grz-cli 0.1.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- __init__.py +0 -0
- grz_cli/__init__.py +0 -0
- grz_cli/cli.py +326 -0
- grz_cli/constants.py +37 -0
- grz_cli/download.py +236 -0
- grz_cli/fastq_validation.py +122 -0
- grz_cli/file_operations.py +364 -0
- grz_cli/logging_setup.py +59 -0
- grz_cli/models/__init__.py +0 -0
- grz_cli/models/config.py +118 -0
- grz_cli/models/v1_0_0/__init__.py +0 -0
- grz_cli/models/v1_0_0/metadata.py +845 -0
- grz_cli/parser.py +771 -0
- grz_cli/progress_logging.py +170 -0
- grz_cli/resources/grz-schema.json +560 -0
- grz_cli/upload.py +243 -0
- grz_cli-0.1.0.dist-info/LICENSE +21 -0
- grz_cli-0.1.0.dist-info/METADATA +240 -0
- grz_cli-0.1.0.dist-info/RECORD +22 -0
- grz_cli-0.1.0.dist-info/WHEEL +5 -0
- grz_cli-0.1.0.dist-info/entry_points.txt +2 -0
- grz_cli-0.1.0.dist-info/top_level.txt +2 -0
|
@@ -0,0 +1,560 @@
|
|
|
1
|
+
{
|
|
2
|
+
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
3
|
+
"version": "1.0.0",
|
|
4
|
+
"title": "Metadata Submission Genomic Data Center (GRZ)",
|
|
5
|
+
"description": "General metadata schema for submissions to the GRZ",
|
|
6
|
+
"type": "object",
|
|
7
|
+
"required": [
|
|
8
|
+
"submission",
|
|
9
|
+
"donors"
|
|
10
|
+
],
|
|
11
|
+
"properties": {
|
|
12
|
+
"submission": {
|
|
13
|
+
"type": "object",
|
|
14
|
+
"required": [
|
|
15
|
+
"submissionDate",
|
|
16
|
+
"submissionType",
|
|
17
|
+
"tanG",
|
|
18
|
+
"submitterId",
|
|
19
|
+
"genomicDataCenterId",
|
|
20
|
+
"clinicalDataNodeId",
|
|
21
|
+
"genomicStudyType",
|
|
22
|
+
"genomicStudySubtype",
|
|
23
|
+
"labName"
|
|
24
|
+
],
|
|
25
|
+
"properties": {
|
|
26
|
+
"submissionDate": {
|
|
27
|
+
"type": "string",
|
|
28
|
+
"description": "Date of submission in ISO 8601 format YYYY-MM-DD",
|
|
29
|
+
"format": "date"
|
|
30
|
+
},
|
|
31
|
+
"submissionType": {
|
|
32
|
+
"type": "string",
|
|
33
|
+
"description": "The options are: 'initial' for first submission, 'followup' is for followup submissions, 'addition' for additional submission, 'correction' for correction",
|
|
34
|
+
"enum": [
|
|
35
|
+
"initial",
|
|
36
|
+
"followup",
|
|
37
|
+
"addition",
|
|
38
|
+
"correction"
|
|
39
|
+
]
|
|
40
|
+
},
|
|
41
|
+
"tanG": {
|
|
42
|
+
"type": "string",
|
|
43
|
+
"description": "The VNg of the genomic data of the patient that will be reimbursed --> a unique 32-byte hex ID.",
|
|
44
|
+
"pattern": "^[a-fA-F0-9]{32}$"
|
|
45
|
+
},
|
|
46
|
+
"localCaseId": {
|
|
47
|
+
"type": "string",
|
|
48
|
+
"description": "A local case identifier for synchronizing locally"
|
|
49
|
+
},
|
|
50
|
+
"submitterId": {
|
|
51
|
+
"type": "string",
|
|
52
|
+
"description": "Institutional ID of the submitter according to §293 SGB V.",
|
|
53
|
+
"pattern": "^[0-9]{9}$"
|
|
54
|
+
},
|
|
55
|
+
"genomicDataCenterId": {
|
|
56
|
+
"type": "string",
|
|
57
|
+
"description": "ID of the genomic data center in the format GRZXXXnnn.",
|
|
58
|
+
"pattern": "^(GRZ|KDK)[A-Z0-9]{3}[0-9]{3}$"
|
|
59
|
+
},
|
|
60
|
+
"clinicalDataNodeId": {
|
|
61
|
+
"type": "string",
|
|
62
|
+
