def test_newick__add_support__multiple_trees__partially_different_topologies():
main_tree = Newick.from_string("(((A,B),C),D);")
bootstraps = [Newick.from_string("(((C,D),A),B);"),
Newick.from_string("(((A,D),B),C);")]
expected = Newick.from_string("(((A,B)1,C)2,D);")
result = main_tree.add_support(bootstraps)
assert_equal(expected, result)
def test_newick__add_support__multiple_trees__two_cladees():
main_tree = Newick.from_string("((A,B),(C,(D,E)));")
bootstraps = [Newick.from_string("((((C,E),D),A),B);"),
Newick.from_string("(((A,(C,D)),B),E);")]
expected = Newick.from_string("((A,B)1,(C,(D,E)0)1);")
result = main_tree.add_support(bootstraps)
assert_equal(expected, result)
def _do_test_formatting(fmt, expected):
main_tree = Newick.from_string("(((A,B),C),D);")
bootstraps = [Newick.from_string("(((C,D),A),B);"),
Newick.from_string("(((C,B),A),D);"),
Newick.from_string("(((A,D),B),C);")]
expected = Newick.from_string(expected)
result = main_tree.add_support(bootstraps, fmt)
assert_equal(expected, result)
def test_newick__add_support__multiple_trees__two_cladees():
main_tree = Newick.from_string("((A,B),(C,(D,E)));")
bootstraps = [
Newick.from_string("((((C,E),D),A),B);"),
Newick.from_string("(((A,(C,D)),B),E);")
]
expected = Newick.from_string("((A,B)1,(C,(D,E)0)1);")
result = main_tree.add_support(bootstraps)
assert_equal(expected, result)
def test_newick__add_support__multiple_trees__partially_different_topologies():
main_tree = Newick.from_string("(((A,B),C),D);")
bootstraps = [
Newick.from_string("(((C,D),A),B);"),
Newick.from_string("(((A,D),B),C);")
]
expected = Newick.from_string("(((A,B)1,C)2,D);")
result = main_tree.add_support(bootstraps)
assert_equal(expected, result)
def _do_test_formatting(fmt, expected):
main_tree = Newick.from_string("(((A,B),C),D);")
bootstraps = [
Newick.from_string("(((C,D),A),B);"),
Newick.from_string("(((C,B),A),D);"),
Newick.from_string("(((A,D),B),C);")
]
expected = Newick.from_string(expected)
result = main_tree.add_support(bootstraps, fmt)
assert_equal(expected, result)
def test_newick__parse__subnode__two_taxa():
child_node_1 = Newick(name="A")
child_node_2a = Newick(name="B")
child_node_2b = Newick(name="C")
child_node_2 = Newick(children=[child_node_2a, child_node_2b])
top_node = Newick(children=[child_node_1, child_node_2])
assert_equal(Newick.from_string("(A,(B,C));"), top_node)
def test_newick__parse__subnode__two_taxa():
child_node_1 = Newick(name = "A")
child_node_2a = Newick(name = "B")
child_node_2b = Newick(name = "C")
child_node_2 = Newick(children = [child_node_2a, child_node_2b])
top_node = Newick(children = [child_node_1, child_node_2])
assert_equal(Newick.from_string("(A,(B,C));"), top_node)
def _read_tree_files(filenames):
trees = []
for filename in filenames:
with open(filename) as handle:
for line in handle:
trees.append(Newick.from_string(line))
return trees
def test_newick__wikipedia_example_8():
# a tree rooted on a leaf node (rare)
taxa_b = Newick(length = "0.2", name = "B")
taxa_c = Newick(length = "0.3", name = "C")
taxa_d = Newick(length = "0.4", name = "D")
node_e = Newick(length = "0.5", name = "E", children = [taxa_c, taxa_d])
node_f = Newick(length = "0.1", name = "F", children = [taxa_b, node_e])
node_a = Newick(name = "A", children = [node_f])
assert_equal(Newick.from_string("((B:0.2,(C:0.3,D:0.4)E:0.5)F:0.1)A;"), node_a)
def test_newick__wikipedia_example_3():
# all nodes are named
taxa_d = Newick(name = "D")
taxa_c = Newick(name = "C")
taxa_sub = Newick(children = [taxa_c, taxa_d], name = "E")
taxa_b = Newick(name = "B")
taxa_a = Newick(name = "A")
top_node = Newick(children = [taxa_a, taxa_b, taxa_sub], name = "F")
assert_equal(Newick.from_string("(A,B,(C,D)E)F;"), top_node)
