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 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 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 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 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.setInfo(json.loads(self._args.info))
self._updateRepo(self._repo.insertDataset, dataset)
def _readDatasetTable(self, cursor):
cursor.row_factory = sqlite3.Row
cursor.execute("SELECT * FROM Dataset;")
for row in cursor:
dataset = datasets.Dataset(row[b'name'])
dataset.populateFromRow(row)
assert dataset.getId() == row[b"id"]
# Insert the dataset into the memory-based object model.
self.addDataset(dataset)
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 _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 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 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 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.setNcbiTaxonId(9606)
for reference in referenceSet.getReferences():
reference.setNcbiTaxonId(9606)
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')
# Write out a valid input
validBioSample = protocol.BioSample(name="test",
created="2016-05-19T21:00:19Z",
updated="2016-05-19T21:00:19Z")
validBioSample.info['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 setUp(self):
self._featureSetName = "testFeatureSet"
self._dataset = datasets.Dataset("test_ds")
self._featureSet = features.AbstractFeatureSet(self._dataset,
self._featureSetName)
def setUp(self):
self._variantSetName = "testVariantSet"
self._dataset = datasets.Dataset("datasetId")
self._variantSet = variants.AbstractVariantSet(self._dataset,
self._variantSetName)
def setUp(self):
self.testDataDir = "tests/faultydata/variants"
self.dataset = datasets.Dataset('dataset1')
def run(self):
if not os.path.exists(self.outputDirectory):
os.makedirs(self.outputDirectory)
self.repo.open("w")
self.repo.initialise()
referenceFileName = "ref_brca1.fa"
inputRef = os.path.join(self.inputDirectory, referenceFileName)
outputRef = os.path.join(self.outputDirectory, referenceFileName)
shutil.copy(inputRef, outputRef)
fastaFilePath = os.path.join(self.outputDirectory,
referenceFileName + '.gz')
pysam.tabix_compress(outputRef, fastaFilePath)
with open(os.path.join(self.inputDirectory,
"ref_brca1.json")) as refMetadataFile:
refMetadata = json.load(refMetadataFile)
with open(os.path.join(self.inputDirectory,
"referenceset_hg37.json")) as refMetadataFile:
refSetMetadata = json.load(refMetadataFile)
referenceSet = references.HtslibReferenceSet(
refSetMetadata['assemblyId'])
referenceSet.populateFromFile(fastaFilePath)
referenceSet.setAssemblyId(refSetMetadata['assemblyId'])
referenceSet.setDescription(refSetMetadata['description'])
referenceSet.setNcbiTaxonId(refSetMetadata['ncbiTaxonId'])
referenceSet.setIsDerived(refSetMetadata['isDerived'])
referenceSet.setSourceUri(refSetMetadata['sourceUri'])
referenceSet.setSourceAccessions(refSetMetadata['sourceAccessions'])
for reference in referenceSet.getReferences():
reference.setNcbiTaxonId(refMetadata['ncbiTaxonId'])
reference.setSourceAccessions(refMetadata['sourceAccessions'])
self.repo.insertReferenceSet(referenceSet)
dataset = datasets.Dataset("brca1")
# Some info is set, it isn't important what
dataset.setInfo({"version": ga4gh.__version__})
self.repo.insertDataset(dataset)
hg00096Individual = biodata.Individual(dataset, "HG00096")
with open(os.path.join(self.inputDirectory,
"individual_HG00096.json")) as jsonString:
hg00096Individual.populateFromJson(jsonString.read())
