def get_harmonically_extended_MDS(self):
Lbb = Ftree.TB_to_L_block(self.T, self.B, self.internal, self.internal)
Lba = Ftree.TB_to_L_block(self.T, self.B, self.internal, self.leaves)
L_schur = Ftree.TB_to_L_schur(self.T, self.B, self.leaves)
W, V = scipy.linalg.eigh(L_schur, eigvals=(1, 2))
V = V * np.reciprocal(np.sqrt(W))
V = self._reflected_to_reference(V)
Y = -np.dot(np.dot(np.linalg.pinv(Lbb), Lba), V)
return np.vstack([V, Y])
def get_response_content(fs):
# read the trees
T_true, B_true, N_true = FtreeIO.newick_to_TBN(fs.true_tree)
T_test, B_test, N_test = FtreeIO.newick_to_TBN(fs.test_tree)
# we are concerned about the names of the leaves of the two trees
true_leaves = Ftree.T_to_leaves(T_true)
test_leaves = Ftree.T_to_leaves(T_test)
true_leaf_to_n = dict((v, N_true[v]) for v in true_leaves)
test_leaf_to_n = dict((v, N_test[v]) for v in test_leaves)
# check that all leaves are named
if len(true_leaves) != len(true_leaf_to_n):
raise ValueError(
'all leaves in the leaf MDS tree should be named')
if len(test_leaves) != len(test_leaf_to_n):
raise ValueError(
'all leaves in the harmonic extension tree should be named')
# check that within each tree all leaves are uniquely named
if len(set(true_leaf_to_n.values())) != len(true_leaves):
raise ValueError(
'all leaf names in the leaf MDS tree should be unique')
if len(set(test_leaf_to_n.values())) != len(test_leaves):
raise ValueError(
'all leaf names in the harmonic extension tree '
'should be unique')
# check that the leaf name sets are the same
if set(true_leaf_to_n.values()) != set(test_leaf_to_n.values()):
raise ValueError(
'the two trees should have corresponding leaf names')
# invert the leaf name maps
true_n_to_leaf = dict((n, v) for v, n in true_leaf_to_n.items())
test_n_to_leaf = dict((n, v) for v, n in test_leaf_to_n.items())
# get correspondingly ordered leaf sequences
leaf_names = true_leaf_to_n.values()
true_leaves_reordered = [true_n_to_leaf[n] for n in leaf_names]
test_leaves_reordered = [test_n_to_leaf[n] for n in leaf_names]
# get the Schur complement matrix for the leaves
L_schur_true = Ftree.TB_to_L_schur(T_true, B_true, true_leaves_reordered)
# get the MDS points
w, V = scipy.linalg.eigh(L_schur_true, eigvals=(1, 2))
X = np.dot(V, np.diag(np.reciprocal(np.sqrt(w))))
# get the linear operator that defines the harmonic extension
test_internal = Ftree.T_to_internal_vertices(T_test)
L22 = Ftree.TB_to_L_block(T_test, B_test,
test_internal, test_internal)
L21 = Ftree.TB_to_L_block(T_test, B_test,
test_internal, test_leaves_reordered)
M = -np.dot(np.linalg.pinv(L22), L21)
# get the harmonic extension
X_extension = np.dot(M, X)
X_extended = np.vstack([X, X_extension])
# draw the image
v_to_index = Ftree.invseq(test_leaves_reordered + test_internal)
physical_size = (640, 480)
ext = Form.g_imageformat_to_ext[fs.imageformat]
return get_animation_frame(ext, physical_size, fs.scale,
v_to_index, T_test, X_extended)
def get_response_content(fs):
# read the tree
T, B, N = FtreeIO.newick_to_TBN(fs.tree)
leaves = Ftree.T_to_leaves(T)
internal = Ftree.T_to_internal_vertices(T)
# get the distinguished vertex of articulation
r = get_unique_vertex(N, fs.vertex)
if r not in internal:
raise ValueError(
'the distinguished vertex should have degree at least two')
