/
allEndpoints.R
2278 lines (2231 loc) · 90.4 KB
/
allEndpoints.R
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
#' Retrieve a single analysis result set by its identifier
#'
#'
#'
#' @param resultSet An expression analysis result set numerical identifier.
#' @param raw \code{TRUE} to receive results as-is from Gemma, or \code{FALSE} to enable
#' parsing. Raw results usually contain additional fields and flags that are
#' omitted in the parsed results.
#' @param memoised Whether or not to save to cache for future calls with the
#' same inputs and use the result saved in cache if a result is already saved.
#' Doing \code{options(gemma.memoised = TRUE)} will ensure that the cache is always
#' used. Use \code{\link{forget_gemma_memoised}} to clear the cache.
#' @param file The name of a file to save the results to, or \code{NULL} to not write
#' results to a file. If \code{raw == TRUE}, the output will be the raw endpoint from the
#' API, likely a JSON or a gzip file. Otherwise, it will be a RDS file.
#' @param overwrite Whether or not to overwrite if a file exists at the specified
#' filename.
#'
#' @return Varies
#' @keywords internal
#'
#' @examples
#' # gemma.R:::.getResultSets(523099)
.getResultSets <- function(resultSet = NA_character_, raw = getOption(
"gemma.raw",
FALSE
), memoised = getOption("gemma.memoised", FALSE), file = getOption(
"gemma.file",
NA_character_
), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
open_api_name <- "get_result_set"
internal <- TRUE
header <- "text/tab-separated-values"
isFile <- TRUE
fname <- ".getResultSets"
preprocessor <- processFile
validators <- list(resultSet = validateOptionalID)
endpoint <- "resultSets/{encode(resultSet)}"
if (memoised) {
if (!is.na(file)) {
warning("Saving to files is not supported with memoisation.")
}
if ("character" %in% class(gemmaCache()) && gemmaCache() ==
"cache_in_memory") {
return(mem_in_memory_cache(".getResultSets",
resultSet = resultSet,
raw = raw, memoised = FALSE, file = file, overwrite = overwrite
))
} else {
out <- mem.getResultSets(
resultSet = resultSet, raw = raw,
memoised = FALSE, file = file, overwrite = overwrite
)
return(out)
}
}
.body(
fname = fname, validators = validators, endpoint = endpoint,
envWhere = environment(), isFile = isFile, header = header,
raw = raw, overwrite = overwrite, file = file, attributes = TRUE,
open_api_name = open_api_name, .call = match.call()
)
}
#' Memoise .getResultSets
#'
#' @noRd
mem.getResultSets <- function(resultSet = NA_character_, raw = getOption(
"gemma.raw",
FALSE
), memoised = getOption("gemma.memoised", FALSE), file = getOption(
"gemma.file",
NA_character_
), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
mem_call <- memoise::memoise(.getResultSets, cache = gemmaCache())
mem_call(
resultSet = resultSet, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
)
}
#' Retrieve all result sets matching the provided criteria
#'
#' Returns queried result set
#'
#' @details Output and usage of this function is mostly identical to \code{\link{get_dataset_differential_expression_analyses}}.
#' The principal difference being the ability to restrict your result sets, being able to
#' query across multiple datasets and being able to use the filter argument
#' to search based on result set properties.
#'
#' @param datasets A numerical dataset identifier or a dataset short name
#' @param resultSets A resultSet identifier. Note that result set identifiers
#' are not static and can change when Gemma re-runs analyses internally. Whem
#' using these as inputs, try to make sure you access a currently existing
#' result set ID by basing them on result sets returned for a particular dataset or
#' filter used in \code{\link{get_result_sets}}
#' @param filter Filter results by matching expression. Use \code{\link{filter_properties}}
#' function to get a list of all available parameters. These properties can be
#' combined using "and" "or" clauses and may contain common operators such as "=", "<" or "in".
#' (e.g. "taxon.commonName = human", "taxon.commonName in (human,mouse), "id < 1000")
#' @param offset The offset of the first retrieved result.
#' @param limit Defaults to 20. Limits the result to specified amount
#' of objects. Has a maximum value of 100. Use together with \code{offset} and
#' the \code{totalElements} \link[base:attributes]{attribute} in the output to
#' compile all data if needed.