self.repo.insertIndividual(hg00096Individual)
hg00096BioSample = biodata.BioSample(dataset, "HG00096")
with open(os.path.join(self.inputDirectory,
"bioSample_HG00096.json")) as jsonString:
hg00096BioSample.populateFromJson(jsonString.read())
hg00096BioSample.setIndividualId(hg00096Individual.getId())
self.repo.insertBioSample(hg00096BioSample)
hg00099Individual = biodata.Individual(dataset, "HG00099")
with open(os.path.join(self.inputDirectory,
"individual_HG00099.json")) as jsonString:
hg00099Individual.populateFromJson(jsonString.read())
self.repo.insertIndividual(hg00099Individual)
hg00099BioSample = biodata.BioSample(dataset, "HG00099")
with open(os.path.join(self.inputDirectory,
"bioSample_HG00099.json")) as jsonString:
hg00099BioSample.populateFromJson(jsonString.read())
hg00099BioSample.setIndividualId(hg00099Individual.getId())
self.repo.insertBioSample(hg00099BioSample)
hg00101Individual = biodata.Individual(dataset, "HG00101")
with open(os.path.join(self.inputDirectory,
"individual_HG00101.json")) as jsonString:
hg00101Individual.populateFromJson(jsonString.read())
self.repo.insertIndividual(hg00101Individual)
hg00101BioSample = biodata.BioSample(dataset, "HG00101")
with open(os.path.join(self.inputDirectory,
"bioSample_HG00101.json")) as jsonString:
hg00101BioSample.populateFromJson(jsonString.read())
hg00101BioSample.setIndividualId(hg00101Individual.getId())
self.repo.insertBioSample(hg00101BioSample)
readFiles = [
"brca1_HG00096.sam", "brca1_HG00099.sam", "brca1_HG00101.sam"
]
for readFile in readFiles:
name = readFile.split('_')[1].split('.')[0]
readSrc = pysam.AlignmentFile(
os.path.join(self.inputDirectory, readFile), "r")
readDest = pysam.AlignmentFile(os.path.join(
self.outputDirectory, name + ".bam"),
"wb",
header=readSrc.header)
destFilePath = readDest.filename
for readData in readSrc:
readDest.write(readData)
readDest.close()
readSrc.close()
pysam.index(destFilePath)
readGroupSet = reads.HtslibReadGroupSet(dataset, name)
readGroupSet.populateFromFile(destFilePath, destFilePath + ".bai")
readGroupSet.setReferenceSet(referenceSet)
dataset.addReadGroupSet(readGroupSet)
bioSamples = [hg00096BioSample, hg00099BioSample, hg00101BioSample]
for readGroup in readGroupSet.getReadGroups():
for bioSample in bioSamples:
if bioSample.getLocalId() == readGroup.getSampleName():
readGroup.setBioSampleId(bioSample.getId())
self.repo.insertReadGroupSet(readGroupSet)
ontologyMapFileName = "so-xp-simple.obo"
inputOntologyMap = os.path.join(self.inputDirectory,
ontologyMapFileName)
outputOntologyMap = os.path.join(self.outputDirectory,
ontologyMapFileName)
shutil.copy(inputOntologyMap, outputOntologyMap)
sequenceOntology = ontologies.Ontology("so-xp-simple")
sequenceOntology.populateFromFile(outputOntologyMap)
sequenceOntology._id = "so-xp-simple"
self.repo.insertOntology(sequenceOntology)
self.repo.addOntology(sequenceOntology)
vcfFiles = [
"brca1_1kgPhase3_variants.vcf", "brca1_WASH7P_annotation.vcf",
"brca1_OR4F_annotation.vcf"
]
for vcfFile in vcfFiles:
self.addVariantSet(vcfFile, dataset, referenceSet,
sequenceOntology, bioSamples)
# Sequence annotations
seqAnnFile = "brca1_gencodev19.gff3"
seqAnnSrc = os.path.join(self.inputDirectory, seqAnnFile)
seqAnnDest = os.path.join(self.outputDirectory, "gencodev19.db")
dbgen = generate_gff3_db.Gff32Db(seqAnnSrc, seqAnnDest)
dbgen.run()
gencode = sequence_annotations.Gff3DbFeatureSet(dataset, "gencodev19")
gencode.setOntology(sequenceOntology)
gencode.populateFromFile(seqAnnDest)
gencode.setReferenceSet(referenceSet)
self.repo.insertFeatureSet(gencode)
