def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
term = protocol.OntologyTerm()
term.term = "male genotypic sex"
term.id = "PATO:0020001"
term.source_name = "PATO"
term.source_version = pb.string("2015-11-18")
# Write out a valid input
print(protocol.toJsonDict(term))
validIndividual = protocol.Individual(
name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
sex=term)
validIndividual.info['test'].values.add().string_value = 'test-info'
# pass through protocol creation
individual = bioMetadata.Individual(
dataset, "test")
individual.populateFromJson(protocol.toJson(validIndividual))
gaIndividual = individual.toProtocolElement()
# Verify elements exist
self.assertEqual(gaIndividual.created, validIndividual.created)
self.assertEqual(gaIndividual.updated, validIndividual.updated)
# Invalid input
invalidIndividual = '{"bad:", "json"}'
individual = bioMetadata.Individual(dataset, "test")
# Should fail
self.assertRaises(
exceptions.InvalidJsonException,
individual.populateFromJson,
invalidIndividual)
def testCreation(self):
dataset = datasets.Dataset('dataset1')
referenceSet = references.SimulatedReferenceSet("srs1")
localId = "variantAnnotationSetId"
simulatedVariantSet = variants.SimulatedVariantSet(
dataset,
referenceSet,
'variantSet1',
randomSeed=self.randomSeed,
numCalls=self.numCalls,
variantDensity=self.variantDensity)
simulatedVariantAnnotationSet = variants.SimulatedVariantAnnotationSet(
simulatedVariantSet, localId, self.randomSeed)
annotations = simulatedVariantAnnotationSet.getVariantAnnotations(
self.referenceName, self.startPosition, self.endPosition)
self.assertEquals(
simulatedVariantSet.toProtocolElement().id,
simulatedVariantAnnotationSet.toProtocolElement().variant_set_id,
"Variant Set ID should match the annotation's variant set ID")
for variant, ann in annotations:
self.assertEquals(
datetime.datetime.strptime(
ann.created,
"%Y-%m-%dT%H:%M:%S.%fZ").strftime("%Y-%m-%dT%H:%M:%S.%fZ"),
ann.created, "Expect time format to be in ISO8601")
self.assertEqual(variant.id, ann.variant_id)
def _getSimulatedVariantSet(self):
dataset = datasets.Dataset('dataset1')
referenceSet = references.SimulatedReferenceSet("srs1")
simulatedVariantSet = variants.SimulatedVariantSet(
dataset, referenceSet, 'variantSet1', randomSeed=self.randomSeed,
numCalls=self.numCalls, variantDensity=self.variantDensity)
return simulatedVariantSet
def testTopLevelIdsUnique(self):
datasetId = "a"
idStr = "b"
dataset = datasets.Dataset(datasetId)
readGroupSet = reads.AbstractReadGroupSet(dataset, idStr)
variantSet = variants.AbstractVariantSet(dataset, idStr)
self.assertNotEqual(readGroupSet.getId(), variantSet.getId())
def _readDatasetTable(self):
for datasetRecord in m.Dataset.select():
dataset = datasets.Dataset(datasetRecord.name)
dataset.populateFromRow(datasetRecord)
assert dataset.getId() == datasetRecord.id
# Insert the dataset into the memory-based object model.
self.addDataset(dataset)
def testGetDatasetByIndexBadIndex(self):
self.assertRaises(IndexError, self._dataRepo.getDatasetByIndex, 0)
self.assertRaises(TypeError, self._dataRepo.getDatasetByIndex, None)
self.assertRaises(TypeError, self._dataRepo.getDatasetByIndex, "")
datasetName = "ds"
dataset = datasets.Dataset(datasetName)
self._dataRepo.addDataset(dataset)
self.assertRaises(IndexError, self._dataRepo.getDatasetByIndex, 1)
def __init__(self, variantSetId, baseDir):
self._dataset = datasets.Dataset("ds")
super(VariantSetTest, self).__init__(variantSetId, baseDir)
self._variantRecords = []
self._reference_names = set()