# Partition the leaves with respect to the given root.
# Each set of leaves will eventually define a connected component.
R = Ftree.T_to_R_specific(T, r)
v_to_sinks = Ftree.R_to_v_to_sinks(R)
# break some edges
R_pruned = set(R)
neighbors = Ftree.T_to_v_to_neighbors(T)[r]
for adj in neighbors:
R_pruned.remove((r, adj))
T_pruned = Ftree.R_to_T(R_pruned)
# get the leaf partition
ordered_leaves = []
leaf_lists = []
for adj in neighbors:
R_subtree = Ftree.T_to_R_specific(T_pruned, adj)
C = sorted(b for a, b in R_subtree if b not in v_to_sinks)
ordered_leaves.extend(C)
leaf_lists.append(C)
# define the vertices to keep and those to remove
keepers = ordered_leaves + [r]
# get the schur complement
L_schur = Ftree.TB_to_L_schur(T, B, keepers)
# get principal submatrices of the schur complement
principal_matrices = []
accum = 0
for component_leaves in leaf_lists:
n = len(component_leaves)
M = L_schur[accum:accum+n, accum:accum+n]
principal_matrices.append(M)
accum += n
# write the report
out = StringIO()
print >> out, 'algebraic connectivity:'
print >> out, get_algebraic_connectivity(T, B, leaves)
print >> out
print >> out
print >> out, 'perron values:'
print >> out
for M, leaf_list in zip(principal_matrices, leaf_lists):
value = scipy.linalg.eigh(M, eigvals_only=True)[0]
name_list = [N[v] for v in leaf_list]
print >> out, name_list
print >> out, value
print >> out
return out.getvalue()
def get_harmonically_extended_MDS(T, B, leaves, internal):
"""
Use harmonically extended 2D MDS.
"""
Lbb = Ftree.TB_to_L_block(T, B, internal, internal)
Lba = Ftree.TB_to_L_block(T, B, internal, leaves)
L_schur = Ftree.TB_to_L_schur(T, B, leaves)
W, V = scipy.linalg.eigh(L_schur, eigvals=(1, 2))
V = V * np.reciprocal(np.sqrt(W))
Y = -np.dot(np.dot(np.linalg.pinv(Lbb), Lba), V)
return np.vstack([V, Y])
def get_gap(blen, T, B, u_edge):
"""
This function will be minimized.
@param blen: proposed branch length
@param T: topology
@param B: branch lengths
@param u_edge: undirected edge
"""
if blen <= 0:
return 1
leaves = Ftree.T_to_leaves(T)
B[u_edge] = blen
L_schur = Ftree.TB_to_L_schur(T, B, leaves)
ev1, ev2 = scipy.linalg.eigh(L_schur, eigvals_only=True, eigvals=(1, 2))
gap = abs(ev1 - ev2)
return gap
def get_v_to_point(self):
"""
This uses the harmonic extension.
Also it uses the reference MDS for reflection.
@return: a map from vertex to point
"""
Lbb = Ftree.TB_to_L_block(self.T, self.B, self.internal, self.internal)
Lba = Ftree.TB_to_L_block(self.T, self.B, self.internal, self.leaves)
L_schur = Ftree.TB_to_L_schur(self.T, self.B, self.leaves)
W, V = scipy.linalg.eigh(L_schur, eigvals=(1, 2))
V = V * np.reciprocal(np.sqrt(W))
V = self._reflected_to_reference(V)
Y = -np.dot(np.dot(np.linalg.pinv(Lbb), Lba), V)
MDS = np.vstack([V, Y])
vertices = self.leaves + self.internal
return dict((vertices[i], tuple(pt)) for i, pt in enumerate(MDS))
def TB_to_harmonic_valuations(T, B):
"""
@param T: topology
@param B: branch lengths
@return: a number of dictionaries equal to the number of leaves
"""
leaves = Ftree.T_to_leaves(T)
internal = Ftree.T_to_internal_vertices(T)
vertices = leaves + internal
nleaves = len(leaves)
Lbb = Ftree.TB_to_L_block(T, B, internal, internal)
Lba = Ftree.TB_to_L_block(T, B, internal, leaves)
L_schur = Ftree.TB_to_L_schur(T, B, leaves)
w, v1 = scipy.linalg.eigh(L_schur)
v2 = -np.dot(np.dot(np.linalg.pinv(Lbb), Lba), v1)
V = np.vstack([v1, v2])
vs = []
for col in range(nleaves):
d = dict((v, V[row, col]) for row, v in enumerate(vertices))
vs.append(d)
return vs
def get_leaf_distn_schur(R, B):
"""
This is a possibly equivalent formulation.
It is based on removing all internal vertices except the root
by Schur complement.