# add g2p featureSet
g2pPath = os.path.join(self.inputDirectory, "cgd")
# copy all files input directory to output path
outputG2PPath = os.path.join(self.outputDirectory, "cgd")
os.makedirs(outputG2PPath)
for filename in glob.glob(os.path.join(g2pPath, '*.*')):
shutil.copy(filename, outputG2PPath)
featuresetG2P = g2p_featureset.PhenotypeAssociationFeatureSet(
dataset, outputG2PPath)
featuresetG2P.setOntology(sequenceOntology)
featuresetG2P.setReferenceSet(referenceSet)
featuresetG2P.populateFromFile(outputG2PPath)
self.repo.insertFeatureSet(featuresetG2P)
# add g2p phenotypeAssociationSet
phenotypeAssociationSet = g2p_associationset\
.RdfPhenotypeAssociationSet(dataset, "cgd", outputG2PPath)
self.repo.insertPhenotypeAssociationSet(phenotypeAssociationSet)
self.repo.commit()
dataset.addFeatureSet(gencode)
# RNA Quantification
rnaDbName = os.path.join(self.outputDirectory, "rnaseq.db")
store = rnaseq2ga.RnaSqliteStore(rnaDbName)
store.createTables()
rnaseq2ga.rnaseq2ga(self.inputDirectory + "/rna_brca1.tsv",
rnaDbName,
"rna_brca1.tsv",
"rsem",
featureType="transcript",
readGroupSetNames="HG00096",
featureSetNames="gencodev19",
dataset=dataset)
rnaQuantificationSet = rna_quantification.SqliteRnaQuantificationSet(
dataset, "rnaseq")
rnaQuantificationSet.setReferenceSet(referenceSet)
rnaQuantificationSet.populateFromFile(rnaDbName)
self.repo.insertRnaQuantificationSet(rnaQuantificationSet)
self.repo.commit()
def getDataset(self):
return datasets.Dataset("dataset")
def run(self):
if not os.path.exists(self.outputDirectory):
os.makedirs(self.outputDirectory)
self.repo.open("w")
self.repo.initialise()
referenceFileName = "ref_brca1.fa"
inputRef = os.path.join(
self.inputDirectory, referenceFileName)
outputRef = os.path.join(
self.outputDirectory, referenceFileName)
shutil.copy(inputRef, outputRef)
fastaFilePath = os.path.join(
self.outputDirectory,
referenceFileName + '.gz')
pysam.tabix_compress(
outputRef, fastaFilePath)
with open(
os.path.join(
self.inputDirectory, "ref_brca1.json")) as refMetadataFile:
refMetadata = json.load(refMetadataFile)
with open(
os.path.join(
self.inputDirectory,
"referenceset_hg37.json")) as refMetadataFile:
refSetMetadata = json.load(refMetadataFile)
referenceSet = references.HtslibReferenceSet(
refSetMetadata['assemblyId'])
referenceSet.populateFromFile(fastaFilePath)
referenceSet.setAssemblyId(refSetMetadata['assemblyId'])
referenceSet.setDescription(refSetMetadata['description'])
referenceSet.setNcbiTaxonId(refSetMetadata['ncbiTaxonId'])
referenceSet.setIsDerived(refSetMetadata['isDerived'])
referenceSet.setSourceUri(refSetMetadata['sourceUri'])
referenceSet.setSourceAccessions(refSetMetadata['sourceAccessions'])
for reference in referenceSet.getReferences():
reference.setNcbiTaxonId(refMetadata['ncbiTaxonId'])
reference.setSourceAccessions(
refMetadata['sourceAccessions'])
self.repo.insertReferenceSet(referenceSet)
dataset = datasets.Dataset("brca1")
self.repo.insertDataset(dataset)
hg00096Individual = biodata.Individual(dataset, "HG00096")
with open(
os.path.join(
self.inputDirectory,
"individual_HG00096.json")) as jsonString:
hg00096Individual.populateFromJson(jsonString.read())
self.repo.insertIndividual(hg00096Individual)
hg00096BioSample = biodata.BioSample(dataset, "HG00096")
with open(
os.path.join(
self.inputDirectory,
"bioSample_HG00096.json")) as jsonString:
hg00096BioSample.populateFromJson(jsonString.read())
hg00096BioSample.setIndividualId(hg00096Individual.getId())
self.repo.insertBioSample(hg00096BioSample)
hg00099Individual = biodata.Individual(dataset, "HG00099")
with open(
os.path.join(