#' @param sort Order results by the given property and direction. The '+' sign
#' indicate ascending order whereas the '-' indicate descending.
#' @param raw \code{TRUE} to receive results as-is from Gemma, or \code{FALSE} to enable
#' parsing. Raw results usually contain additional fields and flags that are
#' omitted in the parsed results.
#' @param memoised Whether or not to save to cache for future calls with the
#' same inputs and use the result saved in cache if a result is already saved.
#' Doing \code{options(gemma.memoised = TRUE)} will ensure that the cache is always
#' used. Use \code{\link{forget_gemma_memoised}} to clear the cache.
#' @param file The name of a file to save the results to, or \code{NULL} to not write
#' results to a file. If \code{raw == TRUE}, the output will be the raw endpoint from the
#' API, likely a JSON or a gzip file. Otherwise, it will be a RDS file.
#' @param overwrite Whether or not to overwrite if a file exists at the specified
#' filename.
#'
#' @inherit processDifferentialExpressionAnalysisResultSetValueObject return
#' @export
#'
#' @keywords misc
#'
#' @examples
#' get_result_sets(dataset = 1)
#' # get all contrasts comparing disease states. use filter_properties to see avaialble options
#' get_result_sets(filter = "baselineGroup.characteristics.value = disease")
get_result_sets <- function(datasets = NA_character_, resultSets = NA_character_,
filter = NA_character_, offset = 0, limit = 20, sort = "+id",
raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_),
overwrite = getOption("gemma.overwrite", FALSE)) {
open_api_name <- "get_result_sets"
internal <- FALSE
keyword <- "misc"
header <- ""
isFile <- FALSE
fname <- "get_result_sets"
preprocessor <- processDifferentialExpressionAnalysisResultSetValueObject
validators <- list(
datasets = validateOptionalID, resultSets = validateOptionalID,
filter = validateFilter, offset = validatePositiveInteger,
limit = validateLimit, sort = validateSort
)
endpoint <- "resultSets?datasets={encode(datasets)}&filter={encode(filter)}&offset={encode(offset)}&limit={encode(limit)}&sort={encode(sort)}"
if (memoised) {
if (!is.na(file)) {
warning("Saving to files is not supported with memoisation.")
}
if ("character" %in% class(gemmaCache()) && gemmaCache() ==
"cache_in_memory") {
return(mem_in_memory_cache("get_result_sets",
datasets = datasets,
resultSets = resultSets, filter = filter, offset = offset,
limit = limit, sort = sort, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
))
} else {
out <- memget_result_sets(
datasets = datasets, resultSets = resultSets,
filter = filter, offset = offset, limit = limit,
sort = sort, raw = raw, memoised = FALSE, file = file,
overwrite = overwrite
)
return(out)
}
}
.body(
fname = fname, validators = validators, endpoint = endpoint,
envWhere = environment(), isFile = isFile, header = header,
raw = raw, overwrite = overwrite, file = file, attributes = TRUE,
open_api_name = open_api_name, .call = match.call()
)
}
#' Memoise get_result_sets
#'
#' @noRd
memget_result_sets <- function(datasets = NA_character_, resultSets = NA_character_,
filter = NA_character_, offset = 0, limit = 20, sort = "+id",
raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_),
overwrite = getOption("gemma.overwrite", FALSE)) {
mem_call <- memoise::memoise(get_result_sets, cache = gemmaCache())
mem_call(
datasets = datasets, resultSets = resultSets, filter = filter,
offset = offset, limit = limit, sort = sort, raw = raw,
memoised = FALSE, file = file, overwrite = overwrite
)
}
#' Search for annotation tags
#'
#'
#'
#' @param query The search query. Queries can include plain text or ontology
#' terms They also support conjunctions ("alpha AND beta"), disjunctions ("alpha OR beta")
#' grouping ("(alpha OR beta) AND gamma"), prefixing ("alpha*"), wildcard characters
#' ("BRCA?") and fuzzy matches ("alpha~").
