def _part(clades):
"""recursive function of adam consensus algorithm"""
new_clade = None
terms = clades[0].get_terminals()
term_names = [term.name for term in terms]
if len(terms) == 1 or len(terms) == 2:
new_clade = clades[0]
else:
bitstrs = set([_BitString('1' * len(terms))])
for clade in clades:
for child in clade.clades:
bitstr = _clade_to_bitstr(child, term_names)
to_remove = set()
to_add = set()
for bs in bitstrs:
if bs == bitstr:
continue
elif bs.contains(bitstr):
to_add.add(bitstr)
to_add.add(bs ^ bitstr)
to_remove.add(bs)
elif bitstr.contains(bs):
to_add.add(bs ^ bitstr)
elif not bs.independent(bitstr):
to_add.add(bs & bitstr)
to_add.add(bs & bitstr ^ bitstr)
to_add.add(bs & bitstr ^ bs)
to_remove.add(bs)
#bitstrs = bitstrs | to_add
bitstrs ^= to_remove
if to_add:
for ta in sorted(to_add, key=lambda bs: bs.count('1')):
independent = True
for bs in bitstrs:
if not ta.independent(bs):
independent = False
break
if independent:
bitstrs.add(ta)
new_clade = BaseTree.Clade()
for bitstr in sorted(bitstrs):
indices = bitstr.index_one()
if len(indices) == 1:
new_clade.clades.append(terms[indices[0]])
elif len(indices) == 2:
bifur_clade = BaseTree.Clade()
bifur_clade.clades.append(terms[indices[0]])
bifur_clade.clades.append(terms[indices[1]])
new_clade.clades.append(bifur_clade)
elif len(indices) > 2:
part_names = [term_names[i] for i in indices]
next_clades = []
for clade in clades:
next_clades.append(_sub_clade(clade, part_names))
# next_clades = [clade.common_ancestor([clade.find_any(name=name) for name in part_names]) for clade in clades]
new_clade.clades.append(_part(next_clades))
return new_clade
def strict_consensus(trees):
"""Search strict consensus tree from multiple trees.
:Parameters:
trees: list
list of trees to produce consensus tree.
"""
terms = trees[0].get_terminals()
bitstr_counts = _count_clades(trees)
# Store bitstrs for strict clades
strict_bitstrs = [
bitstr for bitstr, t in bitstr_counts.items() if t[0] == len(trees)
]
strict_bitstrs.sort(key=lambda bitstr: bitstr.count('1'), reverse=True)
# Create root
root = BaseTree.Clade()
if strict_bitstrs[0].count('1') == len(terms):
root.clades.extend(terms)
else:
raise ValueError('Taxons in provided trees should be consistent')
# make a bitstr to clades dict and store root clade
bitstr_clades = {strict_bitstrs[0]: root}
# create inner clades
for bitstr in strict_bitstrs[1:]:
clade_terms = [terms[i] for i in bitstr.index_one()]
clade = BaseTree.Clade()
clade.clades.extend(clade_terms)
for bs, c in bitstr_clades.items():
# check if it should be the parent of current clade
if bs.contains(bitstr):
# remove old bitstring
del bitstr_clades[bs]
# update clade childs
new_childs = [
child for child in c.clades if child not in clade_terms
]
c.clades = new_childs
# set current clade as child of c
c.clades.append(clade)
# update bitstring
bs = bs ^ bitstr
# update clade
bitstr_clades[bs] = c
break
# put new clade
bitstr_clades[bitstr] = clade
return BaseTree.Tree(root=root)
def adam_consensus(trees):
"""Search Adam Consensus tree from multiple trees
:Parameters:
trees: list
list of trees to produce consensus tree.
