def sample_agglomerated_tree(ntaxa):
"""
Sample a weighted phylogenetic xtree.
All of the branch lengths will be default lengths.
This method follows the simulation method
Used in "Why neighbor-joining works".
It agglomerates subtrees at random.
@param ntaxa: the number of leaves in the tree
@return: the root of a weighted phylogenetic xtree
"""
# a tree must have at least three leaves before it has an internal node
assert ntaxa > 2
# initialize the pool of subtrees
subtrees = []
for i in range(ntaxa):
v = Xtree.WPXVertex()
v.label = i
subtrees.append(v)
# repeatedly agglomerate pairs of subtrees
while len(subtrees) > 3:
root = Xtree.WPXVertex()
# select the items and efficiently delete them from the list
for i in range(2):
a = random.randrange(len(subtrees))
root.add_child(subtrees[a])
subtrees[a] = subtrees[-1]
del subtrees[-1]
# add the new subtree to the list
subtrees.append(root)
# agglomerate the final three subtrees
root = Xtree.WPXVertex()
for t in subtrees:
root.add_child(t)
return root
def evaluate(self, true_splits, D_estimated, atteson, use_nj, use_modified_nj, use_all_spectral, use_one_spectral):
"""
@param true_splits: the set of all full splits implied by the true tree
@param D_estimated: the estimated distance matrix
@param atteson: True iff the distance matrix is Atteson
"""
# initialize the errors
nj_error = None
modified_nj_error = None
all_spectral_error = None
one_spectral_error = None
if use_nj:
nj_splits = BuildTreeTopology.get_splits(D_estimated, BuildTreeTopology.split_nj, BuildTreeTopology.update_nj)
nj_error = Xtree.splits_to_rf_distance(nj_splits, true_splits)
if use_modified_nj:
modified_nj_splits = BuildTreeTopology.get_splits(D_estimated, BuildTreeTopology.split_nj, BuildTreeTopology.update_using_laplacian)
modified_nj_error = Xtree.splits_to_rf_distance(modified_nj_splits, true_splits)
if use_all_spectral:
splitter = BuildTreeTopology.split_using_eigenvector_with_nj_fallback
updater = BuildTreeTopology.update_using_laplacian
all_spectral_splits = BuildTreeTopology.get_splits(D_estimated, splitter, updater)
all_spectral_error = Xtree.splits_to_rf_distance(all_spectral_splits, true_splits)
if use_one_spectral:
splitter = SplitFunctor(len(D_estimated))
updater = UpdateFunctor(len(D_estimated))
one_spectral_splits = BuildTreeTopology.get_splits(D_estimated, splitter, updater)
one_spectral_error = Xtree.splits_to_rf_distance(one_spectral_splits, true_splits)
# add the data point
self.scatter_points.append(ScatterPoint(atteson, nj_error, modified_nj_error, all_spectral_error, one_spectral_error))
def setUp(self):
"""
Define a perturbed and a true distance matrix from a paper.
The paper is Why Neighbor Joining Works.
"""
self.D_perturbed = np.array([[0, 2.7, 2.6, 2.6, 2.6, 4.4, 4.4, 4.4],
[2.7, 0, 4.4, 4.4, 4.4, 2.6, 2.6, 2.6],
[2.6, 4.4, 0, 0.1, 0.4, 2.7, 2.7, 2.7],
[2.6, 4.4, 0.1, 0, 0.4, 2.7, 2.7, 2.7],
[2.6, 4.4, 0.4, 0.4, 0, 2.7, 2.7, 2.7],
[4.4, 2.6, 2.7, 2.7, 2.7, 0, 0.1, 0.4],
[4.4, 2.6, 2.7, 2.7, 2.7, 0.1, 0, 0.4],
[4.4, 2.6, 2.7, 2.7, 2.7, 0.4, 0.4, 0]])
self.D = np.array([[0.0, 3.0, 2.0, 2.0, 2.0, 3.0, 3.0, 3.0],
[3.0, 0.0, 3.0, 3.0, 3.0, 2.0, 2.0, 2.0],
[2.0, 3.0, 0.0, 0.1, 0.4, 3.0, 3.0, 3.0],
[2.0, 3.0, 0.1, 0.0, 0.4, 3.0, 3.0, 3.0],
[2.0, 3.0, 0.4, 0.4, 0.0, 3.0, 3.0, 3.0],
[3.0, 2.0, 3.0, 3.0, 3.0, 0.0, 0.1, 0.4],
[3.0, 2.0, 3.0, 3.0, 3.0, 0.1, 0.0, 0.4],
[3.0, 2.0, 3.0, 3.0, 3.0, 0.4, 0.4, 0.0]])
abc = (4, 0.2), (((2, 0.05), (3, 0.05)), 0.15)
mnp = (7, 0.2), (((5, 0.05), (6, 0.05)), 0.15)
self.tree = Xtree.list_to_weighted_tree(
((((abc, 0.8), (0, 1.0)), 1.0), (1, 1.0), (mnp, 0.8)))
self.true_splits = set([
make_split((2, 3), (0, 1, 4, 5, 6, 7)),
make_split((2, 3, 4), (0, 1, 5, 6, 7)),
make_split((2, 3, 4, 0), (1, 5, 6, 7)),
make_split((2, 3, 4, 0, 1), (5, 6, 7)),
make_split((2, 3, 4, 0, 1, 7), (5, 6))
])
def evaluate(self, true_splits, D_estimated, atteson, use_nj,
use_modified_nj, use_all_spectral, use_one_spectral):
"""
@param true_splits: the set of all full splits implied by the true tree
@param D_estimated: the estimated distance matrix
@param atteson: True iff the distance matrix is Atteson
"""
# initialize the errors
nj_error = None
modified_nj_error = None
all_spectral_error = None
one_spectral_error = None
if use_nj:
nj_splits = BuildTreeTopology.get_splits(
D_estimated, BuildTreeTopology.split_nj,
BuildTreeTopology.update_nj)
nj_error = Xtree.splits_to_rf_distance(nj_splits, true_splits)
if use_modified_nj:
modified_nj_splits = BuildTreeTopology.get_splits(
D_estimated, BuildTreeTopology.split_nj,
BuildTreeTopology.update_using_laplacian)
modified_nj_error = Xtree.splits_to_rf_distance(
modified_nj_splits, true_splits)
if use_all_spectral:
splitter = BuildTreeTopology.split_using_eigenvector_with_nj_fallback
updater = BuildTreeTopology.update_using_laplacian
all_spectral_splits = BuildTreeTopology.get_splits(
D_estimated, splitter, updater)
all_spectral_error = Xtree.splits_to_rf_distance(
all_spectral_splits, true_splits)
if use_one_spectral:
splitter = SplitFunctor(len(D_estimated))
updater = UpdateFunctor(len(D_estimated))
one_spectral_splits = BuildTreeTopology.get_splits(
D_estimated, splitter, updater)
one_spectral_error = Xtree.splits_to_rf_distance(
one_spectral_splits, true_splits)
# add the data point
self.scatter_points.append(
ScatterPoint(atteson, nj_error, modified_nj_error,
all_spectral_error, one_spectral_error))
def __init__(self):
"""
Define the topology of a tree for which branch lengths will be sought.
