def cleanEventTree(experiment):
tree = MultiCactusTree(experiment.getTree())
tree.nameUnlabeledInternalNodes()
for node in tree.breadthFirstTraversal():
if tree.hasName(node):
name = tree.getName(node)
if '.' in name:
newName = name.replace('.', '_')
sys.stderr.write('WARNING renaming event %s to %s\n' %(name, newName))
tree.setName(node, newName)
name = newName
parent = tree.getParent(node)
if parent is not None:
weight = tree.getWeight(parent, node)
if weight is None:
raise RuntimeError('Missing branch length in species_tree tree')
redoPrefix = True
newSuffix = 0
while redoPrefix is True:
redoPrefix = False
for node1 in tree.breadthFirstTraversal():
name1 = tree.getName(node1)
for node2 in tree.breadthFirstTraversal():
name2 = tree.getName(node2)
if node1 != node2 and name1 == name2:
newName = "%s%i" % (name2, newSuffix)
newSuffix += 1
tree.setName(node2, newName)
sys.stderr.write('WARNING renaming event %s to %s\n' % (
name2, newName))
redoPrefix = True
experiment.xmlRoot.attrib["species_tree"] = NXNewick().writeString(tree)
experiment.seqMap = experiment.buildSequenceMap()
def cleanEventTree(experiment):
tree = MultiCactusTree(experiment.getTree())
tree.nameUnlabeledInternalNodes()
for node in tree.breadthFirstTraversal():
if tree.hasName(node):
name = tree.getName(node)
if '.' in name:
newName = name.replace('.', '_')
sys.stderr.write('WARNING renaming event %s to %s\n' %(name, newName))
tree.setName(node, newName)
name = newName
parent = tree.getParent(node)
if parent is not None:
weight = tree.getWeight(parent, node)
if weight is None:
raise RuntimeError('Missing branch length in species_tree tree')
redoPrefix = True
newSuffix = 0
while redoPrefix is True:
redoPrefix = False
for node1 in tree.breadthFirstTraversal():
name1 = tree.getName(node1)
for node2 in tree.breadthFirstTraversal():
name2 = tree.getName(node2)
if node1 != node2 and name1 == name2:
newName = "%s%i" % (name2, newSuffix)
newSuffix += 1
tree.setName(node2, newName)
sys.stderr.write('WARNING renaming event %s to %s\n' % (
name2, newName))
redoPrefix = True
experiment.xmlRoot.attrib["species_tree"] = NXNewick().writeString(tree)
experiment.seqMap = experiment.buildSequenceMap()
def setUp(self):
unittest.TestCase.setUp(self)
self.trees = randomTreeSet()
self.mcTrees = []
self.tempDir = getTempDirectory(os.getcwd())
self.tempFa = os.path.join(self.tempDir, "seq.fa")
with open(self.tempFa, "w") as f:
f.write(">temp\nNNNNNNNCNNNNAAAAAAAAAAAAAAANNNNNNN\n")
self.dummySeqMaps = []
for tree in self.trees:
if tree.size() < 50:
mcTree = MultiCactusTree(tree)
seqMap = dict()
for i in mcTree.breadthFirstTraversal():
mcTree.setName(i, "Node%s" % str(i))
seqMap["Node%s" % str(i)] = self.tempFa
mcTree.computeSubtreeRoots()
mcTree.nameUnlabeledInternalNodes()
self.mcTrees.append(mcTree)
self.dummySeqMaps.append(seqMap)
# Boreoeutherian tree
borTree = '((((HUMAN:0.006969,CHIMP:0.009727)Anc7:0.025291,BABOON:0.044568)Anc6:0.11,(MOUSE:0.072818,RAT:0.081244)Anc5:0.260342)Anc4:0.023260,((DOG:0.07,CAT:0.07)Anc3:0.087381,(PIG:0.06,COW:0.06)Anc2:0.104728)Anc1:0.04)Anc0;'
