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 __init__(self,
localId,
referenceSet,
randomSeed=0,
numVariantSets=1,
numCalls=1,
variantDensity=0.5,
numReadGroupSets=1,
numReadGroupsPerReadGroupSet=1,
numAlignments=1,
numFeatureSets=1,
numPhenotypeAssociationSets=1,
numPhenotypeAssociations=2,
numRnaQuantSets=2,
numExpressionLevels=2):
super(SimulatedDataset, self).__init__(localId)
self._description = "Simulated dataset {}".format(localId)
for i in range(numPhenotypeAssociationSets):
localId = "simPas{}".format(i)
seed = randomSeed + i
phenotypeAssociationSet = g2p.SimulatedPhenotypeAssociationSet(
self, localId, seed, numPhenotypeAssociations)
self.addPhenotypeAssociationSet(phenotypeAssociationSet)
# TODO create a simulated Ontology
# Variants
for i in range(numVariantSets):
localId = "simVs{}".format(i)
seed = randomSeed + i
variantSet = variants.SimulatedVariantSet(self, referenceSet,
localId, seed, numCalls,
variantDensity)
callSets = variantSet.getCallSets()
# Add biosamples
for callSet in callSets:
bioSample = biodata.BioSample(self, callSet.getLocalId())
bioSample2 = biodata.BioSample(self,
callSet.getLocalId() + "2")
individual = biodata.Individual(self, callSet.getLocalId())
bioSample.setIndividualId(individual.getId())
bioSample2.setIndividualId(individual.getId())
self.addIndividual(individual)
self.addBioSample(bioSample)
self.addBioSample(bioSample2)
self.addVariantSet(variantSet)
variantAnnotationSet = variants.SimulatedVariantAnnotationSet(
variantSet, "simVas{}".format(i), seed)
variantSet.addVariantAnnotationSet(variantAnnotationSet)
# Reads
for i in range(numReadGroupSets):
localId = 'simRgs{}'.format(i)
seed = randomSeed + i
readGroupSet = reads.SimulatedReadGroupSet(
self, localId, referenceSet, seed,
numReadGroupsPerReadGroupSet, numAlignments)
for rg in readGroupSet.getReadGroups():
bioSample = biodata.BioSample(self, rg.getLocalId())
individual = biodata.Individual(self, rg.getLocalId())
bioSample.setIndividualId(individual.getId())
rg.setBioSampleId(bioSample.getId())
self.addIndividual(individual)
self.addBioSample(bioSample)
self.addReadGroupSet(readGroupSet)
# Features
for i in range(numFeatureSets):
localId = "simFs{}".format(i)
seed = randomSeed + i
featureSet = sequence_annotations.SimulatedFeatureSet(
self, localId, seed)
featureSet.setReferenceSet(referenceSet)
self.addFeatureSet(featureSet)
# RnaQuantificationSets
for i in range(numRnaQuantSets):
localId = 'simRqs{}'.format(i)
rnaQuantSet = rnaQuantification.SimulatedRnaQuantificationSet(
self, localId)
rnaQuantSet.setReferenceSet(referenceSet)
self.addRnaQuantificationSet(rnaQuantSet)