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
|
#! /usr/bin/env guile
!#
(use-modules (rnrs programs)
(rnrs io ports)
(srfi srfi-1)
(srfi srfi-26)
(ice-9 match)
(ice-9 regex)
(dump strings)
(dump sql)
(dump triples)
(dump special-forms))
;;; GeneNetwork database connection parameters and dump path
(define %connection-settings
(call-with-input-file (list-ref (command-line) 1)
read))
(define %dump-directory
(list-ref (command-line) 2))
;;; Dump tables
(define binomial-name->species-id
(cut string->identifier "species" <>))
(define-dump dump-species
(tables (Species))
(schema-triples
(gn:name rdfs:range rdfs:Literal)
(gn:displayName rdfs:range rdfs:Literal)
(gn:binomialName rdfs:range rdfs:Literal)
(gn:family rdfs:range rdfs:Literal))
(triples (binomial-name->species-id (field Species FullName))
(set rdf:type 'gn:species)
(set gn:name (field Species SpeciesName))
(set gn:displayName (field Species MenuName))
(set gn:binomialName (field Species FullName))
(set gn:family (field Species Family))
(set up:organism (ontology 'taxon: (field Species TaxonomyId)))))
(define-dump dump-strain
(tables (Strain
(join Species "ON Strain.SpeciesId = Species.SpeciesId")))
(schema-triples
(gn:strainOfSpecies rdfs:domain gn:strain)
(gn:strainOfSpecies rdfs:range gn:species)
(gn:name rdfs:range rdfs:Literal)
(gn:alias rdfs:range rdfs:Literal)
(gn:symbol rdfs:range rdfs:Literal))
(triples (string->identifier "strain" (field Strain Name))
(set rdf:type 'gn:strain)
(set gn:strainOfSpecies
(binomial-name->species-id (field Species FullName)))
;; Name, and maybe a second name
(set gn:name (field Strain Name))
(set gn:name (field Strain Name2))
(set gn:alias (field Strain Alias))
(set gn:symbol (field Strain Symbol))))
;; TODO: This function is unused. Remove if not required.
(define mapping-method-name->id
(cut string->identifier "mappingMethod" <>))
;; TODO: This function is unused. Remove if not required.
(define-dump dump-mapping-method
(tables (MappingMethod))
(triples (string->identifier "mappingMethod" (field MappingMethod Name))
(set rdf:type 'gn:mappingMethod)))
(define inbred-set-name->id
(cut string->identifier "inbredSet" <>))
(define-dump dump-inbred-set
(tables (InbredSet
(left-join Species "ON InbredSet.SpeciesId=Species.Id")
(left-join MappingMethod
"ON InbredSet.MappingMethodId=MappingMethod.Id")))
(schema-triples
(gn:fullName rdfs:range rdfs:Literal)
(gn:geneticType rdfs:range rdfs:Literal)
(gn:inbredSetCode rdfs:range rdfs:Literal)
(gn:inbredFamily rdfs:range rdfs:Literal)
(gn:inbredSetOfSpecies rdfs:range gn:species)
(gn:inbredSetType rdfs:range rdfs:Literal)
(gn:phenotype rdfs:range gn:inbredSetType)
(gn:genotype rdfs:range gn:inbredSetType)
(gn:inbredSetOfMappingMethod rdfs:range gn:mappingMethod))
(triples (inbred-set-name->id (field InbredSet Name))
(set rdf:type 'gn:inbredSet)
(set gn:fullName (field InbredSet FullName))
(set gn:geneticType (field InbredSet GeneticType))
(set gn:inbredFamily (field InbredSet Family))
(set gn:inbredSetOfMappingMethod (field MappingMethod Name))
(set gn:inbredSetCode (field InbredSet InbredSetCode))
(set gn:inbredSetOfSpecies
(binomial-name->species-id (field Species FullName BinomialName)))
(set gn:genotype
