def testNewickIO(self):
# feslenstein's own... (http://evolution.genetics.washington.edu/phylip/newicktree.html)
tree1 = '((raccoon:19.19959,bear:6.80041):0.846,((sea_lion:11.997, seal:12.003):7.52973,((monkey:100.8593,cat:47.14069):20.59201, weasel:18.87953):2.0946):3.87382,dog:25.46154);'
tree2 = '(Bovine:0.69395,(Gibbon:0.36079,(Orang:0.33636,(Gorilla:0.17147,(Chimp:0.19268, Human:0.11927):0.08386):0.06124):0.15057):0.54939,Mouse:1.2146):0.1;'
tree3 = '(Bovine:0.69395,(Hylobates:0.36079,(Pongo:0.33636,(G._Gorilla:0.17147, (P._paniscus:0.19268,H._sapiens:0.11927):0.08386):0.06124):0.15057):0.54939, Rodent:1.2146);'
tree4 = 'A;'
tree5 = '((A,B):0.0,(C,D));'
tree6 = '(Alpha,Beta,Gamma,Delta,,Epsilon,,,);'
trees = [tree1, tree2, tree3, tree4, tree5, tree6]
newickParser = NXNewick()
# Parse newicks, adding implied roots
for tree in trees:
newickParser.parseString(tree, addImpliedRoots=True)
answer = self.__cleanTree(tree)
outputString = newickParser.writeString()
logger.debug(" ***************** ")
logger.debug(outputString)
logger.debug(answer)
assert outputString == answer
# Parse newicks, not adding implied roots
for tree in trees:
newickParser.parseString(tree, addImpliedRoots=False)
outputString = newickParser.writeString()
answer = re.sub(r':[.0-9]+?;', ';', tree)
answer = re.sub(r'\s+', '', answer)
logger.debug(" ***************** ")
logger.debug(outputString)
logger.debug(answer)
assert outputString == answer
def testNewickIO(self):
# feslenstein's own... (http://evolution.genetics.washington.edu/phylip/newicktree.html)
tree1 = '((raccoon:19.19959,bear:6.80041):0.846,((sea_lion:11.997, seal:12.003):7.52973,((monkey:100.8593,cat:47.14069):20.59201, weasel:18.87953):2.0946):3.87382,dog:25.46154);'
tree2 = '(Bovine:0.69395,(Gibbon:0.36079,(Orang:0.33636,(Gorilla:0.17147,(Chimp:0.19268, Human:0.11927):0.08386):0.06124):0.15057):0.54939,Mouse:1.2146):0.1;'
tree3 = '(Bovine:0.69395,(Hylobates:0.36079,(Pongo:0.33636,(G._Gorilla:0.17147, (P._paniscus:0.19268,H._sapiens:0.11927):0.08386):0.06124):0.15057):0.54939, Rodent:1.2146);'
tree4 = 'A;'
tree5 = '((A,B):0.0,(C,D));'
tree6 = '(Alpha,Beta,Gamma,Delta,,Epsilon,,,);'
trees = [tree1, tree2, tree3, tree4, tree5, tree6]
newickParser = NXNewick()
# Parse newicks, adding implied roots
for tree in trees:
newickParser.parseString(tree, addImpliedRoots=True)
answer = self.__cleanTree(tree)
outputString = newickParser.writeString()
logger.debug(" ***************** ")
logger.debug(outputString)
logger.debug(answer)
assert outputString == answer
# Parse newicks, not adding implied roots
for tree in trees:
newickParser.parseString(tree, addImpliedRoots=False)
outputString = newickParser.writeString()
answer = re.sub(r':[.0-9]+?;', ';', tree)
answer = re.sub(r'\s+', '', answer)
logger.debug(" ***************** ")
logger.debug(outputString)
logger.debug(answer)
assert outputString == answer
def testSanity(self):
parser = NXNewick()
mcTree1 = MultiCactusTree(parser.parseString(self.tree1, addImpliedRoots=False))
tree1String = NXNewick().writeString(mcTree1)
self.assertEqual(tree1String, self.tree1)
