def testCalculateProbableRootOfGeneTree_Examples(self):
#return
treeString = '(((((((((((((human:0.006969,chimp:0.009727):0.025291,((baboon:0.008968):0.011019):0.024581):0.023649):0.066673):0.018405,((rat:0.081244,mouse:0.072818):0.238435):0.021892):0.02326,(((cow:0.164728,(cat:0.109852,dog:0.107805):0.049576):0.004663):0.010883):0.033242):0.028346):0.016015):0.226853):0.063898):0.126639):0.119814):0.16696);'
speciesTree = newickTreeParser(treeString)
binaryTree_depthFirstNumbers(speciesTree)
geneString1 = ('((human,baboon),chimp);', '((human,chimp),baboon);')
geneString2 = ('((human,chimp),baboon);', '((human,chimp),baboon);')
geneString3 = ('((((human,chimp),baboon),((dog,cat),cow)),(mouse,rat));', '((((human,chimp),baboon),(mouse,rat)),((dog,cat),cow));')
geneString4 = ('((((human,chimp),baboon),(mouse,rat)),((dog,cat),cow));', '((((human,chimp),baboon),(mouse,rat)),((dog,cat),cow));')
geneString5 = ('((((human,(chimp, chimp)),baboon),((dog,cat),cow)),(mouse,rat));', '((((human,(chimp,chimp)),baboon),(mouse,rat)),((dog,cat),cow));')
#geneString3 = ('((human,(human, chimp)),baboon);', 1)
#geneString4 = ('((human,(human, chimp)),(chimp, baboon));', 2)
#geneString5 = ('(dog,cat);', 0)
#geneString6 = ('((dog,cat), cow);', 0)
#geneString7 = ('(cow,(dog,cat));', 0)
#geneString8 = ('(cow,(cat,dog));', 0)
#geneString9 = ('((cow,dog),(dog,cow));', 1)
#geneString10 = ('((cow,(cow,cow)),(dog,cat));', 2)
#geneString11 = ('((cow,(cow,cow)),(dog,((cat,cat),cat)));', 4)
geneStrings = [ geneString1, geneString2, geneString3, geneString4, geneString5 ]
#[ geneString3, geneString4, \
#geneString5, geneString6, geneString7, geneString8,
#geneString9, geneString10, geneString11 ]
for geneString, rootedGeneString in geneStrings:
geneTree = newickTreeParser(geneString)
rootedGeneTree = newickTreeParser(geneString)
binaryTree_depthFirstNumbers(geneTree)
rootedGeneTree2, dupCount, lossCount = calculateProbableRootOfGeneTree(speciesTree, geneTree)
print "rootedGeneTree", rootedGeneString, dupCount, lossCount, printBinaryTree(rootedGeneTree2, False)
def moveRoot(root, branch):
"""
Removes the old root and places the new root at the mid point along the given branch
"""
import bioio
if root.traversalID.mid == branch:
return bioio.newickTreeParser(bioio.printBinaryTree(root, True))
def fn2(tree, seq):
if seq is not None:
return '(' + bioio.printBinaryTree(tree, True)[:-1] + ',' + seq + ')'
return bioio.printBinaryTree(tree, True)[:-1]
def fn(tree, seq):
if tree.traversalID.mid == branch:
i = tree.distance
tree.distance /= 2
seq = '(' + bioio.printBinaryTree(tree, True)[:-1] + ',(' + seq + ('):%s' % tree.distance) + ');'
tree.distance = i
return seq
if tree.internal:
if branch < tree.traversalID.mid:
seq = fn2(tree.right, seq)
return fn(tree.left, seq)
else:
assert branch > tree.traversalID.mid
seq = fn2(tree.left, seq)
return fn(tree.right, seq)
else:
return bioio.printBinaryTree(tree, True)[:-1]
s = fn(root, None)
return bioio.newickTreeParser(s)
def moveRoot(root, branch):
"""
Removes the old root and places the new root at the mid point along the given branch
"""
import bioio
if root.traversalID.mid == branch:
return bioio.newickTreeParser(bioio.printBinaryTree(root, True))
def fn2(tree, seq):
if seq is not None:
return '(' + bioio.printBinaryTree(tree,
True)[:-1] + ',' + seq + ')'
return bioio.printBinaryTree(tree, True)[:-1]
def fn(tree, seq):
if tree.traversalID.mid == branch:
i = tree.distance
tree.distance /= 2
seq = '(' + bioio.printBinaryTree(
tree, True)[:-1] + ',(' + seq + ('):%s' % tree.distance) + ');'
tree.distance = i
return seq
if tree.internal:
if branch < tree.traversalID.mid:
seq = fn2(tree.right, seq)
return fn(tree.left, seq)
else:
assert branch > tree.traversalID.mid
seq = fn2(tree.left, seq)
return fn(tree.right, seq)
else:
return bioio.printBinaryTree(tree, True)[:-1]
s = fn(root, None)
return bioio.newickTreeParser(s)
def testCalculateDupsAndLossesByReconcilingTrees_Examples(self):
