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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285 | #!/usr/bin/env python
import json
import sys
from numpy import arange
import requests
#########################################################
# user parameters
#######################################################
download_all_projects = False
download_all_cases = False
number_of_projects = 2
number_of_cases = 2
number_of_files = 2
# NB very few annotations per case, get all
#######################################################
# endpoints definition
########################################################
projects_endpt = 'https://api.gdc.cancer.gov/projects'
cases_endpt = 'https://api.gdc.cancer.gov/cases'
annotations_endpt = 'https://api.gdc.cancer.gov/annotations'
def create_filter(): # noqa: C901
###########################################################
# step1: get total number of TCGA projects (program.name)
###########################################################
params = {
'facets': 'program.name',
'from': 0,
'size': 0,
}
response = requests.get(projects_endpt, params=params)
buckets = response.json()['data']['aggregations']['program.name']['buckets']
for j in arange(len(buckets)):
if buckets[j]['key'] == 'TCGA':
size_max = buckets[j]['doc_count']
break
if download_all_projects:
size = size_max
else:
size = min(size_max, number_of_projects)
##############################################################
# step 2: filtered query to get the UIDs of each TCGA project
##############################################################
fields = ['summary.case_count', 'summary.file_count']
fields = ','.join(fields)
filters = {
'op': 'in',
'content': {
'field': 'program.name',
'value': ['TCGA'],
},
}
params = {
'filters': json.dumps(filters),
'fields': fields,
'size': size,
}
response = requests.get(projects_endpt, params=params)
if len(response.json()['data']['hits']) != size:
print('size mismatch')
sys.exit()
projects_list = (response.json()['data']['hits'])
##########################################################################
# Step3: filtered query on 'cases' (filter on project_id) to get cases ID for each TCGA project
# the IDs for all the files are also available form this endpoint
########################################################################
fields = ['files.file_id', 'summary.file_count', 'annotation']
fields = ','.join(fields)
for proj in projects_list:
if download_all_cases:
size = proj['summary']['case_count']
else:
size = min(proj['summary']['case_count'], number_of_cases)
filters = {
'op': 'in',
'content': {
'field': 'project.project_id',
'value': proj['id'],
},
}
params = {
'filters': json.dumps(filters),
'fields': fields,
'size': size,
}
response = requests.get(cases_endpt, params=params)
cases = (response.json()['data']['hits'])
proj['cases'] = cases
##############################################################################
# step4: filtered query on 'annotations' (filter on case_id) to get cases
# ID for each TCGA project the IDs for all the files are also available
# form this endpoint
##############################################################################
fields = ['annotation_id']
for proj in projects_list:
for case in proj['cases']:
filters = {
'op': 'in',
'content': {
'field': 'case_id',
'value': case['id'],
},
}
params = {
'fields': fields,
'filters': json.dumps(filters),
}
response = requests.get(annotations_endpt, params=params)
annotations = response.json()['data']['hits']
case['annotations'] = annotations
############################################################################
# step 5: create list of IDs for projects, cases, files and annotations
# Use these lists to define filters and write them to file
###########################################################################
proj_id_list = []
case_id_list = []
file_id_list = []
ant_id_list = []
for proj in projects_list:
proj_id_list.append(proj['id'])
for case in proj['cases']:
case_id_list.append(case['id'])
for i, file in enumerate(case['files']):
if i >= number_of_files:
continue
file_id_list.append(file['file_id'])
for ant in case['annotations']:
ant_id_list.append(ant['annotation_id'])
id_dict = {
'projects': proj_id_list,
'cases': case_id_list,
'files': file_id_list,
'annotations': ant_id_list,
}
for entry in ['cases', 'projects', 'files', 'annotations']:
filters = {
'op': 'in',
'content': {
'field': entry[0:-1] + '_id',
'value': id_dict[entry],
},
}
with open(entry + '_filter.json', 'w') as outfile:
json.dump(filters, outfile, indent=4)
|