"""
# Get the vertex order.
# This order is different from the acl order.
T = Ftree.R_to_T(R)
r = Ftree.R_to_root(R)
leaves = Ftree.T_to_leaves(T)
non_r_internal = [v for v in Ftree.T_to_internal_vertices(T) if v != r]
vertices = leaves + [r] + non_r_internal
# Get the combinatorial Laplacian matrix
# and Schur complement out all of the non-root internal vertices.
L_schur = Ftree.TB_to_L_schur(T, B, leaves + [r])
# Get the vector of negative weights between the root and the leaves.
w_unnormalized = L_schur[-1, :-1]
# Get the normalized weight vector
w = w_unnormalized / w_unnormalized.sum()
return dict((v, w[i]) for i, v in enumerate(leaves))
def __call__(self, X):
"""
First few entries of X are logs of branch lengths.
Next few entries are vr1 entries.
Next few entries are vr2 entries.
@param X: a 1D numpy array of floats
"""
# unpack the parameter array
B, Vr = self.X_to_B_Vr(X)
L, V = self.X_to_L_V(X)
# get the error matrix
E = np.dot(L, V) - self.C
# compute the squared frobenius norm of the error
frob_norm_err = np.sum(E * E)
# use a hack to make sure we are really using the first two eigenvalues
L_schur = Ftree.TB_to_L_schur(self.T_test, B, self.leaves)
w_observed = scipy.linalg.eigvalsh(L_schur, eigvals=(1, 2))
w_error = w_observed - self.w
eigenvalue_err = np.sum(w_error * w_error)
# return the total error
return frob_norm_err + eigenvalue_err
def get_response_content(fs):
# read the user input
weight_delta_mu = fs.weight_delta_mu
T, B, N = FtreeIO.newick_to_TBN(fs.newick)
# summarize the tree
leaves = Ftree.T_to_leaves(T)
internal = Ftree.T_to_internal_vertices(T)
vertices = leaves + internal
nleaves = len(leaves)
# define the fully connected schur complement graph as a Laplacian matrix
# init the tree reconstruction state
v_to_name = {}
for v in leaves:
name = N.get(v, None)
if name is None:
name = 'P' + chr(ord('a') + v)
v_to_name[v] = name
v_to_svs = dict((v, set([0])) for v in leaves)
sv_to_vs = {0: set(leaves)}
# define edge weights (used only for spectral split strategy)
G = Ftree.TB_to_L_schur(T, B, leaves)
# add some random amount to each edge weight
for i in range(nleaves):
for j in range(i):
rate = 1 / fs.weight_delta_mu
x = random.expovariate(rate)
G[i, j] -= x
G[j, i] -= x
G[i, i] += x
G[j, j] += x
edge_to_weight = {}
for index_pair in itertools.combinations(range(nleaves), 2):
i, j = index_pair
leaf_pair = (leaves[i], leaves[j])
edge_to_weight[frozenset(leaf_pair)] = -G[index_pair]
# define pairwise distances (used only for nj split strategy)
D = Ftree.TB_to_D(T, B, leaves)
edge_to_distance = {}
for index_pair in itertools.combinations(range(nleaves), 2):
i, j = index_pair
leaf_pair = (leaves[i], leaves[j])
edge_to_distance[frozenset(leaf_pair)] = D[index_pair]
# pairs like (-(number of vertices in supervertex sv), supervertex sv)
active_svs = set([0])
# initialize the sources of unique vertex and supervertex identifiers
v_gen = itertools.count(max(leaves) + 1)
sv_gen = itertools.count(1)
# write the output
out = StringIO()
print >> out, '<html>'
print >> out, '<body>'
for count_pos in itertools.count(1):
# add the graph rendering before the decomposition at this stage
if fs.nj_split:
edge_to_branch_weight = {}
for k, v in edge_to_distance.items():
edge_to_branch_weight[k] = 1 / v
elif fs.spectral_split:
edge_to_branch_weight = edge_to_weight
print >> out, '<div>'
if fs.vis_star:
print >> out, nhj.get_svg_star_components(active_svs, sv_to_vs,
v_to_name, v_to_svs,
edge_to_branch_weight)