#' @param raw \code{TRUE} to receive results as-is from Gemma, or \code{FALSE} to enable
#' parsing. Raw results usually contain additional fields and flags that are
#' omitted in the parsed results.
#' @param memoised Whether or not to save to cache for future calls with the
#' same inputs and use the result saved in cache if a result is already saved.
#' Doing \code{options(gemma.memoised = TRUE)} will ensure that the cache is always
#' used. Use \code{\link{forget_gemma_memoised}} to clear the cache.
#' @param file The name of a file to save the results to, or \code{NULL} to not write
#' results to a file. If \code{raw == TRUE}, the output will be the raw endpoint from the
#' API, likely a JSON or a gzip file. Otherwise, it will be a RDS file.
#' @param overwrite Whether or not to overwrite if a file exists at the specified
#' filename.
#'
#' @inherit processSearchAnnotations return
#' @export
#'
#' @keywords misc
#'
#' @examples
#' search_annotations("traumatic")
search_annotations <- function(query, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
open_api_name <- "search_annotations"
internal <- FALSE
keyword <- "misc"
header <- ""
isFile <- FALSE
fname <- "search_annotations"
preprocessor <- processSearchAnnotations
validators <- list(query = validateQuery)
endpoint <- "annotations/search?query={encode(query)}"
if (memoised) {
if (!is.na(file)) {
warning("Saving to files is not supported with memoisation.")
}
if ("character" %in% class(gemmaCache()) && gemmaCache() ==
"cache_in_memory") {
return(mem_in_memory_cache("search_annotations",
query = query, raw = raw, memoised = FALSE, file = file,
overwrite = overwrite
))
} else {
out <- memsearch_annotations(
query = query, raw = raw,
memoised = FALSE, file = file, overwrite = overwrite
)
return(out)
}
}
.body(
fname = fname, validators = validators, endpoint = endpoint,
envWhere = environment(), isFile = isFile, header = header,
raw = raw, overwrite = overwrite, file = file, attributes = TRUE,
open_api_name = open_api_name, .call = match.call()
)
}
#' Memoise search_annotations
#'
#' @noRd
memsearch_annotations <- function(query, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
mem_call <- memoise::memoise(search_annotations, cache = gemmaCache())
mem_call(
query = query, raw = raw, memoised = FALSE, file = file,
overwrite = overwrite
)
}
#' Retrieve the annotations of a dataset
#'
#'
#'
#' @param dataset A numerical dataset identifier or a dataset short name
#' @param raw \code{TRUE} to receive results as-is from Gemma, or \code{FALSE} to enable
#' parsing. Raw results usually contain additional fields and flags that are
#' omitted in the parsed results.
#' @param memoised Whether or not to save to cache for future calls with the
#' same inputs and use the result saved in cache if a result is already saved.
#' Doing \code{options(gemma.memoised = TRUE)} will ensure that the cache is always
#' used. Use \code{\link{forget_gemma_memoised}} to clear the cache.
#' @param file The name of a file to save the results to, or \code{NULL} to not write
#' results to a file. If \code{raw == TRUE}, the output will be the raw endpoint from the
#' API, likely a JSON or a gzip file. Otherwise, it will be a RDS file.
#' @param overwrite Whether or not to overwrite if a file exists at the specified
#' filename.
#'
#' @inherit processAnnotations return
#' @export
#'
#' @keywords dataset
#'
#' @examples
#' get_dataset_annotations("GSE2018")
get_dataset_annotations <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
open_api_name <- "get_dataset_annotations"
internal <- FALSE
keyword <- "dataset"
header <- ""
isFile <- FALSE
fname <- "get_dataset_annotations"
preprocessor <- processAnnotations
validators <- list(dataset = function(name, ...) {
ID <- unlist(list(...))
if (length(ID) > 1) {
stop(glue::glue("Please specify one valid identifier for {name}."),
call. = FALSE
)
}
validateID(name, ...)
})
endpoint <- "datasets/{encode(dataset)}/annotations"
if (memoised) {
if (!is.na(file)) {
warning("Saving to files is not supported with memoisation.")