"description": "ID of the genomic data center in the format KDKXXXnnn.",
|
|
63
|
+
"pattern": "^(GRZ|KDK)[A-Z0-9]{3}[0-9]{3}$"
|
|
64
|
+
},
|
|
65
|
+
"genomicStudyType": {
|
|
66
|
+
"type": "string",
|
|
67
|
+
"description": "whether additional persons are tested as well",
|
|
68
|
+
"enum": [
|
|
69
|
+
"single",
|
|
70
|
+
"duo",
|
|
71
|
+
"trio"
|
|
72
|
+
]
|
|
73
|
+
},
|
|
74
|
+
"genomicStudySubtype": {
|
|
75
|
+
"type": "string",
|
|
76
|
+
"description": "whether tumor and/or germ-line are tested",
|
|
77
|
+
"enum": [
|
|
78
|
+
"tumor-only",
|
|
79
|
+
"tumor+germline",
|
|
80
|
+
"germline-only"
|
|
81
|
+
]
|
|
82
|
+
},
|
|
83
|
+
"labName": {
|
|
84
|
+
"type": "string",
|
|
85
|
+
"description": "Name of the sequencing lab."
|
|
86
|
+
}
|
|
87
|
+
}
|
|
88
|
+
},
|
|
89
|
+
"donors": {
|
|
90
|
+
"type": "array",
|
|
91
|
+
"description": "List of donors including the index patient.",
|
|
92
|
+
"items": {
|
|
93
|
+
"type": "object",
|
|
94
|
+
"required": [
|
|
95
|
+
"caseId",
|
|
96
|
+
"sex",
|
|
97
|
+
"relation",
|
|
98
|
+
"mvConsentDate",
|
|
99
|
+
"mvConsentVersion",
|
|
100
|
+
"mvConsentScope",
|
|
101
|
+
"labData"
|
|
102
|
+
],
|
|
103
|
+
"properties": {
|
|
104
|
+
"caseId": {
|
|
105
|
+
"type": "string",
|
|
106
|
+
"description": "The VNg of the genomic data of the donor --> a unique 32-byte hex ID.",
|
|
107
|
+
"pattern": "^[a-fA-F0-9]{32}$"
|
|
108
|
+
},
|
|
109
|
+
"sex": {
|
|
110
|
+
"type": "string",
|
|
111
|
+
"description": "Sex of the donor.",
|
|
112
|
+
"enum": [
|
|
113
|
+
"male",
|
|
114
|
+
"female",
|
|
115
|
+
"other",
|
|
116
|
+
"unknown"
|
|
117
|
+
]
|
|
118
|
+
},
|
|
119
|
+
"relation": {
|
|
120
|
+
"type": "string",
|
|
121
|
+
"description": "Relationship of the donor in respect to the index patient, e.g. 'index', 'brother', 'mother', etc.",
|
|
122
|
+
"enum": [
|
|
123
|
+
"mother",
|
|
124
|
+
"father",
|
|
125
|
+
"brother",
|
|
126
|
+
"sister",
|
|
127
|
+
"child",
|
|
128
|
+
"self"
|
|
129
|
+
]
|
|
130
|
+
},
|
|
131
|
+
"mvConsentDate": {
|
|
132
|
+
"type": "string",
|
|
133
|
+
"description": "Date of the signature of the Modellvorhaben consent; Date in ISO 8601 format YYYY-MM-DD",
|
|
134
|
+
"format": "date"
|
|
135
|
+
},
|
|
136
|
+
"mvConsentPresentedDate": {
|
|
137
|
+
"type": "string",
|
|
138
|
+
"description": "Date of the presentation of the Modellvorhaben consent; Date in ISO 8601 format YYYY-MM-DD",
|
|
139
|
+
"format": "date"
|
|
140
|
+
},
|
|
141
|
+
"mvConsentVersion": {
|
|
142
|
+
"type": "string",
|
|
143
|
+
"description": "Version of the research consent"
|
|
144
|
+
},
|
|
145
|
+
"mvConsentScope": {
|
|
146
|
+
"type": "object",
|
|
147
|
+
"description": "The scope of the Modellvorhaben consent given by the donor.",
|
|
148
|
+
"required": [
|
|
149
|
+
"consentMvSequencing",
|
|
150
|
+
"consentCaseIdentification",
|
|
151
|
+
"consentReIdentification"
|
|
152
|
+
],
|
|
153
|
+
"properties": {
|
|
154
|
+
"consentMvSequencing": {
|
|
155
|
+
"type": "boolean",
|
|
156
|
+
"description": "The donor's consent to participate in the Modellvorhaben and sequencing."