(field ("IF ((SELECT PublishFreeze.Name FROM PublishFreeze WHERE PublishFreeze.InbredSetId = InbredSet.Id LIMIT 1) IS NOT NULL, 'Traits and Cofactors', '')" genotypeP)))
(set gn:phenotype
(field ("IF ((SELECT GenoFreeze.Name FROM GenoFreeze WHERE GenoFreeze.InbredSetId = InbredSet.Id LIMIT 1) IS NOT NULL, 'DNA Markers and SNPs', '')" phenotypeP)))))
(define-dump dump-molecular-traits
(tables (ProbeFreeze
(left-join ProbeSetFreeze "USING (ProbeFreezeId)")
(left-join InbredSet "USING (InbredSetId)")
(left-join Tissue "USING (TissueId)")
(left-join Species "USING (SpeciesId)"))
"GROUP BY InbredSet.Name")
(schema-triples
(gn:molecularTrait rdfs:range rdfs:Literal))
(triples (inbred-set-name->id (field InbredSet Name))
(set gn:molecularTrait (field Tissue TissueName))))
;; Metadata for published datasets
(define-dump dump-publishfreeze
(tables (PublishFreeze
(left-join InbredSet "USING (InbredSetId)")))
(schema-triples
(gn:datasetOfInbredSet rdfs:range gn:inbredSet)
(gn:name rdfs:range rdfs:Literal)
(gn:fullName rdfs:range rdfs:Literal)
(gn:shortName rdfs:range rdfs:Literal)
(gn:createTime rdfs:range rdfs:Literal))
(triples (string->identifier "dataset" (field PublishFreeze Name))
(set rdf:type 'gn:dataset)
(set gn:name (field PublishFreeze Name))
(set gn:fullName (field PublishFreeze FullName))
(set gn:shortName (field PublishFreeze ShortName))
(set gn:createTime (field PublishFreeze CreateTime))
(set gn:datasetOfInbredSet
(inbred-set-name->id (field InbredSet Name InbredSetName)))))
(define-dump dump-publication
(tables (Publication))
(schema-triples
(gn:pubMedId rdfs:range rdfs:Literal)
(gn:title rdfs:range rdfs:Literal)
(gn:journal rdfs:range rdfs:Literal)
(gn:volume rdfs:range rdfs:Literal)
(gn:pages rdfs:range rdfs:Literal)
(gn:month rdfs:range rdfs:Literal)
(gn:year rdfs:range rdfs:Literal)
(gn:author rdfs:range rdfs:Literal)
(gn:abstract rdfs:range rdfs:Literal))
(triples
(let ((pmid (field
("IF(Publication.PubMed_ID IS NULL, '', CONVERT(Publication.PubMed_Id, INT))"
pmid)))
(publication-id (field Publication Id)))
(if (string-null? pmid)
(string->identifier "publication"
(number->string publication-id))
(ontology 'pubmed: pmid)))
(set rdf:type 'gn:publication)
(set gn:pubMedId (field ("IFNULL(PubMed_ID, '')" pubmedId)))
(set gn:title (field Publication Title))
(set gn:journal (field Publication Journal))
(set gn:volume (field Publication Volume))
(set gn:pages (field Publication Pages))
(set gn:month (field Publication Month))
(set gn:year (field Publication Year))
(multiset gn:author
;; The authors field is a comma
;; separated list. Split it.
(map string-trim (string-split (sanitize-rdf-string (field Publication Authors)) #\,)))
(set gn:abstract
(sanitize-rdf-string (field Publication Abstract)))))
(define tissue-short-name->id
(cut string->identifier "tissue" <>))
(define-dump dump-tissue
;; The Name and TissueName fields seem to be identical. BIRN_lex_ID
;; and BIRN_lex_Name are mostly NULL.
(tables (Tissue))
(schema-triples
(gn:name rdfs:range rdfs:Literal))
;; Hopefully the Short_Name field is distinct and can be used as an
;; identifier.
(triples (tissue-short-name->id (field Tissue Short_Name))
(set rdf:type 'gn:tissue)
(set gn:name (field Tissue Name))))
;; One email ID in the Investigators table has spaces in it. This
;; function fixes that.
