-
Notifications
You must be signed in to change notification settings - Fork 31
/
openapi_full.yml
1585 lines (1571 loc) · 61.9 KB
/
openapi_full.yml
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
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
openapi: 3.0.3
info:
contact:
email: [email protected]
name: Chunlei Wu
x-id: https://github.com/newgene
x-role: responsible developer
description: Documentation of the MyVariant.info genetic variant query web services. Learn
more about [MyVariant.info](https://docs.myvariant.info/en/latest/index.html)
termsOfService: https://myvariant.info/terms/
title: MyVariant.info API
version: '1.0'
x-translator:
infores: "infores:myvariant-info"
component: KP
team:
- Service Provider
biolink-version: "4.2.2"
servers:
- description: Encrypted Production server
url: https://myvariant.info/v1
x-maturity: production
tags:
- name: variant
- name: query
- name: metadata
- name: translator
- name: biothings
paths:
"/variant/{id}":
get:
description: >-
By default, this will return the complete variant annotation object in JSON format.
See [here](https://docs.myvariant.info/en/latest/doc/variant_annotation_service.html#returned-object)
for an example and [here](https://docs.myvariant.info/en/latest/doc/data.html#variant-object)
for more details. If the input variant ID is not valid, 404 (NOT FOUND) will be returned.
Optionally, you can pass a "fields" parameter to return only the annotation you want
(by filtering returned object fields). "fields" accepts any attributes (a.k.a fields) available
from the object. Multiple attributes should be separated by commas. If an attribute is not
available for a specific variant object, it will be ignored. Note that the attribute names are
case-sensitive.
Just like the variant query service, you can also pass a "callback" parameter to make a JSONP call.
parameters:
## these are provided in the docs https://docs.myvariant.info/en/latest/doc/variant_annotation_service.html
- name: id
description: >-
Retrieve chemical data based on ID - currently the
HGVS-based id using genomic location based on hg19 human genome assembly
in: path
required: true
example: "chr6:g.152708291G>A"
schema:
type: string
- "$ref": "#/components/parameters/fields"
- "$ref": "#/components/parameters/callback"
- "$ref": "#/components/parameters/email"
## this is useful even when it's not noted in the docs
- "$ref": "#/components/parameters/size"
## these are noted in the https://myvariant.info/v1/spec endpoint; commenting out for now
## assembly is unique to MyVariant
# - "$ref": "#/components/parameters/assembly"
# - "$ref": "#/components/parameters/raw"
# - "$ref": "#/components/parameters/rawquery"
# - "$ref": "#/components/parameters/dotfield"
# - "$ref": "#/components/parameters/_sorted"
# - "$ref": "#/components/parameters/always_list"
# - "$ref": "#/components/parameters/allow_null"
# - "$ref": "#/components/parameters/format"
responses:
'200':
## description from https://docs.myvariant.info/en/latest/doc/response_status_codes.html
description: A 200 status code indicates a successful query, and is accompanied by the query response payload.
## commenting out schemas and other status codes for now
# content:
# application/json:
# schema:
# $ref: '#/components/schemas/Chem'
# '404':
# description: A response indicating an unknown chemical ID
tags:
- variant
"/variant":
post:
description: >-
Although making simple GET requests above to our variant query service is sufficient in most use cases,
there are some times you might find it easier to batch query (e.g., retrieving variant annotations for
multiple variants). Fortunately, you can also make batch queries via POST requests when you need to.
parameters:
## these are provided in the docs https://docs.myvariant.info/en/latest/doc/variant_annotation_service.html
- name: ids
description: >-
Required. Accepts multiple HGVS variant ids separated by comma,
e.g., "ids=chr6:g.152708291G>A,chr7:g.55241707G>T,chr16:g.28883241A>G".
Note that currently we only take the input ids up to 1000 maximum, the rest will be omitted.