# Read in all the VCF files in datadir and store each variant.
for vcfFile in glob.glob(os.path.join(self._dataPath, "*.vcf.gz")):
self._readVcf(vcfFile)
def __init__(self, rnaQuantificationLocalId, baseDir):
self._dataset = datasets.Dataset(_datasetName)
self._repo = datarepo.SqlDataRepository(paths.testDataRepo)
self._repo.open(datarepo.MODE_READ)
self._referenceSet = references.AbstractReferenceSet("test_rs")
rnaQuantificationId = rnaQuantificationLocalId[:-3] # remove '.db'
super(RnaQuantificationTest, self).__init__(rnaQuantificationId,
baseDir)
def testCreation(self):
dataset = datasets.Dataset('dataset1')
localId = "readGroupSetId"
referenceSet = references.SimulatedReferenceSet("srs1")
simulatedReadGroupSet = reads.SimulatedReadGroupSet(
dataset, localId, referenceSet)
for readGroup in simulatedReadGroupSet.getReadGroups():
alignments = list(readGroup.getReadAlignments())
self.assertGreater(len(alignments), 0)
def addDataset(self):
"""
Adds a new dataset into this repo.
"""
self._openRepo()
dataset = datasets.Dataset(self._args.datasetName)
dataset.setDescription(self._args.description)
dataset.setAttributes(json.loads(self._args.attributes))
self._updateRepo(self._repo.insertDataset, dataset)
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
validFusionDetection = protocol.FusionDetection(
name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
fusionDetectionId="n/a",
fusionDetectionIdTier=0,
sampleId="n/a",
sampleIdTier=0,
inHousePipeline="n/a",
inHousePipelineTier=0,
svDetection="n/a",
svDetectionTier=0,
fusionDetection="n/a",
fusionDetectionTier=0,
realignment="n/a",
realignmentTier=0,
annotation="n/a",
annotationTier=0,
genomeReference="n/a",
genomeReferenceTier=0,
geneModels="n/a",
geneModelsTier=0,
alignmentId="n/a",
alignmentIdTier=0,
site="n/a",
siteTier=0)
validFusionDetection.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
fusionDetection = pipeMetadata.FusionDetection(dataset, "test")
fusionDetection.populateFromJson(protocol.toJson(validFusionDetection))
gaFusionDetection = fusionDetection.toProtocolElement()
# Verify select elements exist
self.assertEqual(gaFusionDetection.created,
validFusionDetection.created)
self.assertEqual(gaFusionDetection.updated,
validFusionDetection.updated)
self.assertEqual(gaFusionDetection.fusionDetectionId,
validFusionDetection.fusionDetectionId)
self.assertEqual(gaFusionDetection.sampleId,
validFusionDetection.sampleId)
self.assertEqual(gaFusionDetection.site, validFusionDetection.site)
self.assertEqual(gaFusionDetection.fusionDetectionTier,
validFusionDetection.fusionDetectionTier)
# Invalid input
invalidFusionDetection = '{"bad:", "json"}'
fusionDetection = pipeMetadata.FusionDetection(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
fusionDetection.populateFromJson,
invalidFusionDetection)
def _createContinuousSet(self):
"""
Creates a ContinuousSet from the specified directory.
"""
self._continuousSetName = "testContinuous"
self._repo = datarepo.SqlDataRepository(paths.testDataRepo)
self._repo.open(datarepo.MODE_READ)
self._dataset = datasets.Dataset("testDs")
self._continuousSet = continuous.readSet(
self._dataset, self._continuousSetName)
def __init__(self, localId, dataPath):
self._backend = backend.Backend(datarepo.AbstractDataRepository())
self._referenceSet = None
self._dataset = datasets.Dataset("ds")
self._readGroupInfos = {}
self._readGroupSetInfo = None
self._samFile = pysam.AlignmentFile(dataPath)
self._readReferences()
super(ReadGroupSetTest, self).__init__(localId, dataPath)
self._readAlignmentInfo()
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
validExpressionAnalysis = protocol.ExpressionAnalysis(
name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
expressionAnalysisId="n/a",
expressionAnalysisIdTier=0,
sampleId="n/a",
sampleIdTier=0,
readLength="n/a",
readLengthTier=0,
reference="n/a",
referenceTier=0,
alignmentTool="n/a",
alignmentToolTier=0,
bamHandling="n/a",
bamHandlingTier=0,
expressionEstimation="n/a",
expressionEstimationTier=0,
sequencingId="n/a",
sequencingIdTier=0,
site="n/a",
siteTier=0)
validExpressionAnalysis.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