(define (fix-email-id email)
(string-delete #\space email))
(define (investigator-attributes->id first-name last-name email)
;; There is just one record corresponding to "Evan Williams" which
;; does not have an email ID. To accommodate that record, we
;; construct the investigator ID from not just the email ID, but
;; also the first and the last names. It would be preferable to just
;; find Evan Williams' email ID and insert it into the database.
(string->identifier "investigator"
(string-join
;; Add special case for Yohan Bossé whose name
;; has unprintable characters.
;; TODO: Fix Yohan Bossé's name in the database.
(let ((last-name (if (string=? first-name "Yohan")
"Bosse"
last-name)))
(list first-name last-name (fix-email-id email)))
"_")))
(define-dump dump-investigators
;; There are a few duplicate entries. We group by email to
;; deduplicate.
(tables (Investigators)
"GROUP BY Email")
(schema-triples
;; TODO: Are ranges required for FOAF predicates? Can they not be
;; obtained from the FOAF spec?
(foaf:name rdfs:range rdfs:Literal)
(foaf:givenName rdfs:range rdfs:Literal)
(foaf:familyName rdfs:range rdfs:Literal)
(foaf:phone rdfs:range rdfs:Literal)
(foaf:mbox rdfs:range rdfs:Literal)
(foaf:homepage rdfs:range rdfs:Literal)
(gn:address rdfs:range rdfs:Literal)
(gn:city rdfs:range rdfs:Literal)
(gn:state rdfs:range rdfs:Literal)
(gn:zipCode rdfs:range rdfs:Literal)
(gn:country rdfs:range rdfs:Literal))
(triples (investigator-attributes->id (field Investigators FirstName)
(field Investigators LastName)
(field Investigators Email))
(set rdf:type 'foaf:Person)
;; Special case Yohan Bossé's name since the last name has
;; unprintable characters.
(set foaf:name (string-append (field Investigators FirstName) " "
(if (string=? (field Investigators FirstName) "Yohan")
"Bossé"
(field Investigators LastName))))
(set foaf:givenName (field Investigators FirstName))
;; Special case Yohan Bossé's name since the last name has
;; unprintable characters.
(set foaf:familyName (if (string=? (field Investigators FirstName) "Yohan")
"Bossé"
(field Investigators LastName)))
(set foaf:phone (field Investigators Phone))
(set foaf:mbox (fix-email-id (field Investigators Email)))
(set foaf:homepage (field Investigators Url))
(set gn:address (field Investigators Address))
(set gn:city (field Investigators City))
(set gn:state (field Investigators State))
(set gn:zipCode (field Investigators ZipCode))
(set gn:country (field Investigators Country))))
(define avg-method-name->id
(cut string->identifier "avgmethod" <>))
(define-dump dump-avg-method
;; The Name and Normalization fields seem to be the same. Dump only
;; the Name field.