elif fs.vis_complete:
print >> out, nhj.get_svg(active_svs, sv_to_vs, v_to_name,
v_to_svs, edge_to_branch_weight)
print >> out, '</div>'
# update the splits
next_active_svs = set()
# svs can be decomposed independently in arbitrary order
alpha_index_gen = itertools.count()
for sv in active_svs:
nstates = len(sv_to_vs[sv])
if nstates > 2:
v_new = next(v_gen)
sv_new_a = next(sv_gen)
sv_new_b = next(sv_gen)
alpha_index = next(alpha_index_gen)
alpha = chr(ord('a') + alpha_index)
v_to_name[v_new] = 'R%s%s' % (count_pos, alpha)
next_active_svs.add(sv_new_a)
next_active_svs.add(sv_new_b)
if fs.spectral_split:
if len(sv_to_vs[sv]) == 3:
sv_new_c = next(sv_gen)
nhj.delta_wye_transform(sv, v_to_svs, sv_to_vs,
edge_to_weight, v_new,
sv_new_a, sv_new_b, sv_new_c)
next_active_svs.add(sv_new_c)
else:
nhj.harmonic_split_transform(sv, v_to_svs, sv_to_vs,
edge_to_weight, v_new,
sv_new_a, sv_new_b)
elif fs.nj_split:
sv_new_big = next(sv_gen)
nhj.nj_split_transform(sv, v_to_svs, sv_to_vs,
edge_to_distance, v_new, sv_new_big,
sv_new_a, sv_new_b)
next_active_svs.add(sv_new_big)
elif nstates == 2:
next_active_svs.add(sv)
else:
raise ValueError('supervertex has too few vertices')
# if the set of active svs has not changed then we are done
if active_svs == next_active_svs:
break
else:
active_svs = next_active_svs
print >> out, '</html>'
print >> out, '</body>'
return out.getvalue()
def get_response_content(fs):
T, B, N = FtreeIO.newick_to_TBN(fs.tree)
leaves = Ftree.T_to_leaves(T)
L_schur = Ftree.TB_to_L_schur(T, B, leaves)
mu = scipy.linalg.eigh(L_schur, eigvals_only=True)[1]
return str(mu)
def get_response_content(fs):
# read the tree
R, B, N = FtreeIO.newick_to_RBN(fs.tree)
r = Ftree.R_to_root(R)
T = Ftree.R_to_T(R)
leaves = Ftree.T_to_leaves(T)
internal_not_r = [v for v in Ftree.T_to_internal_vertices(T) if v is not r]
# define the lists of leaves induced by the root
vertex_partition = sorted(Ftree.R_to_vertex_partition(R))
vertex_lists = [sorted(p) for p in vertex_partition]
leaf_set = set(leaves)
leaf_lists = [sorted(s & leaf_set) for s in vertex_partition]
# order the list of leaves in a nice block form
leaves = [v for lst in leaf_lists for v in lst]
# remove internal vertices by Schur complementation
L_schur_rooted = Ftree.TB_to_L_schur(T, B, leaves + [r])
L_schur_full = Ftree.TB_to_L_schur(T, B, leaves)
# show the matrix
np.set_printoptions(linewidth=132)
out = StringIO()
# show the rooted schur complement
w, v = scipy.linalg.eigh(L_schur_rooted)
print >> out, 'rooted Schur complement:'
print >> out, L_schur_rooted
print >> out, 'Felsenstein weights at the root:'
print >> out, -L_schur_rooted[-1][:-1] / L_schur_rooted[-1, -1]
print >> out, 'rooted Schur complement eigendecomposition:'
print >> out, w
print >> out, v
print >> out
# show the full schur complement
w, v = scipy.linalg.eigh(L_schur_full)
print >> out, 'full Schur complement:'
print >> out, L_schur_full
print >> out, 'full Schur complement eigendecomposition:'
print >> out, w
print >> out, v
print >> out
# analyze perron components
print >> out, 'perron components:'
print >> out
start = 0
for lst in leaf_lists:
n = len(lst)
C = L_schur_rooted[start:start + n, start:start + n]
print >> out, 'C:'
print >> out, C
w_eff = np.sum(C)
b_eff = 1 / w_eff
print >> out, 'effective conductance:'
print >> out, w_eff
print >> out, 'effective branch length (or resistance or variance):'
print >> out, b_eff
S = np.linalg.pinv(C)
print >> out, 'C^-1 (rooted covariance-like):'