self.inputDirectory,
"individual_HG00099.json")) as jsonString:
hg00099Individual.populateFromJson(jsonString.read())
self.repo.insertIndividual(hg00099Individual)
hg00099BioSample = biodata.BioSample(dataset, "HG00099")
with open(
os.path.join(
self.inputDirectory,
"bioSample_HG00099.json")) as jsonString:
hg00099BioSample.populateFromJson(jsonString.read())
hg00099BioSample.setIndividualId(hg00099Individual.getId())
self.repo.insertBioSample(hg00099BioSample)
hg00101Individual = biodata.Individual(dataset, "HG00101")
with open(
os.path.join(
self.inputDirectory,
"individual_HG00101.json")) as jsonString:
hg00101Individual.populateFromJson(jsonString.read())
self.repo.insertIndividual(hg00101Individual)
hg00101BioSample = biodata.BioSample(dataset, "HG00101")
with open(
os.path.join(
self.inputDirectory,
"bioSample_HG00101.json")) as jsonString:
hg00101BioSample.populateFromJson(jsonString.read())
hg00101BioSample.setIndividualId(hg00101Individual.getId())
self.repo.insertBioSample(hg00101BioSample)
readFiles = [
"brca1_HG00096.sam",
"brca1_HG00099.sam",
"brca1_HG00101.sam"]
for readFile in readFiles:
name = readFile.split('_')[1].split('.')[0]
readSrc = pysam.AlignmentFile(
os.path.join(self.inputDirectory, readFile), "r")
readDest = pysam.AlignmentFile(
os.path.join(
self.outputDirectory,
name + ".bam"),
"wb", header=readSrc.header)
destFilePath = readDest.filename
for readData in readSrc:
readDest.write(readData)
readDest.close()
readSrc.close()
pysam.index(destFilePath)
readGroupSet = reads.HtslibReadGroupSet(dataset, name)
readGroupSet.populateFromFile(destFilePath, destFilePath + ".bai")
readGroupSet.setReferenceSet(referenceSet)
bioSamples = [hg00096BioSample, hg00099BioSample, hg00101BioSample]
for readGroup in readGroupSet.getReadGroups():
for bioSample in bioSamples:
if bioSample.getLocalId() == readGroup.getSampleName():
readGroup.setBioSampleId(bioSample.getId())
self.repo.insertReadGroupSet(readGroupSet)
ontologyMapFileName = "so-xp-simple.obo"
inputOntologyMap = os.path.join(
self.inputDirectory, ontologyMapFileName)
outputOntologyMap = os.path.join(
self.outputDirectory, ontologyMapFileName)
shutil.copy(inputOntologyMap, outputOntologyMap)
sequenceOntology = ontologies.Ontology("so-xp-simple")
sequenceOntology.populateFromFile(outputOntologyMap)
sequenceOntology._id = "so-xp-simple"
self.repo.insertOntology(sequenceOntology)
self.repo.addOntology(sequenceOntology)
vcfFiles = [
"brca1_1kgPhase3_variants.vcf",
"brca1_WASH7P_annotation.vcf",
"brca1_OR4F_annotation.vcf"]
for vcfFile in vcfFiles:
self.addVariantSet(
vcfFile,
dataset,
referenceSet,
sequenceOntology,
bioSamples)
seqAnnFile = "brca1_gencodev19.gff3"
seqAnnSrc = os.path.join(self.inputDirectory, seqAnnFile)
seqAnnDest = os.path.join(self.outputDirectory, "gencodev19.db")
dbgen = generate_gff3_db.Gff32Db(seqAnnSrc, seqAnnDest)
dbgen.run()
gencode = sequenceAnnotations.Gff3DbFeatureSet(dataset, "gencodev19")
gencode.setOntology(sequenceOntology)
gencode.populateFromFile(seqAnnDest)
gencode.setReferenceSet(referenceSet)
self.repo.insertFeatureSet(gencode)
self.repo.commit()
print("Done converting compliance data.", file=sys.stderr)
def setUp(self):
self._featureSetName = "testFeatureSet"
self._dataset = datasets.Dataset("test_ds")
self._featureSet = sequence_annotations.AbstractFeatureSet(
self._dataset, self._featureSetName)
def __init__(self, localId, baseDir):
self._dataset = datasets.Dataset("ds")
super(PhenotypeAssociationSetTest, self).__init__(localId, baseDir)
self.phenotypeAssocationSet = self.getDataModelInstance(
localId, baseDir)