expressionAnalysis = pipeMetadata.ExpressionAnalysis(dataset, "test")
expressionAnalysis.populateFromJson(
protocol.toJson(validExpressionAnalysis))
gaExpressionAnalysis = expressionAnalysis.toProtocolElement()
# Verify select elements exist
self.assertEqual(gaExpressionAnalysis.created,
validExpressionAnalysis.created)
self.assertEqual(gaExpressionAnalysis.updated,
validExpressionAnalysis.updated)
self.assertEqual(gaExpressionAnalysis.expressionAnalysisId,
validExpressionAnalysis.expressionAnalysisId)
self.assertEqual(gaExpressionAnalysis.sampleId,
validExpressionAnalysis.sampleId)
self.assertEqual(gaExpressionAnalysis.site,
validExpressionAnalysis.site)
self.assertEqual(gaExpressionAnalysis.bamHandlingTier,
validExpressionAnalysis.bamHandlingTier)
# Invalid input
invalidExpressionAnalysis = '{"bad:", "json"}'
expressionAnalysis = pipeMetadata.ExpressionAnalysis(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
expressionAnalysis.populateFromJson,
invalidExpressionAnalysis)
def testAddOneDataset(self):
datasetName = "ds"
dataset = datasets.Dataset(datasetName)
self.assertEqual(self._dataRepo.getNumDatasets(), 0)
self.assertEqual(self._dataRepo.getDatasets(), [])
self._dataRepo.addDataset(dataset)
self.assertEqual(self._dataRepo.getNumDatasets(), 1)
self.assertEqual(self._dataRepo.getDatasets(), [dataset])
self.assertEqual(self._dataRepo.getDatasetByIndex(0), dataset)
self.assertEqual(self._dataRepo.getDatasetByName(datasetName), dataset)
self.assertEqual(self._dataRepo.getDataset(dataset.getId()), dataset)
def testAddMultipleDatasets(self):
firstDatasetName = "ds1"
firstDataset = datasets.Dataset(firstDatasetName)
secondDatasetName = "ds2"
secondDataset = datasets.Dataset(secondDatasetName)
self.assertEqual(self._dataRepo.getNumDatasets(), 0)
self.assertEqual(self._dataRepo.getDatasets(), [])
self._dataRepo.addDataset(firstDataset)
self._dataRepo.addDataset(secondDataset)
self.assertEqual(self._dataRepo.getNumDatasets(), 2)
self.assertEqual(self._dataRepo.getDatasets(),
[firstDataset, secondDataset])
self.assertEqual(self._dataRepo.getDatasetByIndex(0), firstDataset)
self.assertEqual(self._dataRepo.getDatasetByIndex(1), secondDataset)
self.assertEqual(self._dataRepo.getDatasetByName(firstDatasetName),
firstDataset)
self.assertEqual(self._dataRepo.getDatasetByName(secondDatasetName),
secondDataset)
self.assertEqual(self._dataRepo.getDataset(firstDataset.getId()),
firstDataset)
self.assertEqual(self._dataRepo.getDataset(secondDataset.getId()),
secondDataset)
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
validSurgery = protocol.Surgery(name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
patientId="PATIENT_TEST",
patientIdTier=0,
startDate="n/a",
startDateTier=0,
stopDate="n/a",
stopDateTier=0,
sampleId="n/a",
sampleIdTier=0,
collectionTimePoint="n/a",
collectionTimePointTier=0,
diagnosisDate="n/a",
diagnosisDateTier=0,
site="n/a",
siteTier=0,
type="n/a",
typeTier=0,
recordingDate="n/a",
recordingDateTier=0,
treatmentPlanId="n/a",
treatmentPlanIdTier=0,
courseNumber="1",
courseNumberTier=0)
validSurgery.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
surgery = clinMetadata.Surgery(dataset, "test")
surgery.populateFromJson(protocol.toJson(validSurgery))
gaSurgery = surgery.toProtocolElement()
# Verify select elements exist
self.assertEqual(gaSurgery.created, validSurgery.created)
self.assertEqual(gaSurgery.updated, validSurgery.updated)
self.assertEqual(gaSurgery.patientId, validSurgery.patientId)
self.assertEqual(gaSurgery.collectionTimePoint,
validSurgery.collectionTimePoint)
self.assertEqual(gaSurgery.recordingDate, validSurgery.recordingDate)
self.assertEqual(gaSurgery.treatmentPlanIdTier,
validSurgery.treatmentPlanIdTier)
# Invalid input
invalidSurgery = '{"bad:", "json"}'
surgery = clinMetadata.Surgery(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
surgery.populateFromJson, invalidSurgery)
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
validTreatment = protocol.Treatment(
name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
patientId="PATIENT_TEST",
patientIdTier=0,
courseNumber="n/a",
courseNumberTier=0,
therapeuticModality="n/a",
therapeuticModalityTier=0,