def test_newick__wikipedia_example_6():
# distances and leaf names (popular)
taxa_d = Newick(length = "0.4", name = "D")
taxa_c = Newick(length = "0.3", name = "C")
taxa_sub = Newick(children = [taxa_c, taxa_d], length = "0.5")
taxa_b = Newick(length = "0.2", name = "B")
taxa_a = Newick(length = "0.1", name = "A")
top_node = Newick(children = [taxa_a, taxa_b, taxa_sub])
assert_equal(Newick.from_string("(A:0.1,B:0.2,(C:0.3,D:0.4):0.5);"), top_node)
def test_newick__wikipedia_example_5():
# all have a distance to parent
taxa_d = Newick(length = "0.4")
taxa_c = Newick(length = "0.3")
taxa_sub = Newick(children = [taxa_c, taxa_d], length = "0.5")
taxa_b = Newick(length = "0.2")
taxa_a = Newick(length = "0.1")
top_node = Newick(children = [taxa_a, taxa_b, taxa_sub], length = "0.0")
assert_equal(Newick.from_string("(:0.1,:0.2,(:0.3,:0.4):0.5):0.0;"), top_node)
def test_newick__wikipedia_example_7():
# distances and all names
taxa_d = Newick(length = "0.4", name = "D")
taxa_c = Newick(length = "0.3", name = "C")
taxa_sub = Newick(children = [taxa_c, taxa_d], length = "0.5", name = "E")
taxa_b = Newick(length = "0.2", name = "B")
taxa_a = Newick(length = "0.1", name = "A")
top_node = Newick(children = [taxa_a, taxa_b, taxa_sub], name = "F")
assert_equal(Newick.from_string("(A:0.1,B:0.2,(C:0.3,D:0.4)E:0.5)F;"), top_node)
def test_newick__wikipedia_example_3():
# all nodes are named
taxa_d = Newick(name="D")
taxa_c = Newick(name="C")
taxa_sub = Newick(children=[taxa_c, taxa_d], name="E")
taxa_b = Newick(name="B")
taxa_a = Newick(name="A")
top_node = Newick(children=[taxa_a, taxa_b, taxa_sub], name="F")
assert_equal(Newick.from_string("(A,B,(C,D)E)F;"), top_node)
def test_newick__wikipedia_example_2():
# leaf nodes are named
taxa_d = Newick(name="D")
taxa_c = Newick(name="C")
taxa_sub = Newick(children=[taxa_c, taxa_d])
taxa_b = Newick(name="B")
taxa_a = Newick(name="A")
top_node = Newick(children=[taxa_a, taxa_b, taxa_sub])
assert_equal(Newick.from_string("(A,B,(C,D));"), top_node)
def test_newick__wikipedia_example_4():
# all but root node have a distance to parent
taxa_d = Newick(length="0.4")
taxa_c = Newick(length="0.3")
taxa_sub = Newick(children=[taxa_c, taxa_d], length="0.5")
taxa_b = Newick(length="0.2")
taxa_a = Newick(length="0.1")
top_node = Newick(children=[taxa_a, taxa_b, taxa_sub])
assert_equal(Newick.from_string("(:0.1,:0.2,(:0.3,:0.4):0.5);"), top_node)
def test_newick__wikipedia_example_2():
# leaf nodes are named
taxa_d = Newick(name = "D")
taxa_c = Newick(name = "C")
taxa_sub = Newick(children = [taxa_c, taxa_d])
taxa_b = Newick(name = "B")
taxa_a = Newick(name = "A")
top_node = Newick(children = [taxa_a, taxa_b, taxa_sub])
assert_equal(Newick.from_string("(A,B,(C,D));"), top_node)
def test_newick__wikipedia_example_8():
# a tree rooted on a leaf node (rare)
taxa_b = Newick(length="0.2", name="B")
taxa_c = Newick(length="0.3", name="C")
taxa_d = Newick(length="0.4", name="D")
node_e = Newick(length="0.5", name="E", children=[taxa_c, taxa_d])
node_f = Newick(length="0.1", name="F", children=[taxa_b, node_e])
node_a = Newick(name="A", children=[node_f])
assert_equal(Newick.from_string("((B:0.2,(C:0.3,D:0.4)E:0.5)F:0.1)A;"),
node_a)
def test_newick__wikipedia_example_6():
# distances and leaf names (popular)
taxa_d = Newick(length="0.4", name="D")
taxa_c = Newick(length="0.3", name="C")
taxa_sub = Newick(children=[taxa_c, taxa_d], length="0.5")
taxa_b = Newick(length="0.2", name="B")
taxa_a = Newick(length="0.1", name="A")
top_node = Newick(children=[taxa_a, taxa_b, taxa_sub])
assert_equal(Newick.from_string("(A:0.1,B:0.2,(C:0.3,D:0.4):0.5);"),
top_node)
def test_newick__wikipedia_example_7():
# distances and all names
taxa_d = Newick(length="0.4", name="D")
