Biopython

from Bio import Phylo

# Read a tree from file
tree = Phylo.read("tree.nwk", "newick")

# Parse multiple trees from a file
trees = list(Phylo.parse("trees.nwk", "newick"))
print(f"Found {len(trees)} trees")

# Write tree to file
Phylo.write(tree, "output.nwk", "newick")

# Write multiple trees
Phylo.write(trees, "output.nex", "nexus")

# Convert between formats
count = Phylo.convert("input.nwk", "newick", "output.xml", "phyloxml")
print(f"Converted {count} trees")

# Tree root
root = tree.root

# Terminal nodes (leaves)
terminals = tree.get_terminals()
print(f"Number of taxa: {len(terminals)}")

# Non-terminal nodes
nonterminals = tree.get_nonterminals()
print(f"Number of internal nodes: {len(nonterminals)}")

# All clades
all_clades = list(tree.find_clades())
print(f"Total clades: {len(all_clades)}")

# Iterate through all clades
for clade in tree.find_clades():
    if clade.name:
        print(f"Clade: {clade.name}, Branch length: {clade.branch_length}")

# Iterate through terminals only
for terminal in tree.get_terminals():
    print(f"Taxon: {terminal.name}")

# Depth-first traversal
for clade in tree.find_clades(order="preorder"):
    print(clade.name)

# Level-order (breadth-first) traversal
for clade in tree.find_clades(order="level"):
    print(clade.name)

# Find clade by name
clade = tree.find_any(name="Species_A")

# Find all clades matching criteria
def is_long_branch(clade):
    return clade.branch_length and clade.branch_length > 0.5

long_branches = tree.find_clades(is_long_branch)

# Total branch length
total_length = tree.total_branch_length()
print(f"Total tree length: {total_length:.3f}")

# Tree depth (root to furthest leaf)
depths = tree.depths()
max_depth = max(depths.values())
print(f"Maximum depth: {max_depth:.3f}")

# Terminal count
terminal_count = tree.count_terminals()
print(f"Number of taxa: {terminal_count}")

# Distance between two taxa
distance = tree.distance("Species_A", "Species_B")
print(f"Distance: {distance:.3f}")

# Create distance matrix
from Bio import Phylo

terminals = tree.get_terminals()
taxa_names = [t.name for t in terminals]

print("Distance Matrix:")
for taxon1 in taxa_names:
    row = []
    for taxon2 in taxa_names:
        if taxon1 == taxon2:
            row.append(0)
        else:
            dist = tree.distance(taxon1, taxon2)
            row.append(dist)
    print(f"{taxon1}: {row}")

# Find common ancestor of two clades
clade1 = tree.find_any(name="Species_A")
clade2 = tree.find_any(name="Species_B")
ancestor = tree.common_ancestor(clade1, clade2)
print(f"Common ancestor: {ancestor.name}")

# Find common ancestor of multiple clades
clades = [tree.find_any(name=n) for n in ["Species_A", "Species_B", "Species_C"]]
ancestor = tree.common_ancestor(*clades)

# Compare pairwise path lengths (not a topology test)
def compare_trees(tree1, tree2):
    """Compare branch-length distances for the same uniquely named taxa."""
    # Get terminal names
    taxa1 = set(t.name for t in tree1.get_terminals())
    taxa2 = set(t.name for t in tree2.get_terminals())

    # Check if they have same taxa
    if taxa1 != taxa2:
        return False, "Different taxa"

    # Compare distances
    differences = []
    for taxon1 in taxa1:
        for taxon2 in taxa1:
            if taxon1 < taxon2:
                dist1 = tree1.distance(taxon1, taxon2)
                dist2 = tree2.distance(taxon1, taxon2)
                if abs(dist1 - dist2) > 0.01:
                    differences.append((taxon1, taxon2, dist1, dist2))

    return len(differences) == 0, differences

# Prune (remove) specific taxa
import copy
tree_copy = copy.deepcopy(tree)
tree_copy.prune("Species_A")

# Keep only specific taxa
taxa_to_keep = ["Species_B", "Species_C", "Species_D"]
terminals = tree_copy.get_terminals()
for terminal in terminals:
    if terminal.name not in taxa_to_keep:
        tree_copy.prune(terminal)