(tables (AvgMethod))
(schema-triples
(gn:name rdfs:range rdfs:Literal))
(triples (avg-method-name->id (field AvgMethod Name))
(set rdf:type 'gn:avgMethod)
(set gn:name (field AvgMethod Name))))
(define gene-chip-name->id
(cut string->identifier "platform" <>))
(define-dump dump-gene-chip
(tables (GeneChip))
(schema-triples
(gn:name rdfs:range rdfs:Literal))
(triples (gene-chip-name->id (field GeneChip Name))
(set rdf:type 'gn:platform)
(set gn:name (field GeneChip GeneChipName))))
;; Dumping Datasets from InfoFiles that don't exist in PublishFreeze and GenoFreeze
(define-dump dump-info-files
(tables (InfoFiles
(left-join PublishFreeze "ON InfoFiles.InfoPageName = PublishFreeze.Name")
(left-join GenoFreeze "ON InfoFiles.InfoPageName = GenoFreeze.Name")
(left-join Datasets "USING (DatasetId)")
(left-join DatasetStatus "USING (DatasetStatusId)")
(left-join Species "USING (SpeciesId)")
(left-join Tissue "USING (TissueId)")
(left-join Investigators "USING (InvestigatorId)")
(left-join AvgMethod "USING (AvgMethodId)")
(left-join GeneChip "USING (GeneChipId)"))
"WHERE GN_AccesionId IS NOT NULL")
(schema-triples
(gn:datasetOfInvestigator rdfs:domain gn:dataset)
(gn:datasetOfInvestigator rdfs:range foaf:Person)
(gn:datasetOfSpecies rdfs:domain gn:dataset)
(gn:datasetOfSpecies rdfs:range gn:species)
(gn:datasetOfInbredSet rdfs:domain gn:dataset)
(gn:datasetOfInbredSet rdfs:range gn:inbredSet)
(gn:datasetOfTissue rdfs:domain gn:dataset)
(gn:datasetOfTissue rdfs:range gn:tissue)
(gn:normalization rdfs:domain gn:dataset)
(gn:normalization rdfs:range gn:avgMethod)
(gn:datasetOfPlatform rdfs:domain gn:dataset)
(gn:datasetOfPlatform rdfs:range gn:geneChip)
(gn:accessionId rdfs:range rdfs:Literal)
(gn:datasetStatusName rdfs:range rdfs:Literal)
(gn:summary rdfs:range rdfs:Literal)
(gn:aboutTissue rdfs:range rdfs:Literal)
(gn:geoSeries rdfs:range rdfs:Literal)
(gn:name rdfs:range rdfs:Literal)
(gn:title rdfs:range rdfs:Literal)
(gn:specifics rdfs:range rdfs:Literal)
(gn:datasetGroup rdfs:range rdfs:Literal)
(gn:aboutCases rdfs:range rdfs:Literal)
(gn:aboutPlatform rdfs:range rdfs:Literal)
(gn:aboutDataProcessing rdfs:range rdfs:Literal)
(gn:notes rdfs:range rdfs:Literal)
(gn:experimentDesign rdfs:range rdfs:Literal)
(gn:contributors rdfs:range rdfs:Literal)
(gn:citation rdfs:range rdfs:Literal)
(gn:acknowledgment rdfs:range rdfs:Literal))
(triples (string->identifier "dataset"
(field InfoFiles InfoPageName))
(set rdf:type 'gn:dataset)
(set gn:name (field InfoFiles InfoPageName))
(set dct:created
(let* ((genotype-create-time
(field ("IFNULL(GenoFreeze.CreateTime, '')"
createTimeGenoFreeze)))
(phenotype-create-time
(field ("IFNULL(PublishFreeze.CreateTime, '')"
createTimePublishFreeze)))
(create-time
(if (string-null? genotype-create-time)
phenotype-create-time genotype-create-time)))
(annotate-field
create-time
'^^xsd:datetime)))
(set gn:datasetOfInvestigator
(investigator-attributes->id (field Investigators FirstName)
(field Investigators LastName)
(field Investigators Email)))
(set gn:accessionId (string-append "GN" (number->string
(field InfoFiles GN_AccesionId))))
(set gn:datasetStatusName (string-downcase
(field DatasetStatus DatasetStatusName)))
(set gn:datasetOfSpecies (binomial-name->species-id
(field Species FullName BinomialName)))
(set gn:datasetOfTissue (tissue-short-name->id (field Tissue Short_Name)))
(set gn:normalization
(avg-method-name->id
;; If AvgMethodName is NULL, assume N/A.