|
|
157
|
+
},
|
|
158
|
+
"consentCaseIdentification": {
|
|
159
|
+
"type": "boolean",
|
|
160
|
+
"description": "The donor's consent to identify the case."
|
|
161
|
+
},
|
|
162
|
+
"consentReIdentification": {
|
|
163
|
+
"type": "boolean",
|
|
164
|
+
"description": "The donor's consent to be re-identified and to be re-contacted in case of new findings."
|
|
165
|
+
}
|
|
166
|
+
}
|
|
167
|
+
},
|
|
168
|
+
"mvConsentTerminationDate": {
|
|
169
|
+
"type": "string",
|
|
170
|
+
"description": "Date of the termination of the Modellvorhaben consent; Date in ISO 8601 format YYYY-MM-DD",
|
|
171
|
+
"format": "date"
|
|
172
|
+
},
|
|
173
|
+
"mvConsentTerminationScope": {
|
|
174
|
+
"type": "object",
|
|
175
|
+
"description": "The scope of the termination of the Modellvorhaben consent.",
|
|
176
|
+
"properties": {
|
|
177
|
+
"consentMvSequencingTermination": {
|
|
178
|
+
"type": "boolean",
|
|
179
|
+
"description": "The patient's termination of the Modellvorhaben consent to participate in the Modellvorhaben and sequencing"
|
|
180
|
+
},
|
|
181
|
+
"consentCaseIdentificationTermination": {
|
|
182
|
+
"type": "boolean",
|
|
183
|
+
"description": "The patient's termination of the Modellvorhaben consent to identify the case"
|
|
184
|
+
},
|
|
185
|
+
"consentReIdentificationTermination": {
|
|
186
|
+
"type": "boolean",
|
|
187
|
+
"description": "The patient's termination of the Modellvorhaben consent to re-identify the case and to re-contact the patient in case of new findings"
|
|
188
|
+
}
|
|
189
|
+
}
|
|
190
|
+
},
|
|
191
|
+
"researchConsentDate": {
|
|
192
|
+
"type": "string",
|
|
193
|
+
"description": "Date of the signature of the research consent; Date in ISO 8601 format YYYY-MM-DD",
|
|
194
|
+
"format": "date"
|
|
195
|
+
},
|
|
196
|
+
"researchConsentPresentedDate": {
|
|
197
|
+
"type": "string",
|
|
198
|
+
"description": "Date of the presentation of the research consent; Date in ISO 8601 format YYYY-MM-DD",
|
|
199
|
+
"format": "date"
|
|
200
|
+
},
|
|
201
|
+
"researchConsentVersion": {
|
|
202
|
+
"type": "string",
|
|
203
|
+
"description": "Version of the research consent"
|
|
204
|
+
},
|
|
205
|
+
"researchConsentScope": {
|
|
206
|
+
"type": "object",
|
|
207
|
+
"description": "Scope of the research consent given by the patient; shall be given in JSON format.",