mcTree2 = MultiCactusTree(parser.parseString(self.tree2, addImpliedRoots=False), subtreeSize=3)
tree2String = NXNewick().writeString(mcTree2)
self.assertEqual(tree2String, self.tree2)
def testSanity(self):
parser = NXNewick()
mcTree1 = MultiCactusTree(parser.parseString(self.tree1, addImpliedRoots = False))
tree1String = NXNewick().writeString(mcTree1)
self.assertEqual(tree1String, self.tree1)
mcTree2 = MultiCactusTree(parser.parseString(self.tree2, addImpliedRoots = False))
tree2String = NXNewick().writeString(mcTree2)
self.assertEqual(tree2String, self.tree2)
def __generateTrees(self):
self.tree1 = '((((HUMAN:0.006969,CHIMP:0.009727):0.025291,BABOON:0.044568):0.11,(MOUSE:0.072818,RAT:0.081244):0.260342):0.02326,((DOG:0.07,CAT:0.07):0.087381,(PIG:0.06,COW:0.06):0.104728):0.04);'
self.tree2 = '((raccoon:19.19959,bear:6.80041):0.846,((sea_lion:11.997,seal:12.003):7.52973,((monkey:100.8593,cat:47.14069):20.59201,weasel:18.87953):2.0946):3.87382,dog:25.46154);'
parser = NXNewick()
self.mcTree1 = MultiCactusTree(
parser.parseString(self.tree1, addImpliedRoots=False))
self.mcTree2 = MultiCactusTree(
parser.parseString(self.tree2, addImpliedRoots=False))
self.mcTree1.nameUnlabeledInternalNodes()
self.mcTree2.nameUnlabeledInternalNodes()
self.mcTree1.computeSubtreeRoots()
self.mcTree2.computeSubtreeRoots()
def __generateTrees(self):
self.tree1 = "((((HUMAN:0.006969,CHIMP:0.009727):0.025291,BABOON:0.044568):0.11,(MOUSE:0.072818,RAT:0.081244):0.260342):0.02326,((DOG:0.07,CAT:0.07):0.087381,(PIG:0.06,COW:0.06):0.104728):0.04);"
self.tree2 = "((raccoon:19.19959,bear:6.80041):0.846,((sea_lion:11.997,seal:12.003):7.52973,((monkey:100.8593,cat:47.14069):20.59201,weasel:18.87953):2.0946):3.87382,dog:25.46154);"
parser = NXNewick()
self.mcTree1 = MultiCactusTree(parser.parseString(self.tree1, addImpliedRoots=False))
self.mcTree1a = MultiCactusTree(parser.parseString(self.tree1, addImpliedRoots=False), subtreeSize=4)
self.mcTree2 = MultiCactusTree(parser.parseString(self.tree2, addImpliedRoots=False), subtreeSize=3)
self.mcTree1.nameUnlabeledInternalNodes()
self.mcTree1a.nameUnlabeledInternalNodes()
self.mcTree2.nameUnlabeledInternalNodes()
self.mcTree1.computeSubtreeRoots()
self.mcTree1a.computeSubtreeRoots()
self.mcTree2.computeSubtreeRoots()
def testAddOutgroup(self):
trueOg = "((((HUMAN:0.006969,CHIMP:0.009727)Anc7:0.025291,BABOON:0.044568)Anc3:0.11,(MOUSE:0.072818,RAT:0.081244)Anc4:0.260342)Anc1:0.02326,((DOG:0.07,CAT:0.07)Anc5:0.087381,(PIG:0.06,COW:0.06)Anc6:0.104728)Anc2:0.04,outgroup:1.7)Anc0;"
tree = MultiCactusTree(self.mcTree1)
tree.nameUnlabeledInternalNodes()
tree.computeSubtreeRoots()
tree.addOutgroup("outgroup", 1.7)
treeString = NXNewick().writeString(tree)
self.assertEqual(treeString, trueOg)
trueLeafOg = "(A:1.1,outgroup:1.1);"
leafTreeString = "A;"
parser = NXNewick()
leafTree = MultiCactusTree(parser.parseString(leafTreeString, addImpliedRoots=False))
leafTree.nameUnlabeledInternalNodes()
leafTree.computeSubtreeRoots()
leafTree.addOutgroup("outgroup", 2.2)
leafTreeOutString = NXNewick().writeString(leafTree)
self.assertEqual(leafTreeOutString, trueLeafOg)