(if (string-blank? (field AvgMethod Name AvgMethodName))
"N/A" (field AvgMethod Name AvgMethodName))))
(set gn:datasetOfPlatform (gene-chip-name->id (field GeneChip Name GeneChip)))
(set gn:summary
(sanitize-rdf-string (field Datasets Summary)))
(set gn:aboutTissue
(sanitize-rdf-string (field Datasets AboutTissue)))
(set gn:geoSeries
(and (not (string-prefix-ci? "no geo series"
(field Datasets GeoSeries)))
(field Datasets GeoSeries)))
(set gn:title (field InfoFiles Title))
(set gn:specifics (sanitize-rdf-string (field InfoFiles Specifics)))
(set gn:datasetGroup (field Datasets DatasetName DatasetGroup))
(set gn:aboutCases (sanitize-rdf-string (field Datasets AboutCases)))
(set gn:aboutPlatform (sanitize-rdf-string (field Datasets AboutPlatform)))
(set gn:aboutDataProcessing (sanitize-rdf-string
(field Datasets AboutDataProcessing)))
(set gn:notes (sanitize-rdf-string (field Datasets Notes)))
(set gn:experimentDesign (sanitize-rdf-string
(field Datasets ExperimentDesign)))
(set gn:contributors (sanitize-rdf-string (field Datasets Contributors)))
(set gn:citation (sanitize-rdf-string (field Datasets Citation)))
(set gn:acknowledgment (sanitize-rdf-string
(field Datasets Acknowledgment)))))
;; Dumping Phenotypes from PublishFreeze that are not present in the InfoFiles tables
(define-dump dump-phenotypes
(tables (Phenotype
(left-join PublishXRef "ON Phenotype.Id = PublishXRef.PhenotypeId")
(left-join Publication "ON Publication.Id = PublishXRef.PublicationId")
(left-join PublishFreeze "ON PublishFreeze.InbredSetId = PublishXRef.InbredSetId")
(left-join InfoFiles "ON InfoFiles.InfoPageName = PublishFreeze.Name")))
(schema-triples
(gn:phenotypeDataset rdfs:subPropertyOf gn:dataset))
(triples (ontology 'phenotype:
(regexp-substitute/global #f "[^A-Za-z0-9:]"
(field ("CONCAT(IF(PublishFreeze.Name IS NULL, '', CONCAT(PublishFreeze.Name, ':')), IF(Phenotype.Post_publication_abbreviation IS NULL, IF(Phenotype.Pre_publication_abbreviation IS NULL, Phenotype.Id, Pre_publication_abbreviation), Phenotype.Post_publication_abbreviation))" abbrev))
'pre "_" 'post))
(set rdf:type 'gn:phenotype)
(set gn:name (sanitize-rdf-string
(field
("CAST(CONVERT(BINARY CONVERT(CONCAT(IF(PublishFreeze.Name IS NULL, '', CONCAT(PublishFreeze.Name, '-')), IF(Phenotype.Post_publication_abbreviation IS NULL, IF(Phenotype.Pre_publication_abbreviation IS NULL, Phenotype.Id, Phenotype.Pre_publication_abbreviation), Phenotype.Post_publication_abbreviation)) USING latin1) USING utf8) AS VARCHAR(10000))"
abbrev))))
;; There is no row with an empty post-publication description so
;; use this field as the main publication description
(set gn:publicationDescription
(sanitize-rdf-string
(field ("CAST(CONVERT(BINARY CONVERT(Phenotype.Post_publication_description USING latin1) USING utf8) AS CHAR(10000))"
postPubDescr))))
(set gn:originalDescription (sanitize-rdf-string
(delete-substrings
(field Phenotype Original_description)
"Original post publication description: ")))
(set gn:prePublicationDescription
(sanitize-rdf-string
(field
("CAST(CONVERT(BINARY CONVERT(Phenotype.Pre_publication_description USING latin1) USING utf8) AS VARCHAR(15000))"
prePubDesc))))
(set gn:prePublicationAbbreviation (sanitize-rdf-string (field Phenotype Pre_publication_abbreviation)))