treatmentPlanType="n/a",
treatmentPlanTypeTier=0,
treatmentIntent="n/a",
treatmentIntentTier=0,
startDate="n/a",
startDateTier=0,
stopDate="n/a",
stopDateTier=0,
reasonForEndingTheTreatment="n/a",
reasonForEndingTheTreatmentTier=0,
responseToTreatment="n/a",
responseToTreatmentTier=0,
responseCriteriaUsed="n/a",
responseCriteriaUsedTier=0,
dateOfRecurrenceOrProgressionAfterThisTreatment="n/a",
dateOfRecurrenceOrProgressionAfterThisTreatmentTier=0,
unexpectedOrUnusualToxicityDuringTreatment="n/a",
unexpectedOrUnusualToxicityDuringTreatmentTier=0)
validTreatment.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
treatment = clinMetadata.Treatment(dataset, "test")
treatment.populateFromJson(protocol.toJson(validTreatment))
gaTreatment = treatment.toProtocolElement()
# Verify select elements exist
self.assertEqual(gaTreatment.created, validTreatment.created)
self.assertEqual(gaTreatment.updated, validTreatment.updated)
self.assertEqual(gaTreatment.patientId, validTreatment.patientId)
self.assertEqual(gaTreatment.courseNumber, validTreatment.courseNumber)
self.assertEqual(gaTreatment.startDate, validTreatment.startDate)
# Invalid input
invalidTreatment = '{"bad:", "json"}'
treatment = clinMetadata.Treatment(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
treatment.populateFromJson, invalidTreatment)
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
validSequencing = protocol.Sequencing(name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
sequencingId="Sequencing_TEST",
sequencingIdTier=0,
sampleId="Sample_test",
sampleIdTier=0,
dnaLibraryKit="n/a",
dnaLibraryKitTier=0,
dnaSeqPlatform="n/a",
dnaSeqPlatformTier=0,
dnaReadLength="n/a",
dnaReadLengthTier=0,
rnaLibraryKit="n/a",
rnaLibraryKitTier=0,
rnaSeqPlatform="n/a",
rnaSeqPlatformTier=0,
rnaReadLength="n/a",
rnaReadLengthTier=0,
pcrCycles="n/a",
pcrCyclesTier=0,
extractionId="n/a",
extractionIdTier=0,
site="Toronto",
siteTier=0)
validSequencing.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
sequencing = pipeMetadata.Sequencing(dataset, "test")
sequencing.populateFromJson(protocol.toJson(validSequencing))
gaSequencing = sequencing.toProtocolElement()
# Verify select elements exist
self.assertEqual(gaSequencing.created, validSequencing.created)
self.assertEqual(gaSequencing.updated, validSequencing.updated)
self.assertEqual(gaSequencing.sequencingId,
validSequencing.sequencingId)
self.assertEqual(gaSequencing.sampleId, validSequencing.sampleId)
self.assertEqual(gaSequencing.site, validSequencing.site)
self.assertEqual(gaSequencing.sampleIdTier,
validSequencing.sampleIdTier)
# Invalid input
invalidSequencing = '{"bad:", "json"}'
sequencing = pipeMetadata.Sequencing(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
sequencing.populateFromJson, invalidSequencing)
def getDataModelInstance(self, localId, dataPath):
dataset = datasets.Dataset("ds")
variantSet = variants.HtslibVariantSet(dataset, localId)
variantSet.populateFromDirectory(dataPath)
referenceSet = references.AbstractReferenceSet("rs")
variantSet.setReferenceSet(referenceSet)
if variantSet.isAnnotated():
sequenceOntology = ontologies.Ontology(paths.ontologyName)
sequenceOntology.populateFromFile(paths.ontologyPath)
annotationSet = variantSet.getVariantAnnotationSets()[0]
annotationSet.setOntology(sequenceOntology)
return annotationSet
else:
return variantSet
def __init__(self, featureSetLocalName, dataPath):
"""
:param localId: Name of the GFF3 resource corresponding to a pair
of files, .db and .gff3
:param dataPath: string representing full path to the .db file
:return:
"""
self._dataset = datasets.Dataset(_datasetName)
self._repo = datarepo.SqlDataRepository(paths.testDataRepo)
self._repo.open(datarepo.MODE_READ)
self._ontology = self._repo.getOntologyByName(paths.ontologyName)
self._referenceSet = references.AbstractReferenceSet("test_rs")
featureSetLocalName = featureSetLocalName[:-3] # remove '.db'
self._testData = _testDataForFeatureSetName[featureSetLocalName]
super(FeatureSetTests, self).__init__(featureSetLocalName, dataPath)
def _createVariantAnnotationSet(self, vcfDir):
"""
Creates a VariantAnnotationSet from the specified directory of
VCF files.