def testAddOutgroup(self):
trueOg = '((((HUMAN:0.006969,CHIMP:0.009727)Anc7:0.025291,BABOON:0.044568)Anc3:0.11,(MOUSE:0.072818,RAT:0.081244)Anc4:0.260342)Anc1:0.02326,((DOG:0.07,CAT:0.07)Anc5:0.087381,(PIG:0.06,COW:0.06)Anc6:0.104728)Anc2:0.04,outgroup:1.7)Anc0;'
tree = MultiCactusTree(self.mcTree1)
tree.nameUnlabeledInternalNodes()
tree.computeSubtreeRoots()
tree.addOutgroup("outgroup", 1.7)
treeString = NXNewick().writeString(tree)
self.assertEqual(treeString, trueOg)
trueLeafOg = "(A:1.1,outgroup:1.1);"
leafTreeString = "A;"
parser = NXNewick()
leafTree = MultiCactusTree(parser.parseString(leafTreeString, addImpliedRoots = False))
leafTree.nameUnlabeledInternalNodes()
leafTree.computeSubtreeRoots()
leafTree.addOutgroup("outgroup", 2.2)
leafTreeOutString = NXNewick().writeString(leafTree)
self.assertEqual(leafTreeOutString, trueLeafOg)
def parseFile(self, path):
if not os.path.isfile(path):
raise RuntimeError("File not found: %s" % path)
self.tree = None
self.pathMap = dict()
self.outgroups = []
seqFile = open(path, "r")
for l in seqFile:
line = l.strip()
if line:
if line[0] == "#":
continue
tokens = line.split()
if self.tree is None and (len(tokens) == 1 or line[0] == '('):
newickParser = NXNewick()
if not line.strip().endswith(");"):
raise RuntimeError("The newick tree %s may not "
"have a branch length after "
"the root node." % line)
try:
self.tree = newickParser.parseString(line)
except:
raise RuntimeError("Failed to parse newick tree: %s" %
line)
elif len(tokens) > 0 and tokens[0] == '*':
sys.stderr.write("Skipping line %s\n" % l)
elif line[0] != '(' and len(tokens) >= 2:
name = tokens[0]
if name[0] == '*':
name = name[1:]
self.outgroups.append(name)
path = string.join(tokens[1:])
if name in self.pathMap:
raise RuntimeError("Duplicate name found: %s" % name)
self.pathMap[name] = path
elif len(tokens) > 0:
sys.stderr.write("Skipping line %s\n" % l)
if self.tree is None:
self.starTree()
self.cleanTree()
self.validate()
def parseFile(self, path):
if not os.path.isfile(path):
raise RuntimeError("File not found: %s" % path)
self.tree = None
self.pathMap = dict()
self.outgroups = []
seqFile = open(path, "r")
for l in seqFile:
line = l.strip()
if line:
if line[0] == "#":
continue
tokens = line.split()
if self.tree is None and (len(tokens) == 1 or line[0] == '('):
newickParser = NXNewick()
if not line.strip().endswith(");"):
raise RuntimeError("The newick tree %s may not "
"have a branch length after "
"the root node." % line)
try:
self.tree = newickParser.parseString(line)
except:
raise RuntimeError("Failed to parse newick tree: %s" %
line)
elif len(tokens) > 0 and tokens[0] == '*':
sys.stderr.write("Skipping line %s\n" % l)
elif line[0] != '(' and len(tokens) >= 2:
name = tokens[0]
if name[0] == '*':
name = name[1:]
self.outgroups.append(name)
path = string.join(tokens[1:])
if name in self.pathMap:
raise RuntimeError("Duplicate name found: %s" % name)
self.pathMap[name] = path
elif len(tokens) > 0:
sys.stderr.write("Skipping line %s\n" % l)
if self.tree is None:
self.starTree()
self.cleanTree()
self.validate()
