group += Cursor.fetchall()
    return types


def get_datasets(types):
    """Build datasets list"""
    datasets = {}
    for species, group_dict in types.iteritems():
        datasets[species] = {}
        for group, type_list in group_dict.iteritems():
            datasets[species][group] = {}
            for type_name, type_full_name in type_list:
                dataset_text = dataset_value = None
                if type_name == "Phenotypes":
                    dataset_value = "%sPublish" % group
                    if group == 'MDP':
                        dataset_text = "Mouse Phenome Database"
                    else:
                        dataset_text = "%s Published Phenotypes" % group

                elif type_name == "Genotypes":
                    dataset_value = "%sGeno" % group
                    dataset_text = "%s Genotypes" % group
                    
                if dataset_value:
                    datasets[species][group][type_name] = [(dataset_value, dataset_text)]
                else:
                    Cursor.execute("""select ProbeSetFreeze.Name, ProbeSetFreeze.FullName from
                                ProbeSetFreeze, ProbeFreeze, InbredSet, Tissue where
                                ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id and Tissue.Name = %s
                                and ProbeFreeze.TissueId = Tissue.Id and ProbeFreeze.InbredSetId =
                                InbredSet.Id and ProbeSetFreeze.public > %s order by
                                ProbeSetFreeze.CreateTime desc""", (type_name,
                                                                    webqtlConfig.PUBLICTHRESH))
                    datasets[species][group][type_name] = Cursor.fetchall()
            
    return datasets


def main():
    species = get_species()
    groups = get_groups(species)
    types = get_types(groups)
    datasets = get_datasets(types)
    
    species.append(('All Species', 'All Species'))
    groups['All Species'] = [('All Groups', 'All Groups')]
    types['All Species'] = {}
    types['All Species']['All Groups'] = [('Phenotypes', 'Phenotypes')]
    datasets['All Species'] = {}
    datasets['All Species']['All Groups'] = {}
    datasets['All Species']['All Groups']['Phenotypes'] = [('All Phenotypes','All Phenotypes')]
    
    data = dict(species=species,
                groups=groups,
                types=types,
                datasets=datasets,
                )
    
    output_file = """../wqflask/static/new/javascript/dataset_menu_structure.json"""
    
    with open(output_file, 'w') as fh:
        json.dump(data, fh, indent="   ", sort_keys=True)
    

if __name__ == '__main__':
    main()