|
|
208
|
+
"properties": {}
|
|
209
|
+
},
|
|
210
|
+
"researchConsentRevocationDate": {
|
|
211
|
+
"type": "string",
|
|
212
|
+
"description": "Date of the revocation of the research consent; Date in ISO 8601 format YYYY-MM-DD",
|
|
213
|
+
"format": "date"
|
|
214
|
+
},
|
|
215
|
+
"researchConsentRevocationScope": {
|
|
216
|
+
"type": "object",
|
|
217
|
+
"description": "Scope of the revocation of the research consent given by the patient; shall be given in JSON format",
|
|
218
|
+
"properties": {}
|
|
219
|
+
},
|
|
220
|
+
"labData": {
|
|
221
|
+
"type": "array",
|
|
222
|
+
"description": "Lab data related to the donor.",
|
|
223
|
+
"items": {
|
|
224
|
+
"type": "object",
|
|
225
|
+
"required": [
|
|
226
|
+
"labDataName",
|
|
227
|
+
"tissueOntology",
|
|
228
|
+
"tissueTypeId",
|
|
229
|
+
"tissueTypeName",
|
|
230
|
+
"sampleDate",
|
|
231
|
+
"sampleConservation",
|
|
232
|
+
"sequenceType",
|
|
233
|
+
"sequenceSubtype",
|
|
234
|
+
"fragmentationMethod",
|
|
235
|
+
"libraryType",
|
|
236
|
+
"libraryPrepKit",
|
|
237
|
+
"libraryPrepKitManufacturer",
|
|
238
|
+
"sequencerModel",
|
|
239
|
+
"sequencerManufacturer",
|
|
240
|
+
"kitName",
|
|
241
|
+
"kitManufacturer",
|
|
242
|
+
"enrichmentKitManufacturer",
|
|
243
|
+
"enrichmentKitDescription",
|
|
244
|
+
"barcode",
|
|
245
|
+
"sequencingLayout",
|
|
246
|
+
"sequenceData"
|
|
247
|
+
],
|
|
248
|
+
"properties": {
|
|
249
|
+
"labDataName": {
|
|
250
|
+
"type": "string",
|
|
251
|
+
"description": "Name/ID of the biospecimen e.g. 'Blut DNA normal'"
|
|
252
|
+
},
|
|
253
|
+
"tissueOntology": {
|
|
254
|
+
"type": "object",
|
|
255
|
+
"required": [
|
|
256
|
+
"name",
|
|
257
|
+
"version"
|
|
258
|
+
],
|
|
259
|
+
"properties": {
|
|
260
|
+
"name": {
|
|
261
|
+
"type": "string",
|
|
262
|
+
"description": "Name of the tissue ontology"
|
|
263
|
+
},
|
|
264
|
+
"version": {
|
|
265
|
+
"type": "string",
|
|
266
|
+
"description": "Version of the tissue ontology"
|
|
267
|
+
}
|
|
268
|
+
}
|
|
269
|
+
},
|
|
270
|
+
"tissueTypeId": {
|
|
271
|
+
"type": "string",
|
|
272
|
+
"description": "Tissue ID according to the ontology in use."
|
|
273
|
+
},
|
|
274
|
+
"tissueTypeName": {
|
|
275
|
+
"type": "string",
|
|
276
|
+
"description": "Tissue name according to the ontology in use."