"""
self._variantSetName = "testVariantSet"
self._repo = datarepo.SqlDataRepository(paths.testDataRepo)
self._repo.open(datarepo.MODE_READ)
self._dataset = datasets.Dataset("testDs")
self._variantSet = variants.HtslibVariantSet(
self._dataset, self._variantSetName)
self._variantSet.populateFromDirectory(vcfDir)
self._variantAnnotationSet = variants.HtslibVariantAnnotationSet(
self._variantSet, "testVAs")
self._variantAnnotationSet.setOntology(
self._repo.getOntologyByName(paths.ontologyName))
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
validImmunotherapy = protocol.Immunotherapy(
name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
patientId="PATIENT_TEST",
patientIdTier=0,
startDate="n/a",
startDateTier=0,
immunotherapyType="n/a",
immunotherapyTypeTier=0,
immunotherapyTarget="n/a",
immunotherapyTargetTier=0,
immunotherapyDetail="n/a",
immunotherapyDetailTier=0,
treatmentPlanId="n/a",
treatmentPlanIdTier=0,
courseNumber="1",
courseNumberTier=0)
validImmunotherapy.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
immunotherapy = clinMetadata.Immunotherapy(dataset, "test")
immunotherapy.populateFromJson(protocol.toJson(validImmunotherapy))
gaImmunotherapy = immunotherapy.toProtocolElement()
# Verify select elements exist
self.assertEqual(gaImmunotherapy.created, validImmunotherapy.created)
self.assertEqual(gaImmunotherapy.updated, validImmunotherapy.updated)
self.assertEqual(gaImmunotherapy.patientId,
validImmunotherapy.patientId)
self.assertEqual(gaImmunotherapy.immunotherapyType,
validImmunotherapy.immunotherapyType)
self.assertEqual(gaImmunotherapy.immunotherapyDetailTier,
validImmunotherapy.immunotherapyDetailTier)
self.assertEqual(gaImmunotherapy.treatmentPlanId,
validImmunotherapy.treatmentPlanId)
# Invalid input
invalidImmunotherapy = '{"bad:", "json"}'
immunotherapy = clinMetadata.Immunotherapy(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
immunotherapy.populateFromJson, invalidImmunotherapy)
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
validLabtest = protocol.Labtest(
name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
patientId="PATIENT_TEST",
patientIdTier=0,
startDate="n/a",
startDateTier=0,
collectionDate="n/a",
collectionDateTier=0,
endDate="n/a",
endDateTier=0,
eventType="n/a",
eventTypeTier=0,
testResults="n/a",
testResultsTier=0,
timePoint="n/a",
timePointTier=0,
recordingDate="n/a",
recordingDateTier=0,
)
validLabtest.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
labtest = clinMetadata.Labtest(dataset, "test")
labtest.populateFromJson(protocol.toJson(validLabtest))
gaLabtest = labtest.toProtocolElement()
# Verify select elements exist
self.assertEqual(gaLabtest.created, validLabtest.created)
self.assertEqual(gaLabtest.updated, validLabtest.updated)
self.assertEqual(gaLabtest.patientId, validLabtest.patientId)
self.assertEqual(gaLabtest.eventType, validLabtest.eventType)
self.assertEqual(gaLabtest.collectionDate, validLabtest.collectionDate)
self.assertEqual(gaLabtest.recordingDateTier,
validLabtest.recordingDateTier)
# Invalid input
invalidLabtest = '{"bad:", "json"}'
labtest = clinMetadata.Labtest(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
labtest.populateFromJson, invalidLabtest)
def createRepo(self):
"""
Creates the repository for all the data we've just downloaded.