The request body can also be used to provide these ids.
in: query
## setting to false since putting this info in the request body seems to work as well
required: false
schema:
type: string
- "$ref": "#/components/parameters/fields"
- "$ref": "#/components/parameters/email"
## this is useful even when it's not noted in the docs
- "$ref": "#/components/parameters/size"
## these are noted in the https://myvariant.info/v1/spec endpoint; commenting out for now
## assembly is unique to MyVariant
# - "$ref": "#/components/parameters/assembly"
# - "$ref": "#/components/parameters/raw"
# - "$ref": "#/components/parameters/rawquery"
# - "$ref": "#/components/parameters/dotfield"
# - "$ref": "#/components/parameters/_sorted"
# - "$ref": "#/components/parameters/always_list"
# - "$ref": "#/components/parameters/allow_null"
# - "$ref": "#/components/parameters/format"
requestBody:
content:
application/json:
example:
ids:
- "chr6:g.152708291G>A"
- "chr7:g.55241707G>T"
schema:
type: object
properties:
ids:
description: >-
Accepts multiple variant ids. Note that currently we only take the input ids
up to 1000 maximum, the rest will be omitted.
type: array
items:
type: string
responses:
'200':
description: A 200 status code indicates a successful query, and is accompanied by the query response payload.
tags:
- variant
"/metadata":
get:
description: Get metadata about the data available from the API
## these are noted in the hhttps://myvariant.info/v1/spec endpoint; commenting out for now
# parameters:
# - "$ref": "#/components/parameters/format"
# - "$ref": "#/components/parameters/raw"
responses:
'200':
description: A 200 status code indicates a successful query, and is accompanied by the query response payload.
tags:
- metadata
"/metadata/fields":
get:
description: Get metadata about the data fields available from the API
## these are noted in the hhttps://myvariant.info/v1/spec endpoint; commenting out for now
# parameters:
# - "$ref": "#/components/parameters/format"
# - "$ref": "#/components/parameters/raw"
# - "$ref": "#/components/parameters/search"
# - "$ref": "#/components/parameters/prefix"
responses:
'200':
description: A 200 status code indicates a successful query, and is accompanied by the query response payload.
tags:
- metadata
"/query":
get:
description: >-
MyChem.info chemical query web service. In the output, "total" in the output gives the total number
of matching hits, while the actual hits are returned under "hits" field.
parameters:
- name: q
## description partially from https://docs.myvariant.info/en/latest/doc/variant_query_service.html#query-syntax
description: >-
Required, passing user query. The detailed query syntax for parameter is explained
[here](https://docs.myvariant.info/en/latest/doc/variant_query_service.html#query-syntax).
in: query
required: true
example: "rs58991260"
schema:
type: string
- "$ref": "#/components/parameters/fields"
- "$ref": "#/components/parameters/size"
- "$ref": "#/components/parameters/from"
- "$ref": "#/components/parameters/fetch_all"
- "$ref": "#/components/parameters/scroll_id"
- "$ref": "#/components/parameters/sort"
- "$ref": "#/components/parameters/facets"
- "$ref": "#/components/parameters/facet_size"
- "$ref": "#/components/parameters/callback"
- "$ref": "#/components/parameters/dotfield"
- "$ref": "#/components/parameters/email"
## these are noted in the https://myvariant.info/v1/spec endpoint; commenting out for now
## assembly is unique to MyVariant
# - "$ref": "#/components/parameters/assembly"
# - "$ref": "#/components/parameters/aggs"
# - "$ref": "#/components/parameters/userquery"
# - "$ref": "#/components/parameters/explain"
# - "$ref": "#/components/parameters/raw"
# - "$ref": "#/components/parameters/rawquery"
# - "$ref": "#/components/parameters/_sorted"
# - "$ref": "#/components/parameters/always_list"
# - "$ref": "#/components/parameters/allow_null"
# - "$ref": "#/components/parameters/format"
responses:
'200':
description: A 200 status code indicates a successful query, and is accompanied by the query response payload.
## commenting out schemas and other status codes for now
# content:
# application/json:
# schema:
# "$ref": "#/components/schemas/QueryResult"
# '400':
# content:
# application/json:
# schema:
# "$ref": "#/components/schemas/ErrorResult"
# description: A response indicating an improperly formatted query
# description: Make queries and return matching gene hits. Supports JSONP and CORS
# as well.
tags:
- query
post:
description: >-
Although making simple GET requests above to our variant query service is sufficient for most use cases,
there are times you might find it more efficient to make batch queries (e.g., retrieving variant annotation
for multiple variants). Fortunately, you can also make batch queries via POST requests when you need to.
The "query" field in the returned object indicates the matching query term. If a query term has no match,
it will return with a "notfound" field with the value "true".
parameters:
## these are provided in the docs https://docs.myvariant.info/en/latest/doc/variant_query_service.html#id2
- name: q
description: >-
Accepts multiple values separated by commas. Note that currently we only take the input values up to 1000
maximum, the rest will be omitted.