(set gn:postPublicationAbbreviation (sanitize-rdf-string (field Phenotype Post_publication_abbreviation)))
(set gn:labCode (field Phenotype Lab_code))
(set gn:submitter (sanitize-rdf-string (field Phenotype Submitter)))
(set gn:owner (sanitize-rdf-string (field Phenotype Owner)))
(set gn:mean (annotate-field (field ("IFNULL(PublishXRef.mean, '')" mean))
'^^xsd:float))
(set gn:locus (field PublishXRef Locus))
(set gn:LRS (annotate-field (field ("IFNULL(PublishXRef.LRS, '')" lrs)) '^^xsd:float))
(set gn:additive (annotate-field (field ("IFNULL(PublishXRef.additive, '')" additive)) '^^xsd:decimal))
(set gn:sequence (annotate-field (field PublishXRef Sequence) '^^xsd:int))
(set gn:phenotypeOfDataset (string->identifier "dataset" (field PublishFreeze Name)))
(set gn:phenotypeOfPublication
(let ((pmid (field
("IF(Publication.PubMed_ID IS NULL, '', CONVERT(Publication.PubMed_Id, INT))"
pmid)))
(publication-id (field Publication Id)))
(if (string-null? pmid)
(string->identifier "publication"
(number->string publication-id))
(ontology 'pubmed: pmid))))))
(define-dump dump-genotypes
(tables (GenoFreeze
(left-join InfoFiles "ON InfoFiles.InfoPageName = GenoFreeze.Name"))
"WHERE GenoFreeze.Name NOT IN (SELECT DISTINCT InfoFiles.InfoPageName FROM InfoFiles)")
(schema-triples
(gn:phenotypeDataset rdfs:subPropertyOf gn:dataset))
(triples (string->identifier "dataset"
(field GenoFreeze Name))
(set rdf:type 'gn:genotypeDataset)
(set gn:name (field GenoFreeze FullName))
(set dct:created (annotate-field
(field GenoFreeze CreateTime)
'^^xsd:datetime))))
(define (dump-data-table db table-name data-field)
(let ((dump-directory (string-append %dump-directory "/" table-name))
(port #f)
(current-strain-id #f))
(unless (file-exists? dump-directory)
(mkdir dump-directory))
(sql-for-each (match-lambda
(((_ . strain-id)
(_ . value))
;; Close file if new strain.
(when (and port
(not (= current-strain-id strain-id)))
(close-port port)
(set! port #f))
;; If no file is open, open new file.
(unless port
(set! current-strain-id strain-id)
(let ((filename (string-append dump-directory
"/" (number->string strain-id))))
(display filename (current-error-port))
(newline (current-error-port))
(set! port (open-output-file filename))))
(display value port)
(newline port)))
db
(format #f "SELECT StrainId, ~a FROM ~a ORDER BY StrainId"
data-field table-name))
(close-port port)))
;;; Dump schema
(define (tables db)
"Return list of all tables in DB. Each element of the returned list
is a <table> object."
(map (lambda (table)
(set-table-columns table
(sql-map (lambda (row)
(make-column (assoc-ref row "Field")
(assoc-ref row "Type")))
db
(format #f "SHOW COLUMNS FROM ~a" (table-name table)))))
(sql-map (lambda (row)
(make-table (assoc-ref row "table_name")
;; FIXME: This is probably correct only for
;; MyISAM tables.
(assoc-ref row "data_length")
#f))
db
(select-query ((information_schema.tables table_name)
(information_schema.tables data_length))
(information_schema.tables)
(format #f "WHERE table_schema = '~a'"
(assq-ref %connection-settings 'sql-database))))))
(define (dump-schema db)
(let ((tables (tables db)))
(for-each (lambda (table)
(let ((table-id (string->identifier
"table"
;; We downcase table names in
;; identifiers. So, we distinguish
;; between the user and User tables.
