def test_shortcut_functions(self):
t = PhyloTree(
"""((((Human_1, Chimp_1), (Human_2, (Chimp_2, Chimp_3))),
((Fish_1, (Human_3, Fish_3)), Yeast_2)), Yeast_1);""")
t.set_species_naming_function(lambda node: node.name.split("_")[0])
t.get_descendant_evol_events() # DDDSSSDDS
root = t.get_tree_root()
# Detects two consecutive nodes with duplications
pattern0 = """('n_duplications(@) > 0')'n_duplications(@) > 0 '; """
pattern1 = """( 'contains_leaves(@, ["Chimp_2", "Chimp_3"])'); """
pattern2 = """'n_speciations(@) > 3 '; """
pattern0 = TreePattern(pattern0)
pattern1 = TreePattern(pattern1)
pattern2 = TreePattern(pattern2)
pattern0_match = list(pattern0.find_match(t, maxhits=None))
pattern1_match = list(pattern1.find_match(t, maxhits=None))
pattern2_match = list(pattern2.find_match(t, maxhits=None))
self.assertEqual(len(pattern0_match), 5)
self.assertEqual(len(pattern1_match), 4)
self.assertEqual(pattern1_match[0], root)
self.assertEqual(len(pattern2_match), 2)
self.assertEqual(pattern2_match[0], root)
self.assertEqual(pattern2_match[1], root.children[0])
def test_species(self):
"""
tests if node.species and ncbi_query are working
"""
# test node.species
species_tree = PhyloTree(
"""(Felis_catus_1:1,
(Homo_sapiens_1:1, Pan_troglodytes_1:1),
Saccharomyces_cerevisiae_1:1);""",
format=1)
species_tree.set_species_naming_function(lambda n: n.name.split("_")[1] if "_" in n.name else '')
pattern0 = """('',
(' len(set(["sapiens","pygmaeus"]) & species(@))>0',
Pan_troglodytes_1)
);"""
pattern0 = TreePattern(pattern0)
root = species_tree.get_tree_root()
self.assertEqual(list(pattern0.find_match(species_tree)), [root])
# test ncbi taxonomy
ncbi = NCBITaxa()
taxonomy_tree = PhyloTree("((9598, 9606), 10090);", sp_naming_function=lambda name: name)
taxonomy_tree.annotate_ncbi_taxa()
root = taxonomy_tree.get_tree_root()
pattern1 = """ ' @.sci_name == "Euarchontoglires" ';"""
pattern2 = """
(( '@.sci_name=="H**o sapiens"' , '9526 in @.lineage ' )' @.rank=="subfamily" and @.taxid == 207598 ')
' @.sci_name == "Euarchontoglires" and "cellular organisms" in @.named_lineage';
"""
pattern1 = TreePattern(pattern1)
pattern2 = TreePattern(pattern2)
match1 = pattern1.find_match(taxonomy_tree)
match2 = pattern2.find_match(taxonomy_tree)
self.assertEqual(list(match1), [root])
self.assertEqual(list(match2), [root])
def ultrametricer(node_order, tree_file):
with open(tree_file) as f:
mytree = PhyloTree(f.next().strip(), format=1)
# First I get every single leaf
leaves = mytree.get_leaves()
# The total distance must be:
v = len(leaves)
# Now we get the expected distances
distances = dict()
for i, node in enumerate(node_order):
distances[node] = i + 1
for node in leaves:
distances[node.name] = v
# We add the root (that has no name)
distances[""] = 0
# We get the root
root = mytree.get_tree_root()
for node in leaves:
#Now I start traversing to the root
while (node.up):
# The expected distance of this branch is:
expected = distances[node.name] - distances[node.up.name]
node.dist = expected
node = node.up
return mytree.write(format=1)
def test_cached_attributes(self):
pattern0 = """ '"Gallus_gallus_1" in leaves(@)' ;"""
pattern1 = """( '"Hom" in species(@) and n_leaves(@) > 2')'"Pan_troglodytes_1" in leaves(@)';"""
pattern0 = TreePattern(pattern0)
pattern1 = TreePattern(pattern1)
tree = PhyloTree(
"((((Anolis_carolinensis_1:1, Gallus_gallus_1:1), (Felis_catus_1:1, (Homo_sapiens_1:1, Pan_troglodytes_1:1)primates)primates), ((Danio_rerio_1:1, (Xenopus_laevis_1:1, Anolis_carolinensis_1:1)), Saccharomyces_cerevisiae_2:1)), Saccharomyces_cerevisiae_1:1);",
format=1)
root = tree.get_tree_root()
pattern0_match = list(pattern0.find_match(tree, maxhits=None))
self.assertEqual(len(pattern0_match), 5) # returns leaf itself
self.assertEqual(pattern0_match[0], root)
self.assertEqual(pattern0_match[4].name, "Gallus_gallus_1")
pattern1_match = list(pattern1.find_match(tree, maxhits=None))
self.assertEqual(len(pattern1_match), 3)
self.assertEqual(pattern1_match[0], root)
self.assertEqual(pattern1_match[2].children[1].children[1].children[0].name, "Homo_sapiens_1")
print(t)
D = t & "D"
# Get the path from B to the root
node = D
path = []
while node.up:
path.append(node)
node = node.up
# I substract D node from the total number of visited nodes
print("There are", len(path) - 1, "nodes between D and the root")
A = t & "A"
# Get the path from B to the root
node = A
path = []
while node.up:
path.append(node)
node = node.up
print("There are", len(path) - 1, "nodes between A and the root")
print(t.children)
print(t.get_children())
print(t.up)
print(t.name)
print(t.dist)
print(t.is_leaf())
print(t.get_tree_root())
print(t.children[0].get_tree_root())
print(t.children[0].children[0].get_tree_root())
# You can also iterate over tree leaves using a simple syntax
for leaf in t:
print(leaf.name)