}
if ("character" %in% class(gemmaCache()) && gemmaCache() ==
"cache_in_memory") {
return(mem_in_memory_cache("get_dataset_annotations",
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
))
} else {
out <- memget_dataset_annotations(
dataset = dataset,
raw = raw, memoised = FALSE, file = file, overwrite = overwrite
)
return(out)
}
}
.body(
fname = fname, validators = validators, endpoint = endpoint,
envWhere = environment(), isFile = isFile, header = header,
raw = raw, overwrite = overwrite, file = file, attributes = TRUE,
open_api_name = open_api_name, .call = match.call()
)
}
#' Memoise get_dataset_annotations
#'
#' @noRd
memget_dataset_annotations <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
mem_call <- memoise::memoise(get_dataset_annotations, cache = gemmaCache())
mem_call(
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
)
}
#' Retrieve the design of a dataset
#'
#'
#'
#' @param dataset A numerical dataset identifier or a dataset short name
#' @param raw \code{TRUE} to receive results as-is from Gemma, or \code{FALSE} to enable
#' parsing. Raw results usually contain additional fields and flags that are
#' omitted in the parsed results.
#' @param memoised Whether or not to save to cache for future calls with the
#' same inputs and use the result saved in cache if a result is already saved.
#' Doing \code{options(gemma.memoised = TRUE)} will ensure that the cache is always
#' used. Use \code{\link{forget_gemma_memoised}} to clear the cache.
#' @param file The name of a file to save the results to, or \code{NULL} to not write
#' results to a file. If \code{raw == TRUE}, the output will be the raw endpoint from the
#' API, likely a JSON or a gzip file. Otherwise, it will be a RDS file.
#' @param overwrite Whether or not to overwrite if a file exists at the specified
#' filename.
#'
#' @return A data table of the design matrix for the queried dataset.
#' A \code{404 error} if the given identifier does not map to any object
#' @export
#'
#' @keywords dataset
#'
#' @examples
#' head(get_dataset_design("GSE2018"))
get_dataset_design <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
open_api_name <- "get_dataset_design"
internal <- FALSE
keyword <- "dataset"
header <- ""
isFile <- TRUE
fname <- "get_dataset_design"
preprocessor <- processFile
validators <- list(dataset = function(name, ...) {
ID <- unlist(list(...))
if (length(ID) > 1) {
stop(glue::glue("Please specify one valid identifier for {name}."),
call. = FALSE
)
}
validateID(name, ...)
})
endpoint <- "datasets/{encode(dataset)}/design"
if (memoised) {
if (!is.na(file)) {
warning("Saving to files is not supported with memoisation.")
}
if ("character" %in% class(gemmaCache()) && gemmaCache() ==
"cache_in_memory") {
return(mem_in_memory_cache("get_dataset_design",
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
))
} else {
out <- memget_dataset_design(
dataset = dataset, raw = raw,
memoised = FALSE, file = file, overwrite = overwrite
)
return(out)
}
}
.body(
fname = fname, validators = validators, endpoint = endpoint,
envWhere = environment(), isFile = isFile, header = header,
raw = raw, overwrite = overwrite, file = file, attributes = TRUE,
open_api_name = open_api_name, .call = match.call()
)
}
#' Memoise get_dataset_design
#'
#' @noRd
memget_dataset_design <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
mem_call <- memoise::memoise(get_dataset_design, cache = gemmaCache())
mem_call(
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
)
}
#' Retrieve annotations and surface level stats for a dataset's differential analyses
#'
#'
#'
#' @param dataset A numerical dataset identifier or a dataset short name
#' @param raw \code{TRUE} to receive results as-is from Gemma, or \code{FALSE} to enable
#' parsing. Raw results usually contain additional fields and flags that are
#' omitted in the parsed results.
#' @param memoised Whether or not to save to cache for future calls with the
#' same inputs and use the result saved in cache if a result is already saved.
#' Doing \code{options(gemma.memoised = TRUE)} will ensure that the cache is always
#' used. Use \code{\link{forget_gemma_memoised}} to clear the cache.
#' @param file The name of a file to save the results to, or \code{NULL} to not write
#' results to a file. If \code{raw == TRUE}, the output will be the raw endpoint from the
#' API, likely a JSON or a gzip file. Otherwise, it will be a RDS file.