"""
clades = [tree.root for tree in trees]
return BaseTree.Tree(root=_part(clades), rooted=True)
def _sub_clade(clade, term_names):
"""extract a compatible subclade that only contains the given terminal names
"""
term_clades = [clade.find_any(name) for name in term_names]
sub_clade = clade.common_ancestor(term_clades)
if len(term_names) != sub_clade.count_terminals():
temp_clade = BaseTree.Clade()
temp_clade.clades.extend(term_clades)
for c in sub_clade.find_clades(terminal=False, order="preorder"):
if c == sub_clade.root:
continue
childs = set(c.find_clades(terminal=True)) & set(term_clades)
if childs:
for tc in temp_clade.find_clades(terminal=False,
order="preorder"):
tc_childs = set(tc.clades)
tc_new_clades = tc_childs - childs
if childs.issubset(tc_childs) and tc_new_clades:
tc.clades = list(tc_new_clades)
child_clade = BaseTree.Clade()
child_clade.clades.extend(list(childs))
tc.clades.append(child_clade)
sub_clade = temp_clade
return sub_clade
def nj(self, distance_matrix):
"""Construct and return an Neighbor Joining tree.
:Parameters:
distance_matrix : _DistanceMatrix
The distance matrix for tree construction.
"""
if not isinstance(distance_matrix, _DistanceMatrix):
raise TypeError("Must provide a _DistanceMatrix object.")
# make a copy of the distance matrix to be used
dm = copy.deepcopy(distance_matrix)
# init terminal clades
clades = [BaseTree.Clade(None, name) for name in dm.names]
# init node distance
node_dist = [0] * len(dm)
# init minimum index
min_i = 0
min_j = 0
inner_count = 0
while len(dm) > 2:
# calculate nodeDist
for i in range(0, len(dm)):
node_dist[i] = 0
for j in range(0, len(dm)):
node_dist[i] += dm[i, j]
node_dist[i] = node_dist[i] / (len(dm) - 2)
# find minimum distance pair
min_dist = dm[1, 0] - node_dist[1] - node_dist[0]
min_i = 0
min_j = 1
for i in range(1, len(dm)):
for j in range(0, i):
temp = dm[i, j] - node_dist[i] - node_dist[j]
if min_dist > temp:
min_dist = temp
min_i = i
min_j = j
# create clade
clade1 = clades[min_i]
clade2 = clades[min_j]
inner_count += 1
inner_clade = BaseTree.Clade(None, "Inner" + str(inner_count))
inner_clade.clades.append(clade1)
inner_clade.clades.append(clade2)
#assign branch length
clade1.branch_length = (dm[min_i, min_j] + node_dist[min_i]
- node_dist[min_j]) / 2.0
clade2.branch_length = dm[min_i, min_j] - clade1.branch_length
# update node list
clades[min_j] = inner_clade
del clades[min_i]
# rebuild distance matrix,
# set the distances of new node at the index of min_j
for k in range(0, len(dm)):
if k != min_i and k != min_j:
dm[min_j, k] = (dm[min_i, k] + dm[min_j, k]
- dm[min_i, min_j]) / 2.0
dm.names[min_j] = "Inner" + str(inner_count)
del dm[min_i]
# set the last clade as one of the child of the inner_clade
root = None
if clades[0] == inner_clade:
clades[0].branch_length = 0
clades[1].branch_length = dm[1, 0]
clades[0].clades.append(clades[1])
root = clades[0]
else:
clades[0].branch_length = dm[1, 0]
clades[1].branch_length = 0
clades[1].clades.append(clades[0])
root = clades[1]
return BaseTree.Tree(root, rooted=False)
def upgma(self, distance_matrix):
"""Construct and return an UPGMA(Unweighted Pair Group Method
with Arithmetic mean) tree.
:Parameters:
distance_matrix : _DistanceMatrix
The distance matrix for tree construction.
"""
if not isinstance(distance_matrix, _DistanceMatrix):
raise TypeError("Must provide a _DistanceMatrix object.")