# Collapse branches shorter than threshold
def collapse_short_branches(tree, threshold=0.01):
    """Collapse branches shorter than threshold."""
    tree.collapse_all(lambda clade: clade.branch_length is not None
                      and clade.branch_length < threshold)
    return tree

# Ladderize tree (sort branches by size)
tree.ladderize()  # ascending order
tree.ladderize(reverse=True)  # descending order

# Reroot at midpoint
tree.root_at_midpoint()

# Reroot with outgroup
outgroup = tree.find_any(name="Outgroup_Species")
tree.root_with_outgroup(outgroup)

# Reroot at internal node
internal = tree.get_nonterminals()[0]
tree.root_with_outgroup(internal)

# Draw tree to console
Phylo.draw_ascii(tree)

# Draw with custom format
Phylo.draw_ascii(tree, column_width=80)

import matplotlib.pyplot as plt
from Bio import Phylo

# Simple plot
fig = plt.figure(figsize=(10, 8))
axes = fig.add_subplot(1, 1, 1)
Phylo.draw(tree, axes=axes)
plt.show()

# Customize plot
fig = plt.figure(figsize=(10, 8))
axes = fig.add_subplot(1, 1, 1)
Phylo.draw(tree, axes=axes, do_show=False)
axes.set_title("Phylogenetic Tree")
plt.tight_layout()
plt.savefig("tree.png", dpi=300)

# Rectangular tree with branch-length labels (draw is not a radial renderer)
Phylo.draw(tree, branch_labels=lambda c: c.branch_length)

# Show branch support values
Phylo.draw(tree, label_func=lambda n: str(n.confidence) if n.confidence else "")

# Color branches
def color_by_length(clade):
    if clade.branch_length:
        if clade.branch_length > 0.5:
            return "red"
        elif clade.branch_length > 0.2:
            return "orange"
    return "black"

for clade in tree.find_clades():
    clade.color = color_by_length(clade)
Phylo.draw(tree)

from Bio.Phylo.TreeConstruction import DistanceTreeConstructor, DistanceMatrix

# Create distance matrix
dm = DistanceMatrix(
    names=["Alpha", "Beta", "Gamma", "Delta"],
    matrix=[
        [0],
        [0.23, 0],
        [0.45, 0.34, 0],
        [0.67, 0.58, 0.29, 0]
    ]
)

# Build tree using UPGMA
constructor = DistanceTreeConstructor()
tree = constructor.upgma(dm)
Phylo.draw_ascii(tree)

# Build tree using Neighbor-Joining
tree = constructor.nj(dm)

from Bio import AlignIO, Phylo
from Bio.Phylo.TreeConstruction import DistanceCalculator, DistanceTreeConstructor

# Read alignment
alignment = AlignIO.read("alignment.fasta", "fasta")

# Calculate distance matrix
calculator = DistanceCalculator("identity")
distance_matrix = calculator.get_distance(alignment)

# Build tree
constructor = DistanceTreeConstructor()
tree = constructor.upgma(distance_matrix)

# Write tree
Phylo.write(tree, "output_tree.nwk", "newick")

# Use different model
calculator = DistanceCalculator("blosum62")
dm = calculator.get_distance(alignment)

from Bio.Phylo.Consensus import majority_consensus, strict_consensus

# Read multiple trees
trees = list(Phylo.parse("bootstrap_trees.nwk", "newick"))

# Majority-rule consensus
consensus = majority_consensus(trees, cutoff=0.5)

# Strict consensus
strict_cons = strict_consensus(trees)

# Write consensus tree
Phylo.write(consensus, "consensus.nwk", "newick")

from Bio.Phylo.PhyloXML import Phylogeny, Clade

# Create PhyloXML tree
tree = Phylogeny(rooted=True)
tree.name = "Example Tree"
tree.description = "A sample phylogenetic tree"

# Add clades with rich annotations
clade = Clade(branch_length=0.5)
clade.name = "Species_A"
clade.color = "red"
clade.width = 2.0

# Add taxonomy information
from Bio.Phylo.PhyloXML import Taxonomy
taxonomy = Taxonomy(scientific_name="Homo sapiens", common_name="Human")
clade.taxonomies.append(taxonomy)

# Add bootstrap support values to tree
def add_bootstrap_support(tree, support_values):
    """Attach already computed support in a verified matching node order.

