def NJ_Algorithm():
"""
Neighbor-Joining algorithm to join species and create phylogenetic tree
"""
phylo_tree = None
tree_dict = dict()
# Loop through species until down to one pair
for k in range(len(species)-1):
# Get average distance for every node
node_avg = ComputeNodeAvgDist()
# Find lowest pair of species to join from average distance species list
min_val, min_a, min_b = FindLowestPair(node_avg)
if species[min_a] in tree_dict:
# If the first joined species is already in the tree dictionary, retrieve it
child1 = tree_dict[species[min_a]]
else:
# Else create new species tree
child1 = Tree(species[min_a])
# v_i = D_ij/2 + (u_i - u_j)/2
child1.value = min_val/2.0 + (node_avg[min_a] - node_avg[min_b])/2.0
if species[min_b] in tree_dict:
# If the second joined species is already in the tree dictionary, retrieve it
child2 = tree_dict[species[min_b]]
else:
# Else create new species tree
child2 = Tree(species[min_b])
# v_j = D_ij/2 + (u_j - u_i)/2
child2.value = min_val/2.0 + (node_avg[min_b] - node_avg[min_a])/2.0
# Create new tree with both A and B species joined
key = "(" + species[min_a] + "),(" + species[min_b] + ")"
phylo_tree = Tree(key)
phylo_tree.value = min_val/2.0
# Put lower value to left of tree
if child1.value <= child2.value:
phylo_tree.AddLeftChild(child1, child1.value)
phylo_tree.AddRightChild(child2, child2.value)
else:
phylo_tree.AddLeftChild(child2, child2.value)
phylo_tree.AddRightChild(child1, child1.value)
#phylo_tree.printNodeInfo()
tree_dict[key] = phylo_tree
# Create joined values to put back into 2d matrix
joinedDist = CreateJoinedDistances(min_a, min_b, min_val)
# Remove A and B individually and insert AB joined
CombineSpecies(joinedDist, min_a, min_b)
return phylo_tree
def UPGMA_Algorithm():
"""
UPGMA algorithm to join species and create phylogenetic tree
"""
phylo_tree = None
tree_dict = dict()
# Loop through species until down to one pair
for k in range(len(species) - 1):
min_val, min_i, min_j = FindLowestPair()
if species[min_i] in tree_dict:
# If the first joined species is already in the tree dictionary, retrieve it
child1 = tree_dict[species[min_i]]
else:
# Else create new species tree
child1 = Tree(species[min_i])
child1.value = min_val / 2.0
if species[min_j] in tree_dict:
# If the second joined species is already in the tree dictionary, retrieve it
child2 = tree_dict[species[min_j]]
else:
# Else create new species tree
child2 = Tree(species[min_j])
child2.value = min_val / 2.0
# Create new tree with both A and B species joined
key = "(" + species[min_i] + "),(" + species[min_j] + ")"
phylo_tree = Tree(key)
phylo_tree.value = min_val / 2.0
# Put lower value to left of tree
if child1.value <= child2.value:
phylo_tree.AddLeftChild(child1, (phylo_tree.value - child1.value))
phylo_tree.AddRightChild(child2, (phylo_tree.value - child2.value))
else:
phylo_tree.AddLeftChild(child2, (phylo_tree.value - child2.value))
phylo_tree.AddRightChild(child1, (phylo_tree.value - child1.value))
#phylo_tree.printNodeInfo()
tree_dict[key] = phylo_tree
# Create joined values to put back into 2d matrix
joined_values = CreateJoinedDistances(min_i, min_j)
# Remove A and B individually and insert AB joined
CombineSpecies(joined_values, min_i, min_j)
return phylo_tree
def BuildTree(path_tuple):
"""
Build a tree structure from a given path tuple
"""
if _debug: print "##\nBuild Tree...\ntuple:", path_tuple
node_to_split, y_value = FindBestGain(path_tuple)
if node_to_split < 0:
if _debug: print "found leaf for tuple: ", path_tuple
training_tree = Tree("leaf")
training_tree.y_value = y_value
training_tree.is_leaf = True
else:
# Create node for attribute to split on
training_tree = Tree(_attrib_dict[str(node_to_split)])
# Build left side of tree for node
left_tuple = path_tuple + [(node_to_split, 0)]
left_tree = BuildTree(left_tuple)
training_tree.AddLeftChild(left_tree)
# Build right side of tree for node
right_tuple = path_tuple + [(node_to_split, 1)]
right_tree = BuildTree(right_tuple)
training_tree.AddRightChild(right_tree)
return training_tree