"""
TreeSearch.__init__(self)
# create the fixed tree topology
topo = [0, [1, 2], [[3, 4], 5]]
self.tree = Xtree.list_to_uniformly_weighted_tree(topo)
# define the expected primary split
self.desired_primary_split = frozenset([frozenset([0, 1, 2]), frozenset([3, 4, 5])])
# create the mapping from node id to node index
self.id_to_index = dict((id(node), node.label) for node in self.tree.get_labeled_vertices())
# define the internal nodes in the left hand subtree
self.id_to_index[id(self.tree.children[1])] = 6
self.id_to_index[id(self.tree)] = 7
# define the internal nodes in the right hand subtree
self.id_to_index[id(self.tree.children[2].children[0])] = 8
self.id_to_index[id(self.tree.children[2])] = 9
def __init__(self):
"""
Define the topology of a tree for which branch lengths will be sought.
"""
TreeSearch.__init__(self)
# create the fixed tree topology
topo = [0, [1, 2], [[3, 4], 5]]
self.tree = Xtree.list_to_uniformly_weighted_tree(topo)
# define the expected primary split
self.desired_primary_split = frozenset([frozenset([0, 1, 2]), frozenset([3, 4, 5])])
# create the mapping from node id to node index
self.id_to_index = dict((id(node), node.label) for node in self.tree.get_labeled_vertices())
# define the internal nodes in the left hand subtree
self.id_to_index[id(self.tree.children[1])] = 6
self.id_to_index[id(self.tree)] = 7
# define the internal nodes in the right hand subtree
self.id_to_index[id(self.tree.children[2].children[0])] = 8
self.id_to_index[id(self.tree.children[2])] = 9
def setUp(self):
"""
Define a perturbed and a true distance matrix from a paper.
The paper is Why Neighbor Joining Works.
"""
self.D_perturbed = np.array(
[
[0, 2.7, 2.6, 2.6, 2.6, 4.4, 4.4, 4.4],
[2.7, 0, 4.4, 4.4, 4.4, 2.6, 2.6, 2.6],
[2.6, 4.4, 0, 0.1, 0.4, 2.7, 2.7, 2.7],
[2.6, 4.4, 0.1, 0, 0.4, 2.7, 2.7, 2.7],
[2.6, 4.4, 0.4, 0.4, 0, 2.7, 2.7, 2.7],
[4.4, 2.6, 2.7, 2.7, 2.7, 0, 0.1, 0.4],
[4.4, 2.6, 2.7, 2.7, 2.7, 0.1, 0, 0.4],
[4.4, 2.6, 2.7, 2.7, 2.7, 0.4, 0.4, 0],
]
)
self.D = np.array(
[
[0.0, 3.0, 2.0, 2.0, 2.0, 3.0, 3.0, 3.0],
[3.0, 0.0, 3.0, 3.0, 3.0, 2.0, 2.0, 2.0],
[2.0, 3.0, 0.0, 0.1, 0.4, 3.0, 3.0, 3.0],
[2.0, 3.0, 0.1, 0.0, 0.4, 3.0, 3.0, 3.0],
[2.0, 3.0, 0.4, 0.4, 0.0, 3.0, 3.0, 3.0],
[3.0, 2.0, 3.0, 3.0, 3.0, 0.0, 0.1, 0.4],
[3.0, 2.0, 3.0, 3.0, 3.0, 0.1, 0.0, 0.4],
[3.0, 2.0, 3.0, 3.0, 3.0, 0.4, 0.4, 0.0],
]
)
abc = (4, 0.2), (((2, 0.05), (3, 0.05)), 0.15)
mnp = (7, 0.2), (((5, 0.05), (6, 0.05)), 0.15)
self.tree = Xtree.list_to_weighted_tree(((((abc, 0.8), (0, 1.0)), 1.0), (1, 1.0), (mnp, 0.8)))
self.true_splits = set(
[
make_split((2, 3), (0, 1, 4, 5, 6, 7)),
make_split((2, 3, 4), (0, 1, 5, 6, 7)),
make_split((2, 3, 4, 0), (1, 5, 6, 7)),
make_split((2, 3, 4, 0, 1), (5, 6, 7)),
make_split((2, 3, 4, 0, 1, 7), (5, 6)),
]
)