"""
repo = datarepo.SqlDataRepository(self.repoPath)
repo.open("w")
repo.initialise()
referenceSet = references.HtslibReferenceSet("GRCh37-subset")
referenceSet.populateFromFile(self.fastaFilePath)
referenceSet.setDescription("Subset of GRCh37 used for demonstration")
referenceSet.setSpeciesFromJson(
'{"id": "9606",' +
'"term": "H**o sapiens", "source_name": "NCBI"}')
for reference in referenceSet.getReferences():
reference.setSpeciesFromJson(
'{"id": "9606",' +
'"term": "H**o sapiens", "source_name": "NCBI"}')
reference.setSourceAccessions(
self.accessions[reference.getName()] + ".subset")
repo.insertReferenceSet(referenceSet)
dataset = datasets.Dataset("1kg-p3-subset")
dataset.setDescription("Sample data from 1000 Genomes phase 3")
repo.insertDataset(dataset)
variantSet = variants.HtslibVariantSet(dataset, "mvncall")
variantSet.setReferenceSet(referenceSet)
dataUrls = [vcfFile for vcfFile, _ in self.vcfFilePaths]
indexFiles = [indexFile for _, indexFile in self.vcfFilePaths]
variantSet.populateFromFile(dataUrls, indexFiles)
variantSet.checkConsistency()
repo.insertVariantSet(variantSet)
for sample, (bamFile, indexFile) in zip(self.samples,
self.bamFilePaths):
readGroupSet = reads.HtslibReadGroupSet(dataset, sample)
readGroupSet.populateFromFile(bamFile, indexFile)
readGroupSet.setReferenceSet(referenceSet)
repo.insertReadGroupSet(readGroupSet)
repo.commit()
repo.close()
self.log("Finished creating the repository; summary:\n")
repo.open("r")
repo.printSummary()
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
validCelltransplant = protocol.Celltransplant(
name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
patientId="PATIENT_TEST",
patientIdTier=0,
startDate="n/a",
startDateTier=0,
cellSource="n/a",
cellSourceTier=0,
donorType="n/a",
donorTypeTier=0,
treatmentPlanId="PATIENT_TEST_1",
treatmentPlanIdTier=0,
courseNumber="1",
courseNumberTier=0)
validCelltransplant.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
celltransplant = clinMetadata.Celltransplant(dataset, "test")
celltransplant.populateFromJson(protocol.toJson(validCelltransplant))
gaCelltransplant = celltransplant.toProtocolElement()
# Verify select elements exist
self.assertEqual(gaCelltransplant.created, validCelltransplant.created)
self.assertEqual(gaCelltransplant.updated, validCelltransplant.updated)
self.assertEqual(gaCelltransplant.patientId,
validCelltransplant.patientId)
self.assertEqual(gaCelltransplant.cellSource,
validCelltransplant.cellSource)
self.assertEqual(gaCelltransplant.courseNumber,
validCelltransplant.courseNumber)
self.assertEqual(gaCelltransplant.treatmentPlanId,
validCelltransplant.treatmentPlanId)
# Invalid input
invalidCelltransplant = '{"bad:", "json"}'
celltransplant = clinMetadata.Celltransplant(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
celltransplant.populateFromJson,
invalidCelltransplant)
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
validExtraction = protocol.Extraction(name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
extractionId="EXTRACTION_TEST",
extractionIdTier=0,
sampleId="n/a",
sampleIdTier=0,
rnaBlood="n/a",
rnaBloodTier=0,
dnaBlood="n/a",
dnaBloodTier=0,
rnaTissue="n/a",
rnaTissueTier=0,
dnaTissue="n/a",
dnaTissueTier=0,
site="Vancouver",
siteTier=0)
validExtraction.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
extraction = pipeMetadata.Extraction(dataset, "test")
extraction.populateFromJson(protocol.toJson(validExtraction))
gaExtraction = extraction.toProtocolElement()
# Verify select elements exist
self.assertEqual(gaExtraction.created, validExtraction.created)
self.assertEqual(gaExtraction.updated, validExtraction.updated)
self.assertEqual(gaExtraction.extractionId,
validExtraction.extractionId)
self.assertEqual(gaExtraction.sampleId, validExtraction.sampleId)
