def swap_tree(tree):
# make safe tree
if not '"' in tree:
tree = nwk.safe_newick_string(tree)
# swap two nodes of the tree
nodes = list(nwk.nodes_in_tree(tree))[1:]
random.shuffle(nodes)
# choose two nodes to be swapped
nodeA = nodes.pop(0)
# get another node that can be interchanged
while nodes:
nodeB = nodes.pop(0)
if nodeB in nodeA or nodeA in nodeB:
pass
else:
break
tree = tree.replace(nodeA+',', '#dummyA#,')
tree = tree.replace(nodeA+')', '#dummyA#)')
tree = tree.replace(nodeB+',', '#dummyB#,')
tree = tree.replace(nodeB+')', '#dummyB#)')
tree = tree.replace('#dummyA#', nodeB)
tree = tree.replace('#dummyB#', nodeA)
return nwk.sort_tree(tree).replace('"','')
def all_rooted_binary_trees(*taxa):
"""
Compute all rooted trees.
Notes
-----
This procedure yields all rooted binary trees for a given set of taxa, as
described in :bib:`Felsenstein1978`. It implements a depth-first search.
"""
if len(taxa) <= 2:
yield '('+','.join(taxa)+');'
# make queue with taxa included and taxa to be visited
queue = [('('+','.join(taxa[:2])+')', list(taxa[2:]))]
out = []
while queue:
# add next taxon
tree, rest = queue.pop()
if rest:
next_taxon = rest.pop()
nodes = list(nwk.nodes_in_tree(tree))
random.shuffle(nodes)
for node in nodes:
new_tree = tree.replace(node, '('+next_taxon+','+node+')')
r = [x for x in rest]
random.shuffle(r)
queue += [(new_tree, r)]
if not rest:
yield new_tree
def branch_and_bound(
taxa,
patterns,
transitions,
characters,
guide_tree = False,
verbose = True,
lower_bound = False,
sample_steps = 100,
):
"""
Try to make a branch and bound parsimony calculation.
"""
# calculate the lower bound
if lower_bound:
pass
elif not guide_tree:
lower_bound = mst_weight(taxa, patterns, transitions, characters) * 2
print("[i] Lower Bound (estimated):", lower_bound)
else:
lower_bound = 0
ltree = nwk.LingPyTree(guide_tree)
for p,t,c in zip(patterns, transitions, characters):
lower_bound += sankoff_parsimony_up(
p,
taxa,
ltree,
t,
c,
weight_only=True
)
print("[i] Lower Bound (in guide tree):",lower_bound)
trees = []
# we start doing the same as in the case of the calculation of all rooted
# trees below
if len(taxa) <= 2:
return '('+','.join(taxa)+');'
# make queue with taxa included and taxa to be visited
queue = [('('+','.join(taxa[:2])+')', taxa[2:], lower_bound)]
visited = 0
all_trees = []
previous = 0
M = {}
while queue:
queue = sorted(queue, key = lambda x: (len(x[1]), x[2]))
# add next taxon
tree, rest, bound = queue.pop(0)
if rest:
next_taxon = rest.pop()
nodes = list(nwk.nodes_in_tree(tree))
random.shuffle(nodes)
for node in nwk.nodes_in_tree(tree):
new_tree = tree.replace(node, '('+next_taxon+','+node+')')
visited += 1
# parsimony evaluation and lower bound comes here
score = 0
ltree = nwk.LingPyTree(new_tree)
for p,t,c in zip(patterns, transitions, characters):
weight,chars = sankoff_parsimony_up(
p,
taxa,
ltree,
t,
c,
weight_and_chars =True
)
score += weight
if rest:
if tuple(rest) in M:
mst = M[tuple(rest)]
else:
mst = mst_weight(rest, patterns, transitions, characters)
M[tuple(rest)] = mst
score += mst
else:
all_trees += [new_tree]
if score <= lower_bound:
r = [x for x in rest]
random.shuffle(r)
queue += [(new_tree, r, score)]
if not rest:
if score < lower_bound:
lower_bound = score
trees = [nwk.sort_tree(new_tree)]
queue = [q for q in queue if q[2] <= lower_bound]
else:
trees += [nwk.sort_tree(new_tree)]
if len(all_trees) % sample_steps == 0 and len(all_trees) > previous:
print("[i] Checked {0} trees so far, current lower bound is {1} with {2} best trees.".format(
len(all_trees),
lower_bound,
len(trees)
))
previous = len(all_trees)
return trees, lower_bound