(if (string=? (table-name table) "User")
"user2"
(table-name table)))))
(triple table-id 'rdf:type 'gn:sqlTable)
(triple table-id 'gn:name (table-name table))
(triple table-id 'gn:hasSize (table-size table))
(for-each (lambda (column)
(let ((column-id (column-id (table-name table)
(column-name column))))
(triple column-id 'rdf:type 'gn:sqlTableField)
(triple column-id 'gn:name (column-name column))
(triple column-id 'gn:sqlFieldType (column-type column))
(triple table-id 'gn:hasField column-id)))
(table-columns table))))
tables)))
(define-dump dump-groups
(tables (InbredSet
(left-join Species "USING (SpeciesId)"))
(string-join
'("WHERE Species.Name IN "
"(SELECT Name FROM Species ORDER BY OrderId) "
"GROUP BY InbredSet.Name "
"ORDER BY "
"IFNULL(InbredSet.FamilyOrder, InbredSet.FullName) "
"ASC, IFNULL(InbredSet.Family, InbredSet.FullName) "
"ASC, InbredSet.FullName ASC, InbredSet.MenuOrderId ASC")))
(schema-triples
(gn:name rdfs:range rdfs:Literal)
(gn:binomialName rdfs:range rdfs:Literal)
(gn:species rdfs:range gn:species))
(triples (string->identifier "inbredSet" (field InbredSet Name))
(set gn:name (field InbredSet Name))
(set gn:binomialName (field InbredSet fullName))
(set gn:species (field Species Name))))
(define-dump dump-genewiki-symbols
(tables (GeneRIF_BASIC
(left-join Species "USING (SpeciesId)"))
"GROUP BY GeneId ORDER BY BINARY symbol")
(schema-triples
(gn:symbol rdfs:domain gn:geneWikiEntry)
(gn:wikiEntryOfSpecies rdfs:range gn:species)
(gn:taxid rdfs:domain gn:geneWikiEntry))
(triples (ontology 'generif: (field GeneRIF_BASIC GeneId))
(multiset gn:symbol (string-split (field ("GROUP_CONCAT(DISTINCT symbol)" symbol))
#\,))
(multiset gn:wikiEntryOfSpecies
(string-split
(field ("GROUP_CONCAT(DISTINCT Species.SpeciesName)" species))
#\,))
(multiset gn:taxId (map (cut ontology 'taxon: <>)
(string-split (field ("GROUP_CONCAT(DISTINCT TaxID)" taxId))
#\,)))))
;; GeneRIF metadata
(define-dump dump-gn-genewiki-entries
(tables (GeneRIF
(left-join GeneRIF_BASIC "USING (symbol)")
(left-join Species "ON Species.SpeciesId = GeneRIF.SpeciesId")
(left-join GeneRIFXRef "ON GeneRIFXRef.GeneRIFId = GeneRIF.Id")
(left-join GeneCategory "ON GeneRIFXRef.GeneCategoryId = GeneCategory.Id"))
"WHERE GeneRIF.display > 0 AND GeneRIF.VersionId = 0 GROUP BY GeneRIF.symbol")
(schema-triples
(gn:geneWikiEntry a rdfs:Class)
(gn:geneWikiEntry a owl:Class)
(gn:geneWikiEntry rdfs:comment "Represents GeneRIF Entries")
(gn:geneCategory rdfs:domain gn:geneWikiEntry)
(gn:geneWikiEntryOfGn rdfs:domain gn:geneWikiEntry)
(gn:geneWikiEntry rdfs:domain gn:geneWikiEntry))
(triples
(let ([geneid (field GeneRIF_BASIC GeneId)])
(if (eq? geneid 0)
(ontology 'gn:anonSymbol_
(field GeneRIF symbol))
(ontology 'generif:
geneid)))
(set rdf:type (if (eq? (field GeneRIF_BASIC GeneId) 0)
'gn:geneWikiEntry
""))
(set gn:wikiEntryOfSpecies (if (eq? (field GeneRIF_BASIC GeneId) 0)
(field Species SpeciesName)
""))
;; This only dumps symbols not present in the GeneRIF_BASIC table
