-
Notifications
You must be signed in to change notification settings - Fork 2
/
exporter-obesity.py
executable file
·267 lines (226 loc) · 12.8 KB
/
exporter-obesity.py
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
#!/usr/bin/python3
# vim:ts=4:sw=4:tw=0:sts=4:et
import pprint
import re
import argparse
import logging as log
from builtins import str, isinstance, len, set, int
from typing import List
import pandas as pd
from directory import Directory
from orphacodes import OrphaCodes
from icd10codeshelper import ICD10CodesHelper
import pddfutils
cachesList = ['directory', 'emails', 'geocoding', 'URLs']
pp = pprint.PrettyPrinter(indent=4)
class ExtendAction(argparse.Action):
def __call__(self, parser, namespace, values, option_string=None):
from builtins import getattr, setattr
items = getattr(namespace, self.dest) or []
items.extend(values)
setattr(namespace, self.dest, items)
parser = argparse.ArgumentParser()
parser.register('action', 'extend', ExtendAction)
parser.add_argument('-v', '--verbose', dest='verbose', action='store_true',
help='verbose information on progress of the data checks')
parser.add_argument('-d', '--debug', dest='debug', action='store_true',
help='debug information on progress of the data checks')
parser.add_argument('-X', '--output-XLSX', dest='outputXLSX', nargs=1,
help='output of results into XLSX with filename provided as parameter')
parser.add_argument('-O', '--orphacodes-mapfile', dest='orphacodesfile', nargs=1,
help='file name of Orpha code mappings from http://www.orphadata.org/cgi-bin/ORPHAnomenclature.html')
parser.add_argument('-N', '--output-no-stdout', dest='nostdout', action='store_true',
help='no output of results into stdout (default: enabled)')
parser.add_argument('--purge-all-caches', dest='purgeCaches', action='store_const', const=cachesList,
help='disable all long remote checks (email address testing, geocoding, URLs')
parser.add_argument('--purge-cache', dest='purgeCaches', nargs='+', action='extend', choices=cachesList,
help='disable particular long remote checks')
parser.set_defaults(disableChecksRemote=[], disablePlugins=[], purgeCaches=[])
args = parser.parse_args()
if args.debug:
log.basicConfig(format="%(levelname)s: %(message)s", level=log.DEBUG)
elif args.verbose:
log.basicConfig(format="%(levelname)s: %(message)s", level=log.INFO)
else:
log.basicConfig(format="%(levelname)s: %(message)s")
# Main code
dir = Directory(purgeCaches=args.purgeCaches, debug=args.debug, pp=pp)
log.info('Total biobanks: ' + str(dir.getBiobanksCount()))
log.info('Total collections: ' + str(dir.getCollectionsCount()))
orphacodes = OrphaCodes(args.orphacodesfile)
collectionsPediatricOnlyObesityDiagnosed = []
biobanksPediatricOnlyObesityDiagnosed = set()
pediatricOnlyObesitySamplesExplicit = 0
pediatricOnlyObesitySamplesIncOoM = 0
pediatricOnlyObesityDonorsExplicit = 0
collectionsPediatricObesityDiagnosed = []
biobanksPediatricObesityDiagnosed = set()
pediatricObesitySamplesExplicit = 0
pediatricObesitySamplesIncOoM = 0
pediatricObesityDonorsExplicit = 0
collectionsObesityDiagnosed = []
biobanksObesityDiagnosed = set()
obesitySamplesExplicit = 0
obesitySamplesIncOoM = 0
obesityDonorsExplicit = 0
for collection in dir.getCollections():
log.debug("Analyzing collection " + collection['id'])
biobankId = dir.getCollectionBiobankId(collection['id'])
biobank = dir.getBiobankById(biobankId)
biobank_capabilities = []
if 'capabilities' in biobank:
for c in biobank['capabilities']:
biobank_capabilities.append(c['id'])
biobank_covid = []
if 'covid19biobank' in biobank:
for c in biobank['covid19biobank']:
biobank_covid.append(c['id'])
biobank_networks = []
if 'network' in biobank:
for n in biobank['network']:
biobank_networks.append(n['id'])
OoM = collection['order_of_magnitude']['id']
materials = []
if 'materials' in collection:
for m in collection['materials']:
materials.append(m['id'])
data_categories = []
if 'data_categories' in collection:
for c in collection['data_categories']:
data_categories.append(c['id'])
types = []
if 'type' in collection:
for t in collection['type']:
types.append(t['id'])
log.debug("Types: " + str(types))
diags = []
diag_ranges = []
obesity = False
for d in collection['diagnosis_available']:
if re.search('-', d['id']):
diag_ranges.append(d['id'])
else:
diags.append(d['id'])
if diag_ranges:
log.warning("There are diagnosis ranges provided for collection " + collection['id'] + ": " + str(diag_ranges))
log.debug(str(collection['diagnosis_available']))
for d in diags + diag_ranges:
if re.search(r'^urn:miriam:icd:', d):
d = re.sub(r'^urn:miriam:icd:', '', d)
isObesity = ICD10CodesHelper.isObesityCode(d)
if isObesity is not None and isObesity:
log.debug(
"Collection %s identified as obesity collection due to ICD-10 code %s" % (collection['id'], d))
obesity = True
if 'name' in collection:
if re.search(r'(obesity|obese)', collection['name'], re.IGNORECASE):
log.debug("Collection %s identified as obesity collection due to its name %s" % (collection['id'], collection['name']))
obesity = True
if 'description' in collection:
if re.search(r'(obesity|obese)', collection['description'], re.IGNORECASE):
log.debug("Collection %s identified as obesity collection due to its description" % (collection['id']))
obesity = True
pediatric = False
pediatricOnly = False
age_unit = None
if 'age_unit' in collection:
age_units = collection['age_unit']
if len(age_units) > 1:
log.warning("Ambiguous age units provided for %s: %s"%(collection['id'],age_units))
if len(age_units) < 1:
log.warning("Age units missing for %s"%(collection['id']))
else:
age_unit = age_units[0]['id']
age_max = 18
if age_unit == "MONTH":
age_max = age_max*12
elif age_unit == "WEEK":
age_max = age_max*52.1775
elif age_unit == "DAY":
age_max = age_max*365.25
if 'age_high' in collection and collection['age_high'] == 0:
if 'age_low' in collection and collection['age_low'] < 0:
pediatric = True
pediatricOnly = True
log.debug("Prenatal collection detected: %s (%s), age range: %d-%d, diags: %s"%(collection['id'], collection['name'], collection.get('age_low'), collection.get('age_high'), diags + diag_ranges))
else:
log.warning("Age range mismatch detected for collection: %s (%s), age range: %d-%d"%(collection['id'], collection['name'], collection.get('age_low'), collection.get('age_high')))
elif 'age_high' in collection and collection['age_high'] < 0:
log.warning("Age range mismatch detected for collection: %s (%s), age range: %d-%d"%(collection['id'], collection['name'], collection.get('age_low'), collection.get('age_high')))
else:
if 'age_low' in collection and 'age_high' in collection and collection['age_low'] > collection['age_high']:
log.warning("Age range mismatch detected for collection: %s (%s), age range: %d-%d"%(collection['id'], collection['name'], collection.get('age_low'), collection.get('age_high')))
else:
if (('age_low' in collection and collection['age_low'] < age_max ) or ('age_high' in collection and collection['age_high'] < age_max)):
pediatric = True
if 'age_high' in collection and collection['age_high'] < age_max:
pediatricOnly = True
log.debug("Pediatric-only collection detected: %s, age range: %d-%d, diags: %s"%(collection['id'], collection.get('age_low'), collection.get('age_high'), diags + diag_ranges))
if pediatricOnly and obesity:
log.info(f"Pediatric-only collection detected: {collection['id']}, age range: {collection.get('age_low')}-{collection.get('age_high')}, diags: {diags + diag_ranges}")
collectionsPediatricOnlyObesityDiagnosed.append(collection)
biobanksPediatricOnlyObesityDiagnosed.add(biobankId)
if 'size' in collection and isinstance(collection['size'], int):
pediatricOnlyObesitySamplesExplicit += collection['size']
pediatricOnlyObesitySamplesIncOoM += collection['size']
else:
log.info('Adding %d for OoM %d on behalf of %s'%(10**OoM, OoM, collection['id']))
pediatricOnlyObesitySamplesIncOoM += 10 ** OoM