self.borMcTree = MultiCactusTree(NXNewick().parseString(
borTree, addImpliedRoots=False))
self.borMcTree.computeSubtreeRoots()
self.borMcTree.nameUnlabeledInternalNodes()
self.mcTrees.append(self.borMcTree)
# Eutherian backbone tree
backbone = '(((((((((((Homo_sapiens:0.00655,Pan_troglodytes:0.00684):0.00422,Gorilla_gorilla_gorilla:0.008964):0.009693,Pongo_abelii:0.01894):0.015511,Macaca_mulatta:0.043601):0.08444,Aotus_nancymaae:0.08):0.08,Microcebus_murinus:0.10612):0.043494,Galeopterus_variegatus:0.134937):0.04,((((Jaculus_jaculus:0.1,(Microtus_ochrogaster:0.14,(Mus_musculus:0.084509,Rattus_norvegicus:0.091589):0.047773):0.06015):0.122992,(Heterocephalus_glaber:0.1,(Cavia_porcellus:0.065629,(Chinchilla_lanigera:0.06,Octodon_degus:0.1):0.06):0.05):0.06015):0.05,Marmota_marmota:0.1):0.05,Oryctolagus_cuniculus:0.21569):0.04):0.040593,(((Sus_scrofa:0.12,(Orcinus_orca:0.069688,(Bos_taurus:0.04,Capra_hircus:0.04):0.09):0.045488):0.02,((Equus_caballus:0.109397,(Felis_catus:0.098612,(Canis_lupus_familiaris:0.052458,Mustela_putorius_furo:0.08):0.02):0.049845):0.02,(Pteropus_alecto:0.1,Eptesicus_fuscus:0.08):0.033706):0.03):0.025,Erinaceus_europaeus:0.278178):0.021227):0.023664,(((Loxodonta_africana:0.022242,Procavia_capensis:0.145358):0.076687,Chrysochloris_asiatica:0.04):0.05,Dasypus_novemcinctus:0.169809):0.02)backbone_root:0.234728,(Monodelphis_domestica:0.125686,Sarcophilus_harrisii:0.12):0.2151);'
self.backboneTree = MultiCactusTree(NXNewick().parseString(
backbone, addImpliedRoots=False))
self.backboneTree.computeSubtreeRoots()
self.backboneTree.nameUnlabeledInternalNodes()
self.mcTrees.append(self.backboneTree)
seqLens = dict()
seqLens["HUMAN"] = 57553
seqLens["CHIMP"] = 57344
seqLens["BABOON"] = 58960
seqLens["MOUSE"] = 32750
seqLens["RAT"] = 38436
seqLens["DOG"] = 54187
seqLens["CAT"] = 50283
seqLens["PIG"] = 54843
seqLens["COW"] = 55508
self.blanchetteSeqMap = dict()
for event, seqLen in seqLens.items():
p = os.path.join(self.tempDir, event + ".fa")
with open(p, "w") as f:
f.write(">%s\n" % event)
f.write(''.join(['A'] * seqLen))
f.write('\n')
self.blanchetteSeqMap[event] = p
def setUp(self):
unittest.TestCase.setUp(self)
self.trees = randomTreeSet()
self.mcTrees = []
self.tempDir = getTempDirectory(os.getcwd())
self.tempFa = os.path.join(self.tempDir, "seq.fa")
with open(self.tempFa, "w") as f:
f.write(">temp\nNNNNNNNCNNNNAAAAAAAAAAAAAAANNNNNNN\n")
self.dummySeqMaps = []
for tree in self.trees:
if tree.size() < 50:
mcTree = MultiCactusTree(tree, tree.degree())
seqMap = dict()
for i in mcTree.breadthFirstTraversal():
mcTree.setName(i, "Node%s" % str(i))
seqMap["Node%s" % str(i)] = self.tempFa
mcTree.computeSubtreeRoots()
mcTree.nameUnlabeledInternalNodes()
self.mcTrees.append(mcTree)
self.dummySeqMaps.append(seqMap)
# Boreoeutherian tree
borTree = '((((HUMAN:0.006969,CHIMP:0.009727)Anc7:0.025291,BABOON:0.044568)Anc6:0.11,(MOUSE:0.072818,RAT:0.081244)Anc5:0.260342)Anc4:0.023260,((DOG:0.07,CAT:0.07)Anc3:0.087381,(PIG:0.06,COW:0.06)Anc2:0.104728)Anc1:0.04)Anc0;'
self.borMcTree = MultiCactusTree(NXNewick().parseString(borTree, addImpliedRoots=False))