(set gn:symbol (let ([geneid (field GeneRIF_BASIC GeneId)])
(if (eq? geneid 0)
(field GeneRIF symbol)
"")))
(multiset gn:geneWikiEntryOfGn
(let* ([entries
(replace-substrings
(field
("GROUP_CONCAT(DISTINCT CONCAT_WS('::::', IFNULL(GeneCategory.Name, ''), IFNULL(GeneRIF.PubMed_ID, ''), GeneRIF.email, GeneRIF.comment, GeneRIF.createtime, IFNULL(weburl, '')) SEPARATOR';;;;;')"
wikientry))
'(("\x28" . "")
("\x29" . "")
("\xa0" . " ")
("â\x81„" . "/")
("â€\x9d" . #\")
("’" . #\')
("\x02" . "")
("\x01" . "")
("β" . "β")
("α-Â\xad" . "α")
("Â\xad" . "")
("α" . "α")
("–" . "-")))]
[comments (string-split-substring entries ";;;;;")])
(map
(match-lambda
((genecategory pmid email text createtime weburl)
(blank-node
(set gn:geneCategory genecategory)
(multiset dct:source
(map (lambda (el) (if (string-null? el)
""
(ontology 'pubmed: el)))
(string-split pmid #\space)))
(set dct:creator (regexp-substitute/global #f "@.*$"
email
'pre
""
'post))
(set gn:geneWikiEntry
(annotate-field text '^^xsd:string))
(set dct:created (annotate-field
createtime
'^^xsd:datetime))
(set foaf:homepage weburl))))
(map
(cut string-split-substring <> "::::")
comments))))))
(define-dump dump-ncbi-genewiki-entries
(tables (GeneRIF_BASIC)
"GROUP BY GeneId, comment, createtime")
(schema-triples
(gn:geneWikiEntryofNCBI rdfs:domain gn:geneWikiEntry))
(triples (ontology 'generif:
(field GeneRIF_BASIC GeneId))
(set gn:geneWikiEntryOfNCBI
(blank-node
(set gn:geneWikiEntry
(annotate-field (field GeneRIF_BASIC comment)
'^^xsd:string))
(multiset dct:source (map (lambda (el) (if (string-null? el)
""
(ontology 'pubmed: el)))
(string-split (field ("GROUP_CONCAT(PubMed_ID)" pmids))
#\,)))
(set dct:created (annotate-field (time-unix->string
(field GeneRIF_BASIC createtime) "~5")
'^^xsd:datetime))))))
;; Main function
(call-with-genenetwork-database
(lambda (db)
(with-output-to-file (string-append %dump-directory "/dump.ttl")
(lambda ()
(prefix "rdf:" "<http://www.w3.org/1999/02/22-rdf-syntax-ns#>")
(prefix "rdfs:" "<http://www.w3.org/2000/01/rdf-schema#>")
(prefix "foaf:" "<http://xmlns.com/foaf/0.1/>")
(prefix "gn:" "<http://genenetwork.org/>")
(prefix "dct:" "<http://purl.org/dc/terms/>")
(prefix "pubmed:" "<http://rdf.ncbi.nlm.nih.gov/pubmed/>")
(prefix "up:" "<http://purl.uniprot.org/core/>")
(prefix "taxon:" "<http://purl.uniprot.org/taxonomy/>")
(prefix "generif:" "<http://www.ncbi.nlm.nih.gov/gene?cmd=Retrieve&dopt=Graphics&list_uids=>")
(prefix "xsd:" "<http://www.w3.org/2001/XMLSchema#>")
(prefix "owl:" "<http://www.w3.org/2002/07/owl#>")
(prefix "phenotype:" "<http://genenetwork.org/phenotype/>")
(newline)
(dump-genewiki-symbols db)
(dump-gn-genewiki-entries db)
(dump-ncbi-genewiki-entries db)
(dump-species db)
(dump-strain db)
(dump-mapping-method db)
(dump-inbred-set db)
(dump-publishfreeze db)
(dump-publication db)
(dump-tissue db)
(dump-investigators db)
(dump-avg-method db)
(dump-gene-chip db)
(dump-info-files db)
(dump-schema db)
(dump-groups db)
(dump-published-phenotypes db)))))
|