if 'number_of_donors' in collection and isinstance(collection['number_of_donors'], int):
pediatricOnlyObesityDonorsExplicit += collection['number_of_donors']
elif pediatric and obesity:
log.info(f"Pediatric collection detected: {collection['id']}, age range: {collection.get('age_low')}-{collection.get('age_high')}, diags: {diags + diag_ranges}")
collectionsPediatricObesityDiagnosed.append(collection)
biobanksPediatricObesityDiagnosed.add(biobankId)
if 'size' in collection and isinstance(collection['size'], int):
pediatricObesitySamplesExplicit += collection['size']
pediatricObesitySamplesIncOoM += collection['size']
else:
log.info('Adding %d for OoM %d on behalf of %s'%(10**OoM, OoM, collection['id']))
pediatricObesitySamplesIncOoM += 10 ** OoM
if 'number_of_donors' in collection and isinstance(collection['number_of_donors'], int):
pediatricObesityDonorsExplicit += collection['number_of_donors']
elif obesity:
log.info(f"Pediatric-only collection detected: {collection['id']}, age range: {collection.get('age_low')}-{collection.get('age_high')}, diags: {diags + diag_ranges}")
collectionsObesityDiagnosed.append(collection)
biobanksObesityDiagnosed.add(biobankId)
if 'size' in collection and isinstance(collection['size'], int):
obesitySamplesExplicit += collection['size']
obesitySamplesIncOoM += collection['size']
else:
log.info('Adding %d for OoM %d on behalf of %s'%(10**OoM, OoM, collection['id']))
obesitySamplesIncOoM += 10 ** OoM
if 'number_of_donors' in collection and isinstance(collection['number_of_donors'], int):
obesityDonorsExplicit += collection['number_of_donors']
pd_collectionsPediatricOnlyObesityDiagnosed = pd.DataFrame(collectionsPediatricOnlyObesityDiagnosed)
pd_collectionsPediatricObesityDiagnosed = pd.DataFrame(collectionsPediatricObesityDiagnosed)
pd_collectionsObesityDiagnosed = pd.DataFrame(collectionsObesityDiagnosed)
def printCollectionStdout(collectionList: List, headerStr: str):
print(headerStr + " - " + str(len(collectionList)) + " collections")
for collection in collectionList:
biobankId = dir.getCollectionBiobankId(collection['id'])
biobank = dir.getBiobankById(biobankId)
log.info(" Collection: " + collection['id'] + " - " + collection['name'] + ". Parent biobank: " + biobankId + " - " + biobank['name'])
if not args.nostdout:
print("Biobanks/collections totals:")
print("- total of pediatric-only obesity collections with existing samples: %d in %d biobanks" % (
len(collectionsPediatricOnlyObesityDiagnosed), len(biobanksPediatricOnlyObesityDiagnosed)))
print("- total of pediatric-only obesity samples: %d explicit, %d with OoM; donors: %d explicit" % (
pediatricOnlyObesitySamplesExplicit, pediatricOnlyObesitySamplesIncOoM, pediatricOnlyObesityDonorsExplicit))
print("- total of pediatric obesity collections with existing samples: %d in %d biobanks" % (
len(collectionsPediatricObesityDiagnosed), len(biobanksPediatricObesityDiagnosed)))
print("- total of pediatric obesity samples: %d explicit, %d with OoM; donors: %d explicit" % (
pediatricObesitySamplesExplicit, pediatricObesitySamplesIncOoM, pediatricObesityDonorsExplicit))
print("- total of obesity collections with existing samples: %d in %d biobanks" % (
len(collectionsObesityDiagnosed), len(biobanksObesityDiagnosed)))
print("- total of obesity samples: %d explicit, %d with OoM; donors: %d explicit" % (
obesitySamplesExplicit, obesitySamplesIncOoM, obesityDonorsExplicit))
for df in (pd_collectionsPediatricOnlyObesityDiagnosed, pd_collectionsPediatricObesityDiagnosed, pd_collectionsObesityDiagnosed):
pddfutils.tidyCollectionDf(df)
if args.outputXLSX is not None:
log.info("Outputting warnings in Excel file " + args.outputXLSX[0])
writer = pd.ExcelWriter(args.outputXLSX[0], engine='xlsxwriter')
pd_collectionsPediatricOnlyObesityDiagnosed.to_excel(writer, sheet_name='Pediatric-only obesity')
pd_collectionsPediatricObesityDiagnosed.to_excel(writer, sheet_name='Pediatric obesity')
pd_collectionsObesityDiagnosed.to_excel(writer, sheet_name='Obesity')
writer.save()