print >> out, S
w, v = scipy.linalg.eigh(S)
print >> out, 'rooted covariance-like eigendecomposition:'
print >> out, w
print >> out, v
print >> out, 'perron value:'
print >> out, w[-1]
print >> out, 'reciprocal of perron value:'
print >> out, 1 / w[-1]
print >> out
start += n
print >> out
# analyze subtrees
print >> out, 'subtree Laplacian analysis:'
print >> out
start = 0
for lst in vertex_lists:
n = len(lst)
C = Ftree.TB_to_L_schur(T, B, lst + [r])
w, v = scipy.linalg.eigh(C)
print >> out, 'subtree Laplacian:'
print >> out, C
print >> out, 'eigendecomposition:'
print >> out, w
print >> out, v
print >> out
start += n
# analyze subtrees
print >> out, 'full Schur complement subtree analysis:'
print >> out
start = 0
for lst in leaf_lists:
n = len(lst)
C = Ftree.TB_to_L_schur(T, B, lst + [r])
w, v = scipy.linalg.eigh(C)
print >> out, 'full Schur complement in subtree:'
print >> out, C
print >> out, 'eigendecomposition:'
print >> out, w
print >> out, v
print >> out
start += n
return out.getvalue()
def get_algebraic_connectivity(T, B, leaves):
L_schur = Ftree.TB_to_L_schur(T, B, leaves)
w = scipy.linalg.eigh(L_schur, eigvals_only=True)
return w[1]
def get_response_content(fs):
nseconds_limit = 5.0
R_true, B_true = FtreeIO.newick_to_RB(fs.true_tree, int)
R_test = FtreeIO.newick_to_R(fs.test_tree, int)
# get the unrooted tree topology
T_true = Ftree.R_to_T(R_true)
T_test = Ftree.R_to_T(R_test)
# check the trees for vertex compatibility
if set(Ftree.T_to_order(T_true)) != set(Ftree.T_to_order(T_test)):
raise ValueError('vertex sets are not equal')
if set(Ftree.T_to_leaves(T_true)) != set(Ftree.T_to_leaves(T_test)):
raise ValueError('leaf vertex sets are not equal')
if set(Ftree.T_to_internal_vertices(T_true)) != set(
Ftree.T_to_internal_vertices(T_test)):
raise ValueError('internal vertex sets are not equal')
# get the 2D MDS for the true tree
leaves = Ftree.T_to_leaves(T_true)
internal = Ftree.T_to_internal_vertices(T_true)
vertices = leaves + internal
L_schur = Ftree.TB_to_L_schur(T_true, B_true, leaves)
w_all, Vp_all = scipy.linalg.eigh(L_schur)
w, Vp = w_all[1:3], Vp_all[:, 1:3]
# make the constant matrix for Frobenius norm comparison
C = np.zeros((len(vertices), 2))
C[:len(leaves)] = w * Vp
# keep doing iterations until we run out of time
mymax = 256
t_initial = time.time()
while time.time() - t_initial < nseconds_limit / 2:
mymax *= 2
f = Functor(T_test.copy(), Vp.copy(), C.copy(), w.copy())
initial_guess = np.ones(len(T_test) + 2 * len(internal))
results = scipy.optimize.fmin(f,
initial_guess,
ftol=1e-8,
xtol=1e-8,
full_output=True,
maxfun=mymax,
maxiter=mymax)
xopt, fopt, itr, funcalls, warnflag = results
# look at the values from the longest running iteration
B, Vr = f.X_to_B_Vr(xopt)
L, V = f.X_to_L_V(xopt)
Lrr = Ftree.TB_to_L_block(T_test, B, internal, internal)
Lrp = Ftree.TB_to_L_block(T_test, B, internal, leaves)
H_ext = -np.dot(np.linalg.pinv(Lrr), Lrp)
N = dict((v, str(v)) for v in vertices)
# start writing the response
out = StringIO()
print >> out, 'xopt:', xopt
print >> out, 'fopt:', fopt
print >> out, 'number of iterations:', itr
print >> out, 'number of function calls:', funcalls
print >> out, 'warning flags:', warnflag
print >> out, 'first four eigenvalues:', w_all[:4]
print >> out, 'Vr:'
print >> out, Vr
print >> out, '-Lrr^-1 Lrp Vp:'
print >> out, np.dot(H_ext, Vp)
print >> out, C
print >> out, np.dot(L, V)
print >> out, FtreeIO.RBN_to_newick(R_test, B, N)
return out.getvalue()
