def getDataModelInstance(self, localId, dataPath):
# Return a VA set if it is one
if self._isAnnotated():
self._variantSet = variants.HtslibVariantSet(
self._dataset, "vs", self._dataPath, None)
return variants.HtslibVariantAnnotationSet(self._dataset, localId,
dataPath,
self._datarepo,
self._variantSet)
else:
return variants.HtslibVariantSet(self._dataset, localId, dataPath,
None)
def testThousandGenomesAnnotation(self):
variantAnnotationSet = \
variants.HtslibVariantAnnotationSet(
self._dataset,
"vas",
"tests/data/datasets/dataset1/variants/1kg.3.annotations",
self._backend, self._variantSet)
isAnnotated = variantAnnotationSet.isAnnotated(
"tests/data/datasets/dataset1/variants/1kg.3.annotations")
self.assertEqual(
isAnnotated,
True)
def setUp(self):
self._variantSetName = "testVariantSet"
self._backend = datarepo.FileSystemDataRepository("tests/data")
self._dataset = datasets.AbstractDataset(self._backend)
self._variantSet = variants.AbstractVariantSet(
self._dataset, self._variantSetName)
self._variantAnnotationSet = \
variants.HtslibVariantAnnotationSet(
self._dataset,
"vas",
"tests/data/datasets/dataset1/variants/WASH7P_annotation",
self._backend, self._variantSet)
def _readVariantAnnotationSetTable(self, cursor):
cursor.row_factory = sqlite3.Row
cursor.execute("SELECT * FROM VariantAnnotationSet;")
for row in cursor:
variantSet = self.getVariantSet(row[b'variantSetId'])
ontology = self.getOntology(row[b'ontologyId'])
variantAnnotationSet = variants.HtslibVariantAnnotationSet(
variantSet, row[b'name'])
variantAnnotationSet.setOntology(ontology)
variantAnnotationSet.populateFromRow(row)
assert variantAnnotationSet.getId() == row[b'id']
# Insert the variantAnnotationSet into the memory-based model.
variantSet.addVariantAnnotationSet(variantAnnotationSet)
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 __init__(self, localId, dataDir, dataRepository):
super(FileSystemDataset, self).__init__(localId)
self._dataDir = dataDir
self._setMetadata()
# Variants
variantSetDir = os.path.join(dataDir, self.variantsDirName)
for localId in os.listdir(variantSetDir):
relativePath = os.path.join(variantSetDir, localId)
if os.path.isdir(relativePath):
variantSet = variants.HtslibVariantSet(self, localId,
relativePath,
dataRepository)
self.addVariantSet(variantSet)
# Variant annotations sets
if variantSet.isAnnotated(relativePath):
variantAnnotationSet = variants.HtslibVariantAnnotationSet(
self, localId, relativePath, dataRepository,
variantSet)
self.addVariantAnnotationSet(variantAnnotationSet)
# Reads
readGroupSetDir = os.path.join(dataDir, self.readsDirName)
for filename in os.listdir(readGroupSetDir):
if fnmatch.fnmatch(filename, '*.bam'):
localId, _ = os.path.splitext(filename)
bamPath = os.path.join(readGroupSetDir, filename)
readGroupSet = reads.HtslibReadGroupSet(
self, localId, bamPath, dataRepository)
self.addReadGroupSet(readGroupSet)
# Sequence Annotations
featureSetDir = os.path.join(dataDir, self.featuresDirName)
for filename in os.listdir(featureSetDir):
if fnmatch.fnmatch(filename, '*.db'):
localId, _ = os.path.splitext(filename)
fullPath = os.path.join(featureSetDir, filename)
featureSet = sequenceAnnotations.Gff3DbFeatureSet(
self, localId, fullPath, dataRepository)
self.addFeatureSet(featureSet)