    This does not compute bootstrap support. Match bipartitions if tree order differs.
    """
    internal_nodes = tree.get_nonterminals()
    if len(internal_nodes) != len(support_values):
        raise ValueError("Support count does not match the internal nodes")
    for node, support in zip(internal_nodes, support_values):
        node.confidence = support
    return tree

# Illustrative input only: use support estimates mapped to this exact tree.
# tree_with_support = add_bootstrap_support(tree, support_values)

from Bio import AlignIO, Phylo
from Bio.Phylo.TreeConstruction import DistanceCalculator, DistanceTreeConstructor

# Read aligned sequences
alignment = AlignIO.read("sequences.aln", "clustal")

# Calculate distances
calculator = DistanceCalculator("identity")
dm = calculator.get_distance(alignment)

# Build neighbor-joining tree
constructor = DistanceTreeConstructor()
tree = constructor.nj(dm)

# Root at midpoint
tree.root_at_midpoint()

# Save tree
Phylo.write(tree, "tree.nwk", "newick")

# Visualize
import matplotlib.pyplot as plt
fig = plt.figure(figsize=(10, 8))
Phylo.draw(tree)
plt.show()

def extract_subtree(tree, taxa_list):
    """Extract subtree containing specific taxa."""
    available = [t.name for t in tree.get_terminals()]
    if not taxa_list or not set(taxa_list) <= set(available):
        raise ValueError("Choose a nonempty subset of existing tips")
    # Create a copy
    import copy
    subtree = copy.deepcopy(tree)

    # Get all terminals
    all_terminals = subtree.get_terminals()

    # Prune taxa not in list
    for terminal in all_terminals:
        if terminal.name not in taxa_list:
            subtree.prune(terminal)

    return subtree

# Use it
subtree = extract_subtree(tree, ["Species_A", "Species_B", "Species_C"])
Phylo.write(subtree, "subtree.nwk", "newick")

def phylogenetic_diversity(tree, taxa_subset=None):
    """Sum retained branch lengths under this pruning/root convention.

    State the root/stem convention before interpreting this as diversity.
    """
    if taxa_subset is not None:
        # Prune to subset
        tree = extract_subtree(tree, taxa_subset)

    # Sum all branch lengths
    total = 0
    for clade in tree.find_clades():
        if clade.branch_length:
            total += clade.branch_length

    return total

# Calculate PD for all taxa
pd_all = phylogenetic_diversity(tree)
print(f"Total phylogenetic diversity: {pd_all:.3f}")

# Calculate PD for subset
pd_subset = phylogenetic_diversity(tree, ["Species_A", "Species_B"])
print(f"Subset phylogenetic diversity: {pd_subset:.3f}")

def annotate_tree_from_csv(tree, csv_file):
    """Annotate tree leaves with data from CSV."""
    import csv

    # Read annotation data
    annotations = {}
    with open(csv_file) as f:
        reader = csv.DictReader(f)
        for row in reader:
            annotations[row["species"]] = row

    # Annotate tree
    for terminal in tree.get_terminals():
        if terminal.name in annotations:
            # Add custom attributes
            for key, value in annotations[terminal.name].items():
                setattr(terminal, key, value)

    return tree

def robinson_foulds_distance(tree1, tree2):
    """Unnormalized rooted RF distance for identical, uniquely named tip sets."""
    def taxa(tree):
        names = [t.name for t in tree.get_terminals()]
        if any(n is None for n in names) or len(set(names)) != len(names):
            raise ValueError("Tips must have unique nonempty names")
        return frozenset(names)

    tips = taxa(tree1)
    if not tree1.rooted or not tree2.rooted or taxa(tree2) != tips:
        raise ValueError("Requires explicitly rooted trees on the same tip set")

    def clusters(tree):
        return {frozenset(t.name for t in c.get_terminals())
                for c in tree.get_nonterminals()
                if 1 < len(c.get_terminals()) < len(tips)}

    return len(clusters(tree1) ^ clusters(tree2))

# Use it
tree1 = Phylo.read("tree1.nwk", "newick", rooted=True)
tree2 = Phylo.read("tree2.nwk", "newick", rooted=True)
# rooted=True asserts an input convention; it does not infer a biological root.
rf_dist = robinson_foulds_distance(tree1, tree2)
print(f"Robinson-Foulds distance: {rf_dist}")