taxa_c = Newick(length="0.3", name="C")
taxa_sub = Newick(children=[taxa_c, taxa_d], length="0.5", name="E")
taxa_b = Newick(length="0.2", name="B")
taxa_a = Newick(length="0.1", name="A")
top_node = Newick(children=[taxa_a, taxa_b, taxa_sub], name="F")
assert_equal(Newick.from_string("(A:0.1,B:0.2,(C:0.3,D:0.4)E:0.5)F;"),
top_node)
def test_newick__reroot_on_midpoint__nested_clades():
source = Newick.from_string("((A:2,(B:2,C:3):4):1,(D:1,E:0.5):2);")
rerooted = source.reroot_on_midpoint()
expected = Newick.from_string("(((D:1,E:0.5):3.0,A:2):1.5,(B:2,C:3):2.5);")
assert_equal(expected, rerooted)
def test_newick__parse__ignore_whitespace():
assert_equal(Newick.from_string("(A,B);"), Newick.from_string("(A, B);"))
def test_newick__parse__two_taxa():
child_node_1 = Newick(name = "A")
child_node_2 = Newick(name = "Bc")
top_node = Newick(children = [child_node_1, child_node_2])
assert_equal(Newick.from_string("(A,Bc);"), top_node)
def test_newick__parse__three_taxa():
child_node_1 = Newick(name="A")
child_node_2 = Newick(name="Bc")
child_node_3 = Newick(name="DeF")
top_node = Newick(children=[child_node_1, child_node_2, child_node_3])
assert_equal(Newick.from_string("(A,Bc,DeF);"), top_node)
def test_newick__add_support__single_identical_tree__different_rooting():
main_tree = Newick.from_string("(((A,B),C),D);")
bootstraps = [Newick.from_string("(((C,D),B),A);")]
expected = Newick.from_string("(((A,B)1,C)1,D);")
result = main_tree.add_support(bootstraps)
assert_equal(expected, result)
def _test_invalid_branch_lengths(newick):
source = Newick.from_string(newick)
assert_raises(GraphError, source.reroot_on_midpoint)
def test_newick__reroot_on_midpoint__nested_clades():
source = Newick.from_string("((A:2,(B:2,C:3):4):1,(D:1,E:0.5):2);")
rerooted = source.reroot_on_midpoint()
expected = Newick.from_string("(((D:1,E:0.5):3.0,A:2):1.5,(B:2,C:3):2.5);")
assert_equal(expected, rerooted)
def test_newick__add_support__unique_names_required():
main_tree = Newick.from_string("(((A,B),C),A);")
bootstraps = [Newick.from_string("(((A,B),C),A);")]
assert_raises(NewickError, main_tree.add_support, bootstraps)
def test_newick__parse__minimal_newick__name_only():
top_node = Newick(name="A")
assert_equal(Newick.from_string("A;"), top_node)
def test_newick__parse__single_taxa():
child_node = Newick(name="Ab")
top_node = Newick(children=[child_node])
assert_equal(Newick.from_string("(Ab);"), top_node)
def test_newick__reroot_on_midpoint__two_clades():
source = Newick.from_string("((A:7,B:2):1,(C:1,D:0.5):2);")
rerooted = source.reroot_on_midpoint()
expected = Newick.from_string("(((C:1,D:0.5):3.0,B:2):1.5,A:5.5);")
assert_equal(expected, rerooted)
def test_newick__parse__ignore_whitespace():
assert_equal(Newick.from_string("(A,B);"), Newick.from_string("(A, B);"))
def test_newick__add_support__single_identical_tree__different_rooting():
main_tree = Newick.from_string("(((A,B),C),D);")
bootstraps = [Newick.from_string("(((C,D),B),A);")]
expected = Newick.from_string("(((A,B)1,C)1,D);")
result = main_tree.add_support(bootstraps)
assert_equal(expected, result)
def test_newick__reroot_on_midpoint__two_clades():
source = Newick.from_string("((A:7,B:2):1,(C:1,D:0.5):2);")
rerooted = source.reroot_on_midpoint()
expected = Newick.from_string("(((C:1,D:0.5):3.0,B:2):1.5,A:5.5);")
assert_equal(expected, rerooted)
def test_newick__reroot_on_midpoint__single_node():
source = Newick.from_string("(A:3.0);")
expected = Newick.from_string("(A:3.0);")
assert_equal(expected, source.reroot_on_midpoint())
def test_newick__reroot_on_midpoint__reroot_on_internal_node():
source = Newick.from_string("((A:5.0,B:1.0)C:2.0,D:3.0);")
rerooted = source.reroot_on_midpoint()
expected = Newick.from_string("(A:5