# make a copy of the distance matrix to be used
dm = copy.deepcopy(distance_matrix)
# init terminal clades
clades = [BaseTree.Clade(None, name) for name in dm.names]
# init minimum index
min_i = 0
min_j = 0
inner_count = 0
while len(dm) > 1:
min_dist = dm[1, 0]
# find minimum index
for i in range(1, len(dm)):
for j in range(0, i):
if min_dist >= dm[i, j]:
min_dist = dm[i, j]
min_i = i
min_j = j
# create clade
clade1 = clades[min_i]
clade2 = clades[min_j]
inner_count += 1
inner_clade = BaseTree.Clade(None, "Inner" + str(inner_count))
inner_clade.clades.append(clade1)
inner_clade.clades.append(clade2)
#assign branch length
if clade1.is_terminal():
clade1.branch_length = min_dist * 1.0 / 2
else:
clade1.branch_length = min_dist * 1.0 / 2 - self._height_of(clade1)
if clade2.is_terminal():
clade2.branch_length = min_dist * 1.0 / 2
else:
clade2.branch_length = min_dist * 1.0 / 2 - self._height_of(clade2)
# update node list
clades[min_j] = inner_clade
del clades[min_i]
# rebuild distance matrix,
# set the distances of new node at the index of min_j
for k in range(0, len(dm)):
if k != min_i and k != min_j:
dm[min_j, k] = (dm[min_i, k] + dm[min_j, k]) * 1.0 / 2
dm.names[min_j] = "Inner" + str(inner_count)
del dm[min_i]
inner_clade.branch_length = 0
return BaseTree.Tree(inner_clade)
def majority_consensus(trees, cutoff=0):
"""Search majority rule consensus tree from multiple trees.
This is a extend majority rule method, which means the you can set any
cutoff between 0 ~ 1 instead of 0.5. The default value of cutoff is 0 to
create a relaxed binary consensus tree in any condition (as long as one of
the provided trees is a binary tree). The branch length of each consensus
clade in the result consensus tree is the average length of all counts for
that clade.
:Parameters:
trees: list
list of trees to produce consensus tree.
"""
terms = trees[0].get_terminals()
bitstr_counts = _count_clades(trees)
# Sort bitstrs by descending #occurrences, then #tips, then tip order
bitstrs = sorted(
bitstr_counts.keys(),
key=lambda bitstr:
(bitstr_counts[bitstr][0], bitstr.count('1'), str(bitstr)),
reverse=True)
root = BaseTree.Clade()
if bitstrs[0].count('1') == len(terms):
root.clades.extend(terms)
else:
raise ValueError('Taxons in provided trees should be consistent')
# Make a bitstr-to-clades dict and store root clade
bitstr_clades = {bitstrs[0]: root}
# create inner clades
for bitstr in bitstrs[1:]:
# apply majority rule
count_in_trees, branch_length_sum = bitstr_counts[bitstr]
confidence = 100.0 * count_in_trees / len(trees)
if confidence < cutoff * 100.0:
break
clade_terms = [terms[i] for i in bitstr.index_one()]
clade = BaseTree.Clade()
clade.clades.extend(clade_terms)
clade.confidence = confidence
clade.branch_length = branch_length_sum / count_in_trees
bsckeys = sorted(bitstr_clades,
key=lambda bs: bs.count('1'),
reverse=True)
# check if current clade is compatible with previous clades and
# record it's possible parent and child clades.
compatible = True
parent_bitstr = None
child_bitstrs = [] # multiple independent childs
for bs in bsckeys:
if not bs.iscompatible(bitstr):
compatible = False
break
# assign the closest ancestor as its parent
# as bsckeys is sorted, it should be the last one
if bs.contains(bitstr):
parent_bitstr = bs
# assign the closest descendant as its child
# the largest and independent clades
if (bitstr.contains(bs) and bs != bitstr
and all(c.independent(bs) for c in child_bitstrs)):
child_bitstrs.append(bs)
if not compatible:
continue
if parent_bitstr:
# insert current clade; remove old bitstring
parent_clade = bitstr_clades.pop(parent_bitstr)
# update parent clade childs
parent_clade.clades = [
c for c in parent_clade.clades if c not in clade_terms
]
# set current clade as child of parent_clade
parent_clade.clades.append(clade)
# update bitstring
# parent = parent ^ bitstr
# update clade
bitstr_clades[parent_bitstr] = parent_clade
if child_bitstrs:
remove_list = []
for c in child_bitstrs:
remove_list.extend(c.index_one())
child_clade = bitstr_clades[c]
parent_clade.clades.remove(child_clade)
clade.clades.append(child_clade)
remove_terms = [terms[i] for i in remove_list]
clade.clades = [c for c in clade.clades if c not in remove_terms]
# put new clade
bitstr_clades[bitstr] = clade
if ((len(bitstr_clades) == len(terms) - 1) or
(len(bitstr_clades) == len(terms) - 2 and len(root.clades) == 3)):
break
return BaseTree.Tree(root=root)