|
|
277
|
+
},
|
|
278
|
+
"sampleDate": {
|
|
279
|
+
"type": "string",
|
|
280
|
+
"description": "Date of sample in ISO 8601 format YYYY-MM-DD",
|
|
281
|
+
"format": "date"
|
|
282
|
+
},
|
|
283
|
+
"sampleConservation": {
|
|
284
|
+
"type": "string",
|
|
285
|
+
"description": "Sample conservation",
|
|
286
|
+
"enum": [
|
|
287
|
+
"fresh-tissue",
|
|
288
|
+
"cryo-frozen",
|
|
289
|
+
"ffpe",
|
|
290
|
+
"other",
|
|
291
|
+
"unknown"
|
|
292
|
+
]
|
|
293
|
+
},
|
|
294
|
+
"sequenceType": {
|
|
295
|
+
"type": "string",
|
|
296
|
+
"description": "Type of sequence (DNA or RNA)",
|
|
297
|
+
"enum": [
|
|
298
|
+
"dna",
|
|
299
|
+
"rna"
|
|
300
|
+
]
|
|
301
|
+
},
|
|
302
|
+
"sequenceSubtype": {
|
|
303
|
+
"type": "string",
|
|
304
|
+
"description": "Subtype of sequence (germline, somatic, etc.)",
|
|
305
|
+
"enum": [
|
|
306
|
+
"germline",
|
|
307
|
+
"somatic",
|
|
308
|
+
"other",
|
|
309
|
+
"unknown"
|
|
310
|
+
]
|
|
311
|
+
},
|
|
312
|
+
"fragmentationMethod": {
|
|
313
|
+
"type": "string",
|
|
314
|
+
"description": "Fragmentation method",
|
|
315
|
+
"enum": [
|
|
316
|
+
"sonication",
|
|
317
|
+
"enzymatic",
|
|
318
|
+
"none",
|
|
319
|
+
"other",
|
|
320
|
+
"unknown"
|
|
321
|
+
]
|
|
322
|
+
},
|
|
323
|
+
"libraryType": {
|
|
324
|
+
"type": "string",
|
|
325
|
+
"description": "Library type",
|
|
326
|
+
"enum": [
|
|
327
|
+
"panel",
|
|
328
|
+
"wes",
|
|
329
|
+
"wgs",
|
|
330
|
+
"wgs_lr",
|
|
331
|
+
"wxs",
|
|
332
|
+
"other",
|
|
333
|
+
"unknown"
|
|
334
|
+
]
|
|
335
|
+
},
|
|
336
|
+
"libraryPrepKit": {
|
|
337
|
+
"type": "string",
|
|
338
|
+
"description": "Name/version of the library prepkit"
|
|
339
|
+
},
|
|
340
|
+
"libraryPrepKitManufacturer": {
|
|
341
|
+
"type": "string",
|
|
342
|
+
"description": "Library prep kit manufacturer"
|
|
343
|
+
},
|
|
344
|
+
"sequencerModel": {
|
|
345
|
+
"type": "string",
|
|
346
|
+
"description": "Name/version of the sequencer model"
|
|
347
|
+
},
|
|
348
|
+
"sequencerManufacturer": {
|
|
349
|
+
"type": "string",
|
|
350
|
+
"description": "Sequencer manufacturer"
|
|
351
|
+
},
|
|
352
|
+
"kitName": {
|
|
353
|
+
"type": "string",
|
|
354
|
+
"description": "Name/version of the sequencing kit"
|
|
355
|
+
},
|
|
356
|
+
"kitManufacturer": {
|
|
357
|
+
"type": "string",
|
|
358
|
+
"description": "Sequencing kit manufacturer"
|
|
359
|
+
},
|
|
360
|
+
"enrichmentKitManufacturer": {
|
|
361
|
+
"type": "string",
|
|
362
|
+
"description": "Manufacturer of the enrichment kit",
|
|
363
|
+
"enum": [
|
|
364
|
+
"Illumina",
|
|
365
|
+
"Agilent",
|
|
366
|
+
"Twist",
|
|
367
|
+
"NEB",
|
|
368
|
+
"other",
|
|
369
|
+
"unknown"
|
|
370
|
+
]
|
|
371
|
+
},
|
|
372
|
+
"enrichmentKitDescription": {
|
|
373
|
+
"type": "string",
|
|
374
|
+
"description": "Name/version of the enrichment kit"
|
|
375