self.borMcTree.computeSubtreeRoots()
self.borMcTree.nameUnlabeledInternalNodes()
self.mcTrees.append(self.borMcTree)
# Eutherian backbone tree
backbone = '(((((((((((Homo_sapiens:0.00655,Pan_troglodytes:0.00684):0.00422,Gorilla_gorilla_gorilla:0.008964):0.009693,Pongo_abelii:0.01894):0.015511,Macaca_mulatta:0.043601):0.08444,Aotus_nancymaae:0.08):0.08,Microcebus_murinus:0.10612):0.043494,Galeopterus_variegatus:0.134937):0.04,((((Jaculus_jaculus:0.1,(Microtus_ochrogaster:0.14,(Mus_musculus:0.084509,Rattus_norvegicus:0.091589):0.047773):0.06015):0.122992,(Heterocephalus_glaber:0.1,(Cavia_porcellus:0.065629,(Chinchilla_lanigera:0.06,Octodon_degus:0.1):0.06):0.05):0.06015):0.05,Marmota_marmota:0.1):0.05,Oryctolagus_cuniculus:0.21569):0.04):0.040593,(((Sus_scrofa:0.12,(Orcinus_orca:0.069688,(Bos_taurus:0.04,Capra_hircus:0.04):0.09):0.045488):0.02,((Equus_caballus:0.109397,(Felis_catus:0.098612,(Canis_lupus_familiaris:0.052458,Mustela_putorius_furo:0.08):0.02):0.049845):0.02,(Pteropus_alecto:0.1,Eptesicus_fuscus:0.08):0.033706):0.03):0.025,Erinaceus_europaeus:0.278178):0.021227):0.023664,(((Loxodonta_africana:0.022242,Procavia_capensis:0.145358):0.076687,Chrysochloris_asiatica:0.04):0.05,Dasypus_novemcinctus:0.169809):0.02)backbone_root:0.234728,(Monodelphis_domestica:0.125686,Sarcophilus_harrisii:0.12):0.2151);'
self.backboneTree = MultiCactusTree(NXNewick().parseString(backbone, addImpliedRoots=False))
self.backboneTree.computeSubtreeRoots()
self.backboneTree.nameUnlabeledInternalNodes()
self.mcTrees.append(self.backboneTree)
seqLens = dict()
seqLens["HUMAN"] = 57553
seqLens["CHIMP"] = 57344
seqLens["BABOON"] = 58960
seqLens["MOUSE"] = 32750
seqLens["RAT"] = 38436
seqLens["DOG"] = 54187
seqLens["CAT"] = 50283
seqLens["PIG"] = 54843
seqLens["COW"] = 55508
self.blanchetteSeqMap = dict()
for event, seqLen in seqLens.items():
p = os.path.join(self.tempDir, event +".fa")
with open(p, "w") as f:
f.write(">%s\n" % event)
f.write(''.join(['A'] * seqLen))
f.write('\n')
self.blanchetteSeqMap[event] = p
def setUp(self):
unittest.TestCase.setUp(self)
self.trees = randomTreeSet()
self.mcTrees = []
self.tempDir = getTempDirectory(os.getcwd())
self.tempFa = os.path.join(self.tempDir, "seq.fa")
with open(self.tempFa, "w") as f:
f.write(">temp\nNNNNNNNCNNNNAAAAAAAAAAAAAAANNNNNNN\n")
self.dummySeqMaps = []
for tree in self.trees:
if tree.size() < 500:
mcTree = MultiCactusTree(tree, tree.degree())
seqMap = dict()
for i in mcTree.breadthFirstTraversal():
mcTree.setName(i, "Node%s" % str(i))
seqMap["Node%s" % str(i)] = self.tempFa
mcTree.computeSubtreeRoots()
self.mcTrees.append(mcTree)
self.dummySeqMaps.append(seqMap)
seqLens = dict()
seqLens["HUMAN"] = 57553
seqLens["CHIMP"] = 57344
seqLens["BABOON"] = 58960
seqLens["MOUSE"] = 32750
seqLens["RAT"] = 38436
seqLens["DOG"] = 54187
seqLens["CAT"] = 50283
seqLens["PIG"] = 54843
seqLens["COW"] = 55508
self.blanchetteSeqMap = dict()
for event, seqLen in seqLens.items():
p = os.path.join(self.tempDir, event +".fa")
with open(p, "w") as f:
f.write(">%s\n" % event)
f.write(''.join(['A'] * seqLen))
f.write('\n')
self.blanchetteSeqMap[event] = p