#' @param overwrite Whether or not to overwrite if a file exists at the specified
#' filename.
#'
#' @inherit processDEA return
#' @export
#'
#' @keywords dataset
#'
#' @examples
#' result <- get_dataset_differential_expression_analyses("GSE2872")
#' get_differential_expression_values(resultSet = result$result.ID[1])
get_dataset_differential_expression_analyses <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
open_api_name <- "get_dataset_differential_expression_analyses"
internal <- FALSE
keyword <- "dataset"
header <- ""
isFile <- FALSE
fname <- "get_dataset_differential_expression_analyses"
preprocessor <- processDEA
validators <- list(dataset = function(name, ...) {
ID <- unlist(list(...))
if (length(ID) > 1) {
stop(glue::glue("Please specify one valid identifier for {name}."),
call. = FALSE
)
}
validateID(name, ...)
})
endpoint <- "datasets/{encode(dataset)}/analyses/differential"
if (memoised) {
if (!is.na(file)) {
warning("Saving to files is not supported with memoisation.")
}
if ("character" %in% class(gemmaCache()) && gemmaCache() ==
"cache_in_memory") {
return(mem_in_memory_cache("get_dataset_differential_expression_analyses",
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
))
} else {
out <- memget_dataset_differential_expression_analyses(
dataset = dataset,
raw = raw, memoised = FALSE, file = file, overwrite = overwrite
)
return(out)
}
}
.body(
fname = fname, validators = validators, endpoint = endpoint,
envWhere = environment(), isFile = isFile, header = header,
raw = raw, overwrite = overwrite, file = file, attributes = TRUE,
open_api_name = open_api_name, .call = match.call()
)
}
#' Memoise get_dataset_differential_expression_analyses
#'
#' @noRd
memget_dataset_differential_expression_analyses <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
mem_call <- memoise::memoise(get_dataset_differential_expression_analyses,
cache = gemmaCache()
)
mem_call(
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
)
}
#' Retrieve the expression data matrix of a set of datasets and genes
#'
#'
#'
#' @param datasets A numerical dataset identifier or a dataset short name
#' @param genes An ensembl gene identifier which typically starts with ensg or an ncbi gene identifier or an official gene symbol approved by hgnc
#' @param keepNonSpecific logical. \code{FALSE} by default. If \code{TRUE}, results
#' from probesets that are not specific to the gene will also be returned.
#' @param consolidate An option for gene expression level consolidation. If empty,
#' will return every probe for the genes. "pickmax" to
#' pick the probe with the highest expression, "pickvar" to pick the prove with
#' the highest variance and "average" for returning the average expression
#' @param raw \code{TRUE} to receive results as-is from Gemma, or \code{FALSE} to enable
#' parsing. Raw results usually contain additional fields and flags that are
#' omitted in the parsed results.
#' @param memoised Whether or not to save to cache for future calls with the
#' same inputs and use the result saved in cache if a result is already saved.
#' Doing \code{options(gemma.memoised = TRUE)} will ensure that the cache is always
#' used. Use \code{\link{forget_gemma_memoised}} to clear the cache.
#' @param file The name of a file to save the results to, or \code{NULL} to not write
#' results to a file. If \code{raw == TRUE}, the output will be the raw endpoint from the
#' API, likely a JSON or a gzip file. Otherwise, it will be a RDS file.
#' @param overwrite Whether or not to overwrite if a file exists at the specified
#' filename.
#'
#' @return A list of data frames
#' @export
#'
#' @keywords dataset
#'
#' @examples
#' get_dataset_expression_for_genes("GSE2018", genes = c(10225, 2841))
get_dataset_expression_for_genes <- function(datasets, genes, keepNonSpecific = FALSE, consolidate = NA_character_,
raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_),
overwrite = getOption("gemma.overwrite", FALSE)) {
open_api_name <- "get_dataset_expression_for_genes"
internal <- FALSE
keyword <- "dataset"
header <- ""
isFile <- FALSE
fname <- "get_dataset_expression_for_genes"
preprocessor <- process_dataset_gene_expression
validators <- list(datasets = function(name, ...) {
ID <- unlist(list(...))