|
+
},
|
|
376
|
+
"barcode": {
|
|
377
|
+
"type": "string",
|
|
378
|
+
"description": "The barcode used or 'na'"
|
|
379
|
+
},
|
|
380
|
+
"sequencingLayout": {
|
|
381
|
+
"type": "string",
|
|
382
|
+
"description": "The sequencing layout, aka the end type of sequencing.",
|
|
383
|
+
"enum": [
|
|
384
|
+
"single-end",
|
|
385
|
+
"paired-end",
|
|
386
|
+
"reverse",
|
|
387
|
+
"other"
|
|
388
|
+
]
|
|
389
|
+
},
|
|
390
|
+
"tumorCellCount": {
|
|
391
|
+
"type": "number",
|
|
392
|
+
"description": "Tumor cell count in %",
|
|
393
|
+
"minimum": 0,
|
|
394
|
+
"maximum": 100
|
|
395
|
+
},
|
|
396
|
+
"tumorCellCountMethod": {
|
|
397
|
+
"type": "string",
|
|
398
|
+
"description": "Method used to determine cell count.",
|
|
399
|
+
"enum": [
|
|
400
|
+
"Pathology",
|
|
401
|
+
"Bioinformatics",
|
|
402
|
+
"other",
|
|
403
|
+
"unknown"
|
|
404
|
+
]
|
|
405
|
+
},
|
|
406
|
+
"sequenceData": {
|
|
407
|
+
"type": "object",
|
|
408
|
+
"description": "Sequence data generated from the wet lab experiment.",
|
|
409
|
+
"required": [
|
|
410
|
+
"bioinformaticsPipelineName",
|
|
411
|
+
"bioinformaticsPipelineVersion",
|
|
412
|
+
"referenceGenome",
|
|
413
|
+
"percentBasesQ30",
|
|
414
|
+
"meanDepthOfCoverage",
|
|
415
|
+
"minCoverage",
|
|
416
|
+
"targetedRegionsAboveMinCoverage",
|
|
417
|
+
"files",
|
|
418
|
+
"readLength",
|
|
419
|
+
"nonCodingVariants",
|
|
420
|
+
"callerUsed"
|
|
421
|
+
],
|
|
422
|
+
"properties": {
|
|
423
|
+
"bioinformaticsPipelineName": {
|
|
424
|
+
"type": "string",
|
|
425
|
+
"description": "Name of the bioinformatics pipeline used"
|
|
426
|
+
},
|
|
427
|
+
"bioinformaticsPipelineVersion": {
|
|
428
|
+
"type": "string",
|
|
429
|
+
"description": "Version or commit hash of the bioinformatics pipeline"
|
|
430
|
+
},
|
|
431
|
+
"referenceGenome": {
|
|
432
|
+
"type": "string",
|
|
433
|
+
"description": "Reference genome used"
|
|
434
|
+
},
|
|
435
|
+
"percentBasesQ30": {
|
|
436
|
+
"type": "number",
|
|
437
|
+
"description": "Percentage of bases with Q30 or higher",
|
|
438
|
+
"minimum": 0,
|
|
439
|
+
"maximum": 100
|
|
440
|
+
},
|
|
441
|
+
"meanDepthOfCoverage": {
|
|
442
|
+
"type": "number",
|
|
443
|
+
"description": "Mean depth of coverage",
|
|
444
|
+
"minimum": 0
|
|
445
|
+
},
|
|
446
|
+
"minCoverage": {
|
|
447
|
+
"type": "number",
|
|
448
|
+
"description": "Minimum coverage",
|
|
449
|
+
"minimum": 0
|
|
450
|
+
},
|
|
451
|
+
"targetedRegionsAboveMinCoverage": {
|
|
452
|
+
"type": "number",
|
|
453
|
+
"description": "Fraction of targeted regions that are above minimum coverage",
|
|
454
|
+
"minimum": 0,
|
|
455
|
+
"maximum": 1
|
|
456
|
+
},
|
|
457
|
+
"readLength": {
|
|
458
|
+
"type": "integer",
|
|
459
|
+
"description": "The read length; in the case of long-read sequencing it is the rounded average read length.",