treeString = '(((((((((((((human:0.006969,chimp:0.009727):0.025291,((baboon:0.008968):0.011019):0.024581):0.023649):0.066673):0.018405,((rat:0.081244,mouse:0.072818):0.238435):0.021892):0.02326,(((cow:0.164728,(cat:0.109852,dog:0.107805):0.049576):0.004663):0.010883):0.033242):0.028346):0.016015):0.226853):0.063898):0.126639):0.119814):0.16696);'
speciesTree = newickTreeParser(treeString)
binaryTree_depthFirstNumbers(speciesTree)
#s = printBinaryTree(speciesTree, True)
#speciesTree = newickTreeParser(s)
#binaryTree_depthFirstNumbers(speciesTree)
geneString1 = ('((human,baboon),chimp);', 1, 3)
geneString2 = ('((human,chimp),baboon);', 0, 0)
geneString3 = ('((human,(human, chimp)),baboon);', 1, 1)
geneString4 = ('((human,(human, chimp)),(chimp, baboon));', 2, 3)
geneString5 = ('(dog,cat);', 0, 0)
geneString6 = ('((dog,cat), cow);', 0, 0)
geneString7 = ('(cow,(dog,cat));', 0, 0)
geneString8 = ('(cow,(cat,dog));', 0, 0)
geneString9 = ('((cow,dog),(dog,cow));', 1, 2)
geneString10 = ('((cow,(cow,cow)),(dog,cat));', 2, 0)
geneString11 = ('((cow,(cow,cow)),(dog,((cat,cat),cat)));', 4, 0)
geneStrings = [ geneString1, geneString2, geneString3, geneString4, \
geneString5, geneString6, geneString7, geneString8,
geneString9, geneString10, geneString11 ]
print ""
for geneString, dupCount, lossCount in geneStrings:
geneTree = newickTreeParser(geneString)
binaryTree_depthFirstNumbers(geneTree)
print printBinaryTree(geneTree, True), printBinaryTree(speciesTree, True)
dupCount2, lossCount2 = calculateDupsAndLossesByReconcilingTrees(speciesTree, geneTree, processID=lambda x : x)
print geneString, "dups", dupCount, dupCount2, "losses", lossCount, lossCount2
assert dupCount == dupCount2
assert lossCount == lossCount2
def remodelTreeRemovingRoot(root, node):
"""
Node is mid order number
"""
import bioio
assert root.traversalID.mid != node
hash = {}
def fn(bT):
if bT.traversalID.mid == node:
assert bT.internal == False
return [ bT ]
elif bT.internal:
i = fn(bT.left)
if i is None:
i = fn(bT.right)
if i is not None:
hash[i[-1]]= bT
i.append(bT)
return i
return None
l = fn(root)
def fn2(i, j):
if i.left == j:
return i.right
assert i.right == j
return i.left
def fn3(bT):
if hash[bT] == root:
s = '(' + bioio.printBinaryTree(fn2(hash[bT], bT), bT, True)[:-1] + ')'
else:
s = '(' + bioio.printBinaryTree(fn2(hash[bT], bT), bT, True)[:-1] + ',' + fn3(hash[bT]) + ')'
return s + ":" + str(bT.distance)
s = fn3(l[0]) + ';'
t = bioio.newickTreeParser(s)
return t
def testNewickTreeParser(self):
if self.testNo > 0:
d = '((human,baboon),chimp);'
e = newickTreeParser(d)
f = printBinaryTree(e, False)
print d, f
assert d == f
def testNewickTreeParser_UnaryNodes(self):
#tests with unary nodes
for test in xrange(0, self.testNo):
tree = getRandomTreeString()
logger.debug("tree to try\t", tree)
tree2 = newickTreeParser(tree, reportUnaryNodes=True)
tree3 = printBinaryTree(tree2, True)
logger.debug("tree found\t", tree3)
assert tree == tree3
def main(): parser = ArgumentParser() InitializeArguments(parser) args = parser.parse_args() CheckArguments(args, parser) tree = newickTreeParser(args.newick, 0.0) distance_tree = ConvertTree(tree, args) distances = GetDistances(distance_tree, args) PrintDistances(distances, args)
def testCalculateProbableRootOfGeneTree_Examples(self):
#return
treeString = '(((((((((((((human:0.006969,chimp:0.009727):0.025291,((baboon:0.008968):0.011019):0.024581):0.023649):0.066673):0.018405,((rat:0.081244,mouse:0.072818):0.238435):0.021892):0.02326,(((cow:0.164728,(cat:0.109852,dog:0.107805):0.049576):0.004663):0.010883):0.033242):0.028346):0.016015):0.226853):0.063898):0.126639):0.119814):0.16696);'
speciesTree = newickTreeParser(treeString)
binaryTree_depthFirstNumbers(speciesTree)
geneString1 = ('((human,baboon),chimp);', '((human,chimp),baboon);')
geneString2 = ('((human,chimp),baboon);', '((human,chimp),baboon);')
geneString3 = (