The request body can also be used to provide these ids.
in: query
## setting to false since putting this info in the request body seems to work as well
required: false
schema:
type: array
items:
type: string
- name: scopes
description: >-
Optional, specify one or more fields (separated by commas) to search, e.g., "scopes=dbsnp.rsid".
The available "fields" can be passed to "scopes" parameter are listed
[here](https://docs.myvariant.info/en/latest/doc/data.html#available-fields). Default: _id
The request body can also be used to provide this information.
in: query
## setting to false since putting this info in the request body seems to work as well
required: false
schema:
type: string
- "$ref": "#/components/parameters/fields"
- "$ref": "#/components/parameters/email"
## this is useful even when it's not noted in the docs
- "$ref": "#/components/parameters/size"
- "$ref": "#/components/parameters/from"
- "$ref": "#/components/parameters/fetch_all"
- "$ref": "#/components/parameters/scroll_id"
## these are noted in the https://myvariant.info/v1/spec endpoint; commenting out for now
## assembly is unique to MyVariant
## others haven't been written down here: with_total, analyzer
# - "$ref": "#/components/parameters/assembly"
# - "$ref": "#/components/parameters/sort"
# - "$ref": "#/components/parameters/raw"
# - "$ref": "#/components/parameters/rawquery"
# - "$ref": "#/components/parameters/dotfield"
# - "$ref": "#/components/parameters/_sorted"
# - "$ref": "#/components/parameters/always_list"
# - "$ref": "#/components/parameters/allow_null"
# - "$ref": "#/components/parameters/format"
requestBody:
content:
application/json:
example:
q:
- "rs58991260"
- "rs928128624"
scopes:
- "dbsnp.rsid"
schema:
type: object
properties:
q:
description: >-
Accepts multiple values separated by commas. Note that currently we only take the input values
up to 1000 maximum, the rest will be omitted.
type: array
items:
type: string
scopes:
description: >-
Specify one or more fields (separated by commas) to search, e.g., "scopes=dbsnp.rsid".
The available "fields" can be passed to "scopes" parameter are listed
[here](https://docs.myvariant.info/en/latest/doc/data.html#available-fields). Default: _id
type: array
items:
type: string
responses:
'200':
description: A 200 status code indicates a successful query, and is accompanied by the query response payload.
## commenting out schemas and other status codes for now
# content:
# application/json:
# schema:
# "$ref": "#/components/schemas/QueryPOSTResult"
# '400':
# content:
# application/json:
# schema:
# "$ref": "#/components/schemas/ErrorResult"
# description: A response indicating an improperly formatted query
# description: Make batch gene queries and return matching gene hits
tags:
- query
## 32 operations (16 sets)
x-bte-kgs-operations:
- "$ref": "#/components/x-bte-kgs-operations/civic-geneDisease"
- "$ref": "#/components/x-bte-kgs-operations/civic-geneDisease-rev"
- "$ref": "#/components/x-bte-kgs-operations/civic-variantDisease"
- "$ref": "#/components/x-bte-kgs-operations/civic-variantDisease-rev"
- "$ref": "#/components/x-bte-kgs-operations/dbsnp-variantGene"
- "$ref": "#/components/x-bte-kgs-operations/dbsnp-variantGene-rev"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variantGene"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variantGene-rev"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-gene-diseaseOMIM"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-gene-diseaseORPHANET"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-gene-diseaseMONDO"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-gene-diseaseMESH"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-gene-phenoHP"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-gene-diseaseOMIM-rev"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-gene-diseaseORPHANET-rev"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-gene-diseaseMONDO-rev"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-gene-diseaseMESH-rev"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-gene-phenoHP-rev"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variant-diseaseOMIM"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variant-diseaseORPHANET"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variant-diseaseMONDO"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variant-diseaseMESH"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variant-phenoHP"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variant-diseaseOMIM-rev"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variant-diseaseORPHANET-rev"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variant-diseaseMONDO-rev"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variant-diseaseMESH-rev"
- "$ref": "#/components/x-bte-kgs-operations/clinvar-variant-phenoHP-rev"
components:
parameters:
## assembly is specific to MyVariant
assembly:
name: assembly
in: query
required: false
schema:
type: string
default: hg19
callback:
name: callback
description: >-
Optional, you can pass a "callback" parameter to make a JSONP call.
in: query
required: false
schema:
type: string
dotfield:
name: dotfield
description: >-
Optional, can be used to control the format of the returned object.
If "dotfield" is true, the returned data object is returned flattened (no nested objects)
using dotfield notation for key names. Default: false.
in: query
required: false
schema:
type: boolean
default: false
email:
name: email
description: >-
Optional, if you are regular users of our services, we encourage you to provide us an email,
so that we can better track the usage or follow up with you.
in: query
required: false
schema:
type: string
facet_size:
name: facet_size
description: >-
Optional, an integer (1 <= facet_size <= 1000) that specifies how many buckets to return in a
[faceted query](https://docs.mychem.info/en/latest/doc/chem_query_service.html?highlight=from#faceted-queries).
in: query
required: false
schema:
type: integer
default: 10
facets:
name: facets
description: >-
Optional, a single field or comma-separated fields to return facets, can only be used on non-free text fields.
E.g. "facets=chembl.molecule_properties.full_mwt". See [examples of faceted queries
here](https://docs.mychem.info/en/latest/doc/chem_query_service.html?highlight=from#faceted-queries).
in: query
required: false
schema:
type: array
items:
type: string
fetch_all:
name: fetch_all
description: >-
Optional, a boolean, which when TRUE, allows fast retrieval of all unsorted query hits.
The return object contains a _scroll_id field, which when passed as a parameter to the query endpoint
(see the scroll_id parameter), returns the next 1000 query results. Setting fetch_all = TRUE causes
the results to be inherently unsorted, therefore the sort parameter is ignored. For more information,
see [examples using fetch_all
here](https://docs.mychem.info/en/latest/doc/chem_query_service.html?highlight=from#scrolling-queries).
Default: FALSE.
in: query
required: false
schema:
type: boolean
default: false
fields:
name: fields
description: >-
Optional, can be a comma-separated list to limit the fields returned from the object.
If "fields=all", all available fields will be returned. Look
[here](https://docs.mychem.info/en/latest/doc/data.html#available-fields) for a list of available fields.
Note that it supports dot notation as well, e.g., you can pass "chebi.name".
Default: "fields=all".
The parameter "filter" is an alias for this parameter.
in: query
required: false
schema:
type: string
default: all
from:
name: from
description: >-
Optional, the number of matching hits to skip, starting from 0. Default: 0.
in: query
required: false
schema:
type: integer
default: 0
scroll_id:
name: scroll_id
description: >-
Optional, a string containing the _scroll_id returned from a query request with fetch_all = TRUE.
Supplying a valid scroll_id will return the next 1000 unordered results. If the next results are
not obtained within 1 minute of the previous set of results, the scroll_id becomes stale, and a
new one must be obtained with another query request with fetch_all = TRUE. All other parameters are
ignored when the scroll_id parameter is supplied. For more information see [examples using scroll_id
here](https://docs.mychem.info/en/latest/doc/chem_query_service.html?highlight=from#scrolling-queries).
in: query
required: false
schema:
type: string
size:
name: size
description: >-
Optional, the maximum number of matching hits to return (with a cap of 1000 at the moment). Default: 10.
The combination of "size" and "from" parameters can be used to get paging for a large query.
in: query
required: false
schema:
type: integer
default: 10
sort:
name: sort
description: >-
Optional, the comma-separated fields to sort on. Prefix with "-" for descending order, otherwise in ascending order.
Default: sort by matching scores in descending order.
in: query
required: false
schema:
type: array
items:
type: string
## these are noted in the https://mychem.info/v1/spec endpoint; commenting out for now
# _sorted:
# name: _sorted
# in: query
# required: false
# schema:
# type: boolean
# default: true
# aggs:
# name: aggs
# in: query
# required: false
# schema:
# type: array
# items:
# type: string
# allow_null:
# name: allow_null
# in: query
# required: false
# schema:
# type: array
# items:
# type: string
# always_list:
# name: always_list
# in: query
# required: false
# schema:
# type: array
# items:
# type: string
# explain:
# name: explain
# in: query
# required: false
# schema:
# type: boolean
# format:
# name: format
# description: 'controls output format of server response, currently supports:
# "json", "jsonld", "html". Type: string. Default: json.'
# in: query
# required: false
# schema:
# type: string
# default: json
# prefix:
# name: prefix
# in: query
# required: false
# schema:
# type: string
# raw:
# name: raw
# in: query
# required: false
# schema:
# type: boolean
# rawquery:
# name: rawquery
# in: query
# required: false
# schema:
# type: boolean
# search:
# name: search
# in: query
# required: false
# schema:
# type: string
# userquery:
# name: userquery
# in: query
# required: false
# schema:
# type: string
## commenting out schemas and other status codes for now
# schemas:
# Chem:
# properties:
# _id:
# type: string
# required:
# - _id
# type: object
# ErrorResult:
# properties:
# message:
# type: string
# success:
# type: boolean
# type: object
# QueryPOSTResult:
# items:
# allOf:
# - "$ref": "#/components/schemas/Chem"
# - properties:
# _score:
# format: float
# type: number
# query:
# type: string
# type: object
# type: array
# QueryResult:
# properties:
# hits:
# items:
# "$ref": "#/components/schemas/Chem"
# type: array
# max_score:
# format: float
# type: number
# took:
# type: integer
# total:
# type: integer
# type: object
# int64_or_array:
# oneOf:
# - items:
# format: int64
# type: integer
# type: array
# - format: int64
# type: integer
# string_or_array:
# oneOf:
# - items:
# type: string
# type: array
# - type: string
x-bte-response-mapping:
civic-geneDisease:
DOID: civic.evidence_items.disease.doid
ref_pmid: civic.evidence_items.source.pubmed ## no prefix
ref_clinicaltrials: civic.evidence_items.source.clinical_trials.nct_id ## no prefix (ID starts with "NCT")
## commenting out because data-processing / biolink-modeling issues
# ## categorical var / relation
# civic_clinical_significance: civic.evidence_items.clinical_significance
# ## free text
# civic_description: civic.evidence_items.description
# ## context: drugs involved
# civic_drug_interaction: civic.evidence_items.drug_interaction_type
# civic_drugs_involved: civic.evidence_items.drugs.name
# ## categorical vars
# civic_evidence_direction: civic.evidence_items.evidence_direction
# civic_evidence_level: civic.evidence_items.evidence_level
# civic_evidence_type: civic.evidence_items.evidence_type
# ## context: variant involved, could use "biolink:sequence_variant_qualifier"
# ## but then ID-namespace would be unclear (this ID doesn't have a prefix)
# civic_variant_id: civic.evidence_items.variant_id
# ## context: variant involved was Somatic, unknown...
# civic_variant_origin: civic.evidence_items.variant_origin
civic-geneOnly:
NCBIGene: civic.entrez_id
civic-variantDisease:
DOID: civic.evidence_items.disease.doid
## variant name
input_name: _id
ref_pmid: civic.evidence_items.source.pubmed ## no prefix
ref_clinicaltrials: civic.evidence_items.source.clinical_trials.nct_id ## no prefix (ID starts with "NCT")
## commenting out because data-processing / biolink-modeling issues
# ## categorical var / relation
# civic_clinical_significance: civic.evidence_items.clinical_significance
# ## free text
# civic_description: civic.evidence_items.description
# ## context: gene involved
# civic_variant_in_gene: civic.entrez_name
# ## context: drugs involved
# civic_drug_interaction: civic.evidence_items.drug_interaction_type
# civic_drugs_involved: civic.evidence_items.drugs.name
# ## categorical vars
# civic_evidence_direction: civic.evidence_items.evidence_direction
# civic_evidence_level: civic.evidence_items.evidence_level
# civic_evidence_type: civic.evidence_items.evidence_type
# ## context: variant involved was Somatic, unknown...
# civic_variant_origin: civic.evidence_items.variant_origin
dbsnp-rsid:
DBSNP: dbsnp.rsid ## no prefix
output_name: _id ## variant name
dbsnp-gene:
NCBIGene: dbsnp.gene.geneid ## no prefix
input_name: _id ## variant name
clinvar-rsid:
DBSNP: clinvar.rsid ## no prefix
output_name: _id ## variant name
clinvar-diseaseOMIM:
OMIM: clinvar.rcv.conditions.identifiers.omim ## no prefix
input_name: clinvar.gene.symbol ## Node Norm doesn't recognize all NCBIGene IDs
## commenting out because data-processing / biolink-modeling issues
# ## edge attributes
# clinvar_clinical_significance: clinvar.rcv.clinical_significance ## similar to relation
# variant_rsid: dbsnp.rsid ## no prefix
# clinvar_submission_last_evaluated: clinvar.rcv.last_evaluated ## gives a date yyyy-mm-dd
# clinvar_num_submitters: clinvar.rcv.number_submitters
# clinvar_variant_origin: clinvar.rcv.origin
# clinvar_review_status: clinvar.rcv.review_status
clinvar-diseaseORPHANET:
ORPHANET: clinvar.rcv.conditions.identifiers.orphanet ## no prefix
input_name: clinvar.gene.symbol
clinvar-diseaseMONDO:
MONDO: clinvar.rcv.conditions.identifiers.mondo ## HAS PREFIX (MONDO)
input_name: clinvar.gene.symbol
clinvar-diseaseMESH:
MESH: clinvar.rcv.conditions.identifiers.mesh ## no prefix
input_name: clinvar.gene.symbol
clinvar-phenoHP:
HP: clinvar.rcv.conditions.identifiers.human_phenotype_ontology ## HAS PREFIX
input_name: clinvar.gene.symbol
clinvar-gene-variant-start:
NCBIGene: clinvar.gene.id ## no prefix
input_name: _id ## variant name
clinvar-variantDiseaseOMIM:
OMIM: clinvar.rcv.conditions.identifiers.omim ## no prefix
input_name: _id ## variant name
## commenting out because data-processing / biolink-modeling issues
# ## edge attributes
# clinvar_clinical_significance: clinvar.rcv.clinical_significance ## similar to relation
# clinvar_variant_in_gene: clinvar.gene.symbol ## context: gene
# clinvar_submission_last_evaluated: clinvar.rcv.last_evaluated ## gives a date yyyy-mm-dd
# clinvar_num_submitters: clinvar.rcv.number_submitters
# clinvar_variant_origin: clinvar.rcv.origin
# clinvar_review_status: clinvar.rcv.review_status
clinvar-variantDiseaseORPHANET:
ORPHANET: clinvar.rcv.conditions.identifiers.orphanet ## no prefix
input_name: _id ## variant name
clinvar-variantDiseaseMONDO:
MONDO: clinvar.rcv.conditions.identifiers.mondo ## HAS PREFIX
input_name: _id ## variant name
clinvar-variantDiseaseMESH:
MESH: clinvar.rcv.conditions.identifiers.mesh ## no prefix
input_name: _id ## variant name
clinvar-variantPhenoHP:
HP: clinvar.rcv.conditions.identifiers.human_phenotype_ontology ## HAS PREFIX
input_name: _id ## variant name
clinvar-gene:
NCBIGene: clinvar.gene.id ## no prefix
output_name: clinvar.gene.symbol ## Node Norm doesn't recognize all NCBIGene IDs
## not included:
## - cgi: only 323 records, doesn't have IDs for disease, gene, or drug ID...
## - cosmic: only seems to connect variants to tissue they were found in, but no IDs for the tissue...
## - dbnsfp.clinvar: overlap with clinvar section?
## missing indexing for omim, orphanet IDs have ORPHA000 format...
## - dbnsfp.ensembl.geneid: very repetitive for some reason...
## - dbnsfp.gtex.tissue: string, no IDs...
## - docm: Chunlei said not to annotate this data. It's a very old tool doing variant impact prediction
## - grasp.publication.phenotype: looks like curation of publications for variants / phenotypes. string, no IDs...
## - gwassnps.trait: looks like curation of publications for variants / phenotypes. string, no IDs...
x-bte-kgs-operations:
## CIVIC:
## knowledge_level / agent_type: appears to be heavily manually-curated
## see https://www.nature.com/articles/ng.3774 (and website https://civicdb.org/)
## data seems to be connecting variant-disease, sometimes with a drug (although that drug may not have an ID)
## having a drug means looking at drug response (given the disease...)
## However, the civic variant IDs don't seem to be easily mapped...
## The variants are mapped to their genes: 2648 records total, all have entrez_id field...
## - not including
## - civic assertions (only 30 variant records https://myvariant.info/v1/query?q=_exists_:%22civic.assertions%22)
## - civic evidence_items.phenotypes: 598 records, some seem to repeat the disease info
## - civic variant_groups: 129 records, not clear how to structure / what the relationship is
## civic data currently not in hg38:
## https://myvariant.info/v1/metadata/fields?assembly=hg38
## https://docs.myvariant.info/en/latest/doc/data.html?highlight=hg19#data-sources
civic-geneDisease:
- supportBatch: true
useTemplating: true
inputs:
- id: NCBIGene
semantic: Gene
requestBody:
body:
q: "{{ queryInputs }}" ## no prefix
scopes: civic.entrez_id
outputs:
- id: DOID
semantic: Disease
## out of 2648 civic records, most (2610) have the doid disease field...only some have dbsnp.rsid...
parameters:
## most fields below are categorical variables
## description is free text, Disease ID has prefix (DOID), variant ID is CIVIC (no prefix)
## only some records have drug information, and only some drugs have NCIT IDs
## commenting out because data-processing / biolink-modeling issues
# fields: civic.evidence_items
fields: >-
civic.evidence_items.disease.doid,
civic.evidence_items.source.pubmed,
civic.evidence_items.source.clinical_trials.nct_id
size: 1000 ## note size limit; added just in case
assembly: hg19
predicate: affects
source: "infores:civic"
knowledge_level: knowledge_assertion
agent_type: manual_agent
response_mapping:
"$ref": "#/components/x-bte-response-mapping/civic-geneDisease"
## this record has drug interaction: https://myvariant.info/v1/query?q=_exists_:%22civic.evidence_items.drug_interaction_type%22
testExamples:
- qInput: "NCBIGene:1956" ## EGFR
oneOutput: "DOID:3910" ## Lung Adenocarcinoma aka MONDO:0005061
civic-geneDisease-rev:
- supportBatch: true
useTemplating: true
inputs:
- id: DOID
semantic: Disease
requestBody:
body:
q: "{{ queryInputs }}" ## HAS PREFIX
scopes: civic.evidence_items.disease.doid
outputs:
- id: NCBIGene
semantic: Gene
parameters:
fields: civic.entrez_id ## no prefix
size: 1000
assembly: hg19
predicate: affected_by
source: "infores:civic"
knowledge_level: knowledge_assertion
agent_type: manual_agent
response_mapping:
"$ref": "#/components/x-bte-response-mapping/civic-geneOnly"
## this record has drug interaction: https://myvariant.info/v1/query?q=_exists_:%22civic.evidence_items.drug_interaction_type%22
testExamples:
- qInput: "DOID:9256" ## Colorectal Cancer aka MONDO:0005575
oneOutput: "NCBIGene:5290" ## PIK3CA
civic-variantDisease:
## out of 2648 civic records, only some (653) have the doid disease field...
- supportBatch: true
useTemplating: true
inputs:
- id: DBSNP
semantic: SequenceVariant
requestBody:
body:
q: "{{ queryInputs }}" ## no prefix
scopes: dbsnp.rsid
outputs:
- id: DOID
semantic: Disease
parameters:
## most fields below are categorical variables
## description is free text, Disease ID has prefix (DOID), variant ID is CIVIC (no prefix)
## only some records have drug information, and only some drugs have NCIT IDs
## using entrez gene name for now (human-readable) rather than id
## commenting out because data-processing / biolink-modeling issues
# fields: >-
# civic.evidence_items,
# civic.entrez_name,
# _id
fields: >-
civic.evidence_items.disease.doid,
_id,
civic.evidence_items.source.pubmed,
civic.evidence_items.source.clinical_trials.nct_id
size: 1000 ## note size limit; added just in case
assembly: hg19
predicate: affects
source: "infores:civic"
knowledge_level: knowledge_assertion
agent_type: manual_agent
response_mapping:
"$ref": "#/components/x-bte-response-mapping/civic-variantDisease"
## this record has drug interaction: https://myvariant.info/v1/query?q=_exists_:%22civic.evidence_items.drug_interaction_type%22%20AND%20_exists_:%22dbsnp.rsid%22
testExamples:
- qInput: "DBSNP:rs121913521" ## chr4:g.55593613T>G in KIT
oneOutput: "DOID:9253" ## Gastrointestinal Stromal Tumor aka MONDO:0011719
civic-variantDisease-rev:
- supportBatch: true
useTemplating: true
inputs:
- id: DOID
semantic: Disease
requestBody:
body:
q: "{{ queryInputs }}" ## HAS PREFIX
scopes: civic.evidence_items.disease.doid
outputs:
- id: DBSNP
semantic: SequenceVariant
parameters:
fields: dbsnp.rsid,_id
size: 1000 ## note size limit; added just in case
assembly: hg19
predicate: affected_by
source: "infores:civic"