|
|
460
|
+
"minimum": 0
|
|
461
|
+
},
|
|
462
|
+
"nonCodingVariants": {
|
|
463
|
+
"type": "boolean",
|
|
464
|
+
"description": "The analysis includes non-coding variants -> true or false"
|
|
465
|
+
},
|
|
466
|
+
"callerUsed": {
|
|
467
|
+
"type": "array",
|
|
468
|
+
"description": "Caller that is used in the pipeline",
|
|
469
|
+
"items": {
|
|
470
|
+
"type": "object",
|
|
471
|
+
"required": [
|
|
472
|
+
"name",
|
|
473
|
+
"version"
|
|
474
|
+
],
|
|
475
|
+
"properties": {
|
|
476
|
+
"name": {
|
|
477
|
+
"type": "string",
|
|
478
|
+
"description": "Name of the caller used"
|
|
479
|
+
},
|
|
480
|
+
"version": {
|
|
481
|
+
"type": "string",
|
|
482
|
+
"description": "Version of the caller used"
|
|
483
|
+
}
|
|
484
|
+
}
|
|
485
|
+
}
|
|
486
|
+
},
|
|
487
|
+
"files": {
|
|
488
|
+
"type": "array",
|
|
489
|
+
"description": "List of files generated and required in this analysis.",
|
|
490
|
+
"items": {
|
|
491
|
+
"type": "object",
|
|
492
|
+
"required": [
|
|
493
|
+
"filePath",
|
|
494
|
+
"fileType",
|
|
495
|
+
"fileChecksum",
|
|
496
|
+
"fileSizeInBytes"
|
|
497
|
+
],
|
|
498
|
+
"properties": {
|
|
499
|
+
"filePath": {
|
|
500
|
+
"type": "string",
|
|
501
|
+
"description": "Path relative to the submission root, e.g.: sequencing_data/patient_001/patient_001_dna.bam"
|
|
502
|
+
},
|
|
503
|
+
"fileType": {
|
|
504
|
+
"type": "string",
|
|
505
|
+
"description": "Type of the file; if BED file is submitted, only 1 file is allowed.",
|
|
506
|
+
"enum": [
|
|
507
|
+
"bam",
|
|
508
|
+
"vcf",
|
|
509
|
+
"bed",
|
|
510
|
+
"fastq"
|
|
511
|
+
]
|
|
512
|
+
},
|
|
513
|
+
"checksumType": {
|
|
514
|
+
"type": "string",
|
|
515
|
+
"description": "Type of checksum algorithm used",
|
|
516
|
+
"enum": [
|
|
517
|
+
"sha256"
|
|
518
|
+
],
|
|
519
|
+
"default": "sha256"
|
|
520
|
+
},
|
|
521
|
+
"fileChecksum": {
|
|
522
|
+
"type": "string",
|
|
523
|
+
"description": "checksum of the file",
|
|
524
|
+
"pattern": "^[a-fA-F0-9]{64}$"
|
|
525
|
+
},
|
|
526
|
+
"fileSizeInBytes": {
|
|
527
|
+
"type": "number",
|
|
528
|
+
"description": "Size of the file in bytes",
|
|
529
|
+
"minimum": 0
|
|
530
|
+
},
|
|
531
|
+
"readOrder": {
|
|
532
|
+
"type": "string",
|
|
533
|
+
"enum": [
|
|
534
|
+
"R1",
|
|
535
|
+
"R2"
|
|
536
|
+
],
|
|
537
|
+
"description": "Indicates the read order for paired-end reads."
|
|
538
|
+
},
|
|
539
|
+
"flowcellId": {
|
|
540
|
+
"type": "string",
|
|
541
|
+
"description": "Indicates the flow cell."
|
|
542
|
+
},
|
|
543
|
+
"laneId": {
|
|
544
|
+
"type": "string",
|
|
545
|
+
"description": "Indicates the lane"
|
|
546
|
+
}
|
|
547
|
+
}
|
|
548
|
+
}
|
|
549
|
+
}
|
|
550
|
+
}
|
|
551
|
+
}
|
|
552
|
+
}
|
|
553
|
+
}
|
|
554
|
+
}
|
|
555
|
+
}
|
|
556
|
+
}
|
|
557
|
+
}
|
|
558
|
+
}
|
|
559
|
+
}
|
|
560
|
+
|