isID <- grepl("^\\d+$", ID)
if (any(is.na(ID)) || (any(isID) && !all(isID)) || any(ID ==
"")) {
stop(glue::glue("Please specify valid identifiers for {name} and do not combine different types of identifiers."),
call. = FALSE
)
}
paste0(ID, collapse = ",")
}, genes = function(name, ...) {
ID <- unlist(list(...))
isID <- grepl("^\\d+$", ID)
if (any(is.na(ID)) || (any(isID) && !all(isID)) || any(ID ==
"")) {
stop(glue::glue("Please specify valid identifiers for {name} and do not combine different types of identifiers."),
call. = FALSE
)
}
paste0(ID, collapse = ",")
}, keepNonSpecific = function(name, ...) {
args <- unlist(list(...))
if (length(args) != 1 || !is.logical(args)) {
stop(glue::glue("Please only specify boolean values for {name}."),
call. = FALSE
)
}
tolower(as.character(args))
}, consolidate = function(name, ...) {
consolidate <- unlist(list(...))
if (length(consolidate) > 1 | (!consolidate %in% c(
NA,
"pickmax", "pickvar", "average"
))) {
stop("consolidate must be NA, \"pickmax\", \"pickmax\" or \"average\"")
}
return(consolidate)
})
endpoint <- "datasets/{encode(datasets)}/expressions/genes/{encode(genes)}?keepNonSpecific={encode(keepNonSpecific)}&consolidate={encode(consolidate)}"
if (memoised) {
if (!is.na(file)) {
warning("Saving to files is not supported with memoisation.")
}
if ("character" %in% class(gemmaCache()) && gemmaCache() ==
"cache_in_memory") {
return(mem_in_memory_cache("get_dataset_expression_for_genes",
datasets = datasets, genes = genes, keepNonSpecific = keepNonSpecific,
consolidate = consolidate, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
))
} else {
out <- memget_dataset_expression_for_genes(
datasets = datasets,
genes = genes, keepNonSpecific = keepNonSpecific,
consolidate = consolidate, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
)
return(out)
}
}
.body(
fname = fname, validators = validators, endpoint = endpoint,
envWhere = environment(), isFile = isFile, header = header,
raw = raw, overwrite = overwrite, file = file, attributes = TRUE,
open_api_name = open_api_name, .call = match.call()
)
}
#' Memoise get_dataset_expression_for_genes
#'
#' @noRd
memget_dataset_expression_for_genes <- function(datasets, genes, keepNonSpecific = FALSE, consolidate = NA_character_,
raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_),
overwrite = getOption("gemma.overwrite", FALSE)) {
mem_call <- memoise::memoise(get_dataset_expression_for_genes,
cache = gemmaCache()
)
mem_call(
datasets = datasets, genes = genes, keepNonSpecific = keepNonSpecific,
consolidate = consolidate, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
)
}
#' Retrieve the platforms of a dataset
#'
#'
#'
#' @param dataset A numerical dataset identifier or a dataset short name
#' @param raw \code{TRUE} to receive results as-is from Gemma, or \code{FALSE} to enable
#' parsing. Raw results usually contain additional fields and flags that are
#' omitted in the parsed results.
#' @param memoised Whether or not to save to cache for future calls with the
#' same inputs and use the result saved in cache if a result is already saved.
#' Doing \code{options(gemma.memoised = TRUE)} will ensure that the cache is always
#' used. Use \code{\link{forget_gemma_memoised}} to clear the cache.
#' @param file The name of a file to save the results to, or \code{NULL} to not write
#' results to a file. If \code{raw == TRUE}, the output will be the raw endpoint from the
#' API, likely a JSON or a gzip file. Otherwise, it will be a RDS file.
#' @param overwrite Whether or not to overwrite if a file exists at the specified
#' filename.
#'
#' @inherit processPlatforms return
#' @export
#'
#' @keywords dataset
#'
#' @examples
#' get_dataset_platforms("GSE2018")
get_dataset_platforms <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
open_api_name <- "get_dataset_platforms"
internal <- FALSE
keyword <- "dataset"
header <- ""
isFile <- FALSE
fname <- "get_dataset_platforms"
preprocessor <- processPlatforms
validators <- list(dataset = function(name, ...) {
ID <- unlist(list(...))
if (length(ID) > 1) {
stop(glue::glue("Please specify one valid identifier for {name}."),
call. = FALSE
)
}
validateID(name, ...)