self.assertEqual(gaExtraction.site, validExtraction.site)
self.assertEqual(gaExtraction.sampleIdTier,
validExtraction.sampleIdTier)
# Invalid input
invalidExtraction = '{"bad:", "json"}'
extraction = pipeMetadata.Extraction(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
extraction.populateFromJson, invalidExtraction)
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
validComplication = protocol.Complication(
name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
patientId="PATIENT_TEST",
patientIdTier=0,
date="n/a",
dateTier=0,
lateComplicationOfTherapyDeveloped="n/a",
lateComplicationOfTherapyDevelopedTier=0,
lateToxicityDetail="n/a",
lateToxicityDetailTier=0,
suspectedTreatmentInducedNeoplasmDeveloped="n/a",
suspectedTreatmentInducedNeoplasmDevelopedTier=0,
treatmentInducedNeoplasmDetails="n/a",
treatmentInducedNeoplasmDetailsTier=0)
validComplication.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
complication = clinMetadata.Complication(dataset, "test")
complication.populateFromJson(protocol.toJson(validComplication))
gaComplication = complication.toProtocolElement()
# Verify select elements exist
self.assertEqual(gaComplication.created, validComplication.created)
self.assertEqual(gaComplication.updated, validComplication.updated)
self.assertEqual(gaComplication.patientId, validComplication.patientId)
self.assertEqual(gaComplication.date, validComplication.date)
self.assertEqual(gaComplication.lateToxicityDetail,
validComplication.lateToxicityDetail)
self.assertEqual(gaComplication.treatmentInducedNeoplasmDetailsTier,
validComplication.treatmentInducedNeoplasmDetailsTier)
# Invalid input
invalidComplication = '{"bad:", "json"}'
complication = clinMetadata.Complication(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
complication.populateFromJson, invalidComplication)
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
# Write out a valid input
validBiosample = protocol.Biosample(name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z")
validBiosample.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
biosample = bioMetadata.Biosample(dataset, "test")
biosample.populateFromJson(protocol.toJson(validBiosample))
gaBiosample = biosample.toProtocolElement()
# Verify elements exist
self.assertEqual(gaBiosample.created, validBiosample.created)
self.assertEqual(gaBiosample.updated, validBiosample.updated)
# Invalid input
invalidBiosample = '{"bad:", "json"}'
biosample = bioMetadata.Individual(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
biosample.populateFromJson, invalidBiosample)
def testToProtocolElement(self):
dataset = datasets.Dataset('dataset1')
validStudy = protocol.Study(name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z",
patientId="PATIENT_TEST",
patientIdTier=0,
startDate="n/a",
startDateTier=0,
endDate="n/a",
endDateTier=0,
status="n/a",
statusTier=0,
recordingDate="n/a",
recordingDateTier=0)
validStudy.attributes.attr['test']. \
values.add().string_value = 'test-info'
# pass through protocol creation
study = clinMetadata.Study(dataset, "test")
study.populateFromJson(protocol.toJson(validStudy))
gaStudy = study.toProtocolElement()
# Verify select elements exist
self.assertEqual(gaStudy.created, validStudy.created)
self.assertEqual(gaStudy.updated, validStudy.updated)
self.assertEqual(gaStudy.patientId, validStudy.patientId)
self.assertEqual(gaStudy.startDate, validStudy.startDate)
self.assertEqual(gaStudy.status, validStudy.status)
self.assertEqual(gaStudy.recordingDateTier,
validStudy.recordingDateTier)
# Invalid input
invalidStudy = '{"bad:", "json"}'
study = clinMetadata.Study(dataset, "test")
# Should fail
self.assertRaises(exceptions.InvalidJsonException,
study.populateFromJson, invalidStudy)