'((((human,chimp),baboon),((dog,cat),cow)),(mouse,rat));',
'((((human,chimp),baboon),(mouse,rat)),((dog,cat),cow));')
geneString4 = (
'((((human,chimp),baboon),(mouse,rat)),((dog,cat),cow));',
'((((human,chimp),baboon),(mouse,rat)),((dog,cat),cow));')
geneString5 = (
'((((human,(chimp, chimp)),baboon),((dog,cat),cow)),(mouse,rat));',
'((((human,(chimp,chimp)),baboon),(mouse,rat)),((dog,cat),cow));')
#geneString3 = ('((human,(human, chimp)),baboon);', 1)
#geneString4 = ('((human,(human, chimp)),(chimp, baboon));', 2)
#geneString5 = ('(dog,cat);', 0)
#geneString6 = ('((dog,cat), cow);', 0)
#geneString7 = ('(cow,(dog,cat));', 0)
#geneString8 = ('(cow,(cat,dog));', 0)
#geneString9 = ('((cow,dog),(dog,cow));', 1)
#geneString10 = ('((cow,(cow,cow)),(dog,cat));', 2)
#geneString11 = ('((cow,(cow,cow)),(dog,((cat,cat),cat)));', 4)
geneStrings = [
geneString1, geneString2, geneString3, geneString4, geneString5
]
#[ geneString3, geneString4, \
#geneString5, geneString6, geneString7, geneString8,
#geneString9, geneString10, geneString11 ]
for geneString, rootedGeneString in geneStrings:
geneTree = newickTreeParser(geneString)
rootedGeneTree = newickTreeParser(geneString)
binaryTree_depthFirstNumbers(geneTree)
rootedGeneTree2, dupCount, lossCount = calculateProbableRootOfGeneTree(
speciesTree, geneTree)
print "rootedGeneTree", rootedGeneString, dupCount, lossCount, printBinaryTree(
rootedGeneTree2, False)
def testCalculateDupsAndLossesByReconcilingTrees_Examples(self):
treeString = '(((((((((((((human:0.006969,chimp:0.009727):0.025291,((baboon:0.008968):0.011019):0.024581):0.023649):0.066673):0.018405,((rat:0.081244,mouse:0.072818):0.238435):0.021892):0.02326,(((cow:0.164728,(cat:0.109852,dog:0.107805):0.049576):0.004663):0.010883):0.033242):0.028346):0.016015):0.226853):0.063898):0.126639):0.119814):0.16696);'
speciesTree = newickTreeParser(treeString)
binaryTree_depthFirstNumbers(speciesTree)
#s = printBinaryTree(speciesTree, True)
#speciesTree = newickTreeParser(s)
#binaryTree_depthFirstNumbers(speciesTree)
geneString1 = ('((human,baboon),chimp);', 1, 3)
geneString2 = ('((human,chimp),baboon);', 0, 0)
geneString3 = ('((human,(human, chimp)),baboon);', 1, 1)
geneString4 = ('((human,(human, chimp)),(chimp, baboon));', 2, 3)
geneString5 = ('(dog,cat);', 0, 0)
geneString6 = ('((dog,cat), cow);', 0, 0)
geneString7 = ('(cow,(dog,cat));', 0, 0)
geneString8 = ('(cow,(cat,dog));', 0, 0)
geneString9 = ('((cow,dog),(dog,cow));', 1, 2)
geneString10 = ('((cow,(cow,cow)),(dog,cat));', 2, 0)
geneString11 = ('((cow,(cow,cow)),(dog,((cat,cat),cat)));', 4, 0)
geneStrings = [ geneString1, geneString2, geneString3, geneString4, \
geneString5, geneString6, geneString7, geneString8,
geneString9, geneString10, geneString11 ]
print ""
for geneString, dupCount, lossCount in geneStrings:
geneTree = newickTreeParser(geneString)
binaryTree_depthFirstNumbers(geneTree)
print printBinaryTree(geneTree,
True), printBinaryTree(speciesTree, True)
dupCount2, lossCount2 = calculateDupsAndLossesByReconcilingTrees(
speciesTree, geneTree, processID=lambda x: x)
print geneString, "dups", dupCount, dupCount2, "losses", lossCount, lossCount2
assert dupCount == dupCount2
assert lossCount == lossCount2
def remodelTreeRemovingRoot(root, node):
"""
Node is mid order number
"""
import bioio
assert root.traversalID.mid != node
hash = {}
def fn(bT):
if bT.traversalID.mid == node:
assert bT.internal == False
return [bT]
elif bT.internal:
i = fn(bT.left)
if i is None:
i = fn(bT.right)
if i is not None:
hash[i[-1]] = bT
i.append(bT)
return i
return None
l = fn(root)
def fn2(i, j):
if i.left == j:
return i.right
assert i.right == j
return i.left
def fn3(bT):
if hash[bT] == root:
s = '(' + bioio.printBinaryTree(fn2(hash[bT], bT), bT,
True)[:-1] + ')'
else:
s = '(' + bioio.printBinaryTree(fn2(
hash[bT], bT), bT, True)[:-1] + ',' + fn3(hash[bT]) + ')'
return s + ":" + str(bT.distance)
s = fn3(l[0]) + ';'
t = bioio.newickTreeParser(s)
return t