})
endpoint <- "datasets/{encode(dataset)}/platforms"
if (memoised) {
if (!is.na(file)) {
warning("Saving to files is not supported with memoisation.")
}
if ("character" %in% class(gemmaCache()) && gemmaCache() ==
"cache_in_memory") {
return(mem_in_memory_cache("get_dataset_platforms",
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
))
} else {
out <- memget_dataset_platforms(
dataset = dataset,
raw = raw, memoised = FALSE, file = file, overwrite = overwrite
)
return(out)
}
}
.body(
fname = fname, validators = validators, endpoint = endpoint,
envWhere = environment(), isFile = isFile, header = header,
raw = raw, overwrite = overwrite, file = file, attributes = TRUE,
open_api_name = open_api_name, .call = match.call()
)
}
#' Memoise get_dataset_platforms
#'
#' @noRd
memget_dataset_platforms <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
mem_call <- memoise::memoise(get_dataset_platforms, cache = gemmaCache())
mem_call(
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
)
}
#' Retrieve processed expression data of a dataset
#'
#'
#'
#' @param dataset A numerical dataset identifier or a dataset short name
#' @param raw \code{TRUE} to receive results as-is from Gemma, or \code{FALSE} to enable
#' parsing. Raw results usually contain additional fields and flags that are
#' omitted in the parsed results.
#' @param memoised Whether or not to save to cache for future calls with the
#' same inputs and use the result saved in cache if a result is already saved.
#' Doing \code{options(gemma.memoised = TRUE)} will ensure that the cache is always
#' used. Use \code{\link{forget_gemma_memoised}} to clear the cache.
#' @param file The name of a file to save the results to, or \code{NULL} to not write
#' results to a file. If \code{raw == TRUE}, the output will be the raw endpoint from the
#' API, likely a JSON or a gzip file. Otherwise, it will be a RDS file.
#' @param overwrite Whether or not to overwrite if a file exists at the specified
#' filename.
#'
#' @return If raw is FALSE (default), a data table of the expression matrix for
#' the queried dataset. If raw is TRUE, returns the binary file in raw form.
#' @export
#'
#' @keywords dataset
#'
#' @examples
#' get_dataset_processed_expression("GSE2018")
get_dataset_processed_expression <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
open_api_name <- "get_dataset_processed_expression"
internal <- FALSE
keyword <- "dataset"
header <- ""
isFile <- TRUE
fname <- "get_dataset_processed_expression"
preprocessor <- processFile
validators <- list(dataset = validateID)
endpoint <- "datasets/{encode(dataset)}/data/processed"
if (memoised) {
if (!is.na(file)) {
warning("Saving to files is not supported with memoisation.")
}
if ("character" %in% class(gemmaCache()) && gemmaCache() ==
"cache_in_memory") {
return(mem_in_memory_cache("get_dataset_processed_expression",
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
))
} else {
out <- memget_dataset_processed_expression(
dataset = dataset,
raw = raw, memoised = FALSE, file = file, overwrite = overwrite
)
return(out)
}
}
.body(
fname = fname, validators = validators, endpoint = endpoint,
envWhere = environment(), isFile = isFile, header = header,
raw = raw, overwrite = overwrite, file = file, attributes = TRUE,
open_api_name = open_api_name, .call = match.call()
)
}
#' Memoise get_dataset_processed_expression
#'
#' @noRd
memget_dataset_processed_expression <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
mem_call <- memoise::memoise(get_dataset_processed_expression,
cache = gemmaCache()
)
mem_call(
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
)
}
#' Retrieve quantitation types of a dataset
#'
#'
#'
#' @param dataset A numerical dataset identifier or a dataset short name
#' @param raw \code{TRUE} to receive results as-is from Gemma, or \code{FALSE} to enable
#' parsing. Raw results usually contain additional fields and flags that are
#' omitted in the parsed results.