knowledge_level: knowledge_assertion
agent_type: manual_agent
response_mapping:
"$ref": "#/components/x-bte-response-mapping/dbsnp-rsid"
## this record has drug interaction: https://myvariant.info/v1/query?q=_exists_:%22civic.evidence_items.drug_interaction_type%22%20AND%20_exists_:%22dbsnp.rsid%22
testExamples:
- qInput: "DOID:2671" ## Transitional Cell Carcinoma aka MONDO:0006474
oneOutput: "DBSNP:rs1057519803" ## chr12:g.56481922G>A in ERBB3
dbsnp-variantGene:
## knowledge_level / agent_type: gene assignments seem to happen in automated build process
## https://www.ncbi.nlm.nih.gov/books/NBK21088/#_ch5_ch5_s4_
## note: there may be redundant results in the response
## there are 741 million records for hg38
- supportBatch: true
useTemplating: true
inputs:
- id: DBSNP
semantic: SequenceVariant
requestBody:
body:
q: "{{ queryInputs }}" ## no prefix
scopes: dbsnp.rsid
outputs:
- id: NCBIGene
semantic: Gene
parameters:
fields: dbsnp.gene.geneid,_id ## no prefix
size: 1000
assembly: hg38
predicate: is_sequence_variant_of
source: "infores:dbsnp"
knowledge_level: knowledge_assertion
agent_type: automated_agent
response_mapping:
"$ref": "#/components/x-bte-response-mapping/dbsnp-gene"
## https://myvariant.info/v1/query?q=_exists_:%22dbsnp.rsid%22%20AND%20_exists_:%22dbsnp.gene.geneid%22&fields=dbsnp&assembly=hg38
testExamples:
- qInput: "DBSNP:rs770112667" ## chr10:g.14218676G>A (diff for hg19)
oneOutput: "NCBIGene:55691" ## FRMD4A
dbsnp-variantGene-rev:
- supportBatch: true
useTemplating: true
inputs:
- id: NCBIGene
semantic: Gene
requestBody:
body:
q: "{{ queryInputs }}" ## no prefix
scopes: dbsnp.gene.geneid
outputs:
- id: DBSNP
semantic: SequenceVariant
parameters:
fields: dbsnp.rsid,_id
size: 1000
assembly: hg38
predicate: has_sequence_variant
source: "infores:dbsnp"
knowledge_level: knowledge_assertion
agent_type: automated_agent
response_mapping:
"$ref": "#/components/x-bte-response-mapping/dbsnp-rsid"
## https://myvariant.info/v1/query?q=_exists_:%22dbsnp.rsid%22%20AND%20_exists_:%22dbsnp.gene.geneid%22
testExamples:
- qInput: "NCBIGene:102724392" ## LINC02197
oneOutput: "DBSNP:rs188861200" ## chr5:g.71414410C>T (diff for hg19)
## CLINVAR
## knowledge_level / agent_type: data going in seems to be manually-curated
## https://www.ncbi.nlm.nih.gov/clinvar/docs/datasources/
clinvar-variantGene:
## possibly redundant, with all hg38 clinvar data already covered by hg38 dbsnp.rsid <-> gene...
## > 822k records for hg38
- supportBatch: true
useTemplating: true
inputs:
- id: DBSNP
semantic: SequenceVariant
requestBody:
body:
q: "{{ queryInputs }}" ## no prefix
scopes: clinvar.rsid
outputs:
- id: NCBIGene
semantic: Gene
parameters:
fields: clinvar.gene.id,_id ## no prefix
size: 1000
assembly: hg38
predicate: is_sequence_variant_of
source: "infores:clinvar"
knowledge_level: knowledge_assertion
agent_type: manual_agent
response_mapping:
"$ref": "#/components/x-bte-response-mapping/clinvar-gene-variant-start"
testExamples:
- qInput: "DBSNP:rs794727661" ## chrX:g.32343175_32343176dup (diff for hg19)
oneOutput: "NCBIGene:1756" ## DMD
clinvar-variantGene-rev:
- supportBatch: true
useTemplating: true
inputs:
- id: NCBIGene
semantic: Gene
requestBody:
body:
q: "{{ queryInputs }}" ## no prefix
scopes: clinvar.gene.id
outputs:
- id: DBSNP
semantic: SequenceVariant
parameters:
fields: clinvar.rsid,_id ## no prefix
size: 1000
assembly: hg38
predicate: has_sequence_variant
source: "infores:clinvar"
knowledge_level: knowledge_assertion
agent_type: manual_agent
response_mapping:
"$ref": "#/components/x-bte-response-mapping/clinvar-rsid"
testExamples:
- qInput: "NCBIGene:9231" ## DLG5