#' @param memoised Whether or not to save to cache for future calls with the
#' same inputs and use the result saved in cache if a result is already saved.
#' Doing \code{options(gemma.memoised = TRUE)} will ensure that the cache is always
#' used. Use \code{\link{forget_gemma_memoised}} to clear the cache.
#' @param file The name of a file to save the results to, or \code{NULL} to not write
#' results to a file. If \code{raw == TRUE}, the output will be the raw endpoint from the
#' API, likely a JSON or a gzip file. Otherwise, it will be a RDS file.
#' @param overwrite Whether or not to overwrite if a file exists at the specified
#' filename.
#'
#' @inherit processQuantitationTypeValueObject return
#' @export
#'
#' @keywords dataset
#'
#' @examples
#' get_dataset_quantitation_types("GSE59918")
get_dataset_quantitation_types <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
open_api_name <- "get_dataset_quantitation_types"
internal <- FALSE
keyword <- "dataset"
header <- ""
isFile <- FALSE
fname <- "get_dataset_quantitation_types"
preprocessor <- processQuantitationTypeValueObject
validators <- list(dataset = validateID)
endpoint <- "datasets/{encode(dataset)}/quantitationTypes"
if (memoised) {
if (!is.na(file)) {
warning("Saving to files is not supported with memoisation.")
}
if ("character" %in% class(gemmaCache()) && gemmaCache() ==
"cache_in_memory") {
return(mem_in_memory_cache("get_dataset_quantitation_types",
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
))
} else {
out <- memget_dataset_quantitation_types(
dataset = dataset,
raw = raw, memoised = FALSE, file = file, overwrite = overwrite
)
return(out)
}
}
.body(
fname = fname, validators = validators, endpoint = endpoint,
envWhere = environment(), isFile = isFile, header = header,
raw = raw, overwrite = overwrite, file = file, attributes = TRUE,
open_api_name = open_api_name, .call = match.call()
)
}
#' Memoise get_dataset_quantitation_types
#'
#' @noRd
memget_dataset_quantitation_types <- function(dataset, raw = getOption("gemma.raw", FALSE), memoised = getOption(
"gemma.memoised",
FALSE
), file = getOption("gemma.file", NA_character_), overwrite = getOption(
"gemma.overwrite",
FALSE
)) {
mem_call <- memoise::memoise(get_dataset_quantitation_types,
cache = gemmaCache()
)
mem_call(
dataset = dataset, raw = raw, memoised = FALSE,
file = file, overwrite = overwrite
)
}
#' Retrieve raw expression data of a dataset
#'
#'
#'
#' @param dataset A numerical dataset identifier or a dataset short name
#' @param quantitationType Quantitation type id. These can be acquired
#' using \code{\link{get_dataset_quantitation_types}} function. This endpoint can
#' only return non-processed quantitation types.
#' @param raw \code{TRUE} to receive results as-is from Gemma, or \code{FALSE} to enable
#' parsing. Raw results usually contain additional fields and flags that are
#' omitted in the parsed results.
#' @param memoised Whether or not to save to cache for future calls with the
#' same inputs and use the result saved in cache if a result is already saved.
#' Doing \code{options(gemma.memoised = TRUE)} will ensure that the cache is always
#' used. Use \code{\link{forget_gemma_memoised}} to clear the cache.
#' @param file The name of a file to save the results to, or \code{NULL} to not write
#' results to a file. If \code{raw == TRUE}, the output will be the raw endpoint from the
#' API, likely a JSON or a gzip file. Otherwise, it will be a RDS file.
#' @param overwrite Whether or not to overwrite if a file exists at the specified
#' filename.
#'
#' @return If raw is FALSE (default), a data table of the expression matrix for
#' the queried dataset. If raw is TRUE, returns the binary file in raw form.
#' @export
#'
#' @keywords dataset
#'
#' @examples
#' q_types <- get_dataset_quantitation_types("GSE59918")
#' get_dataset_raw_expression("GSE59918", q_types$id[q_types$name == "Counts"])
get_dataset_raw_expression <- function(dataset, quantitationType, raw = getOption(
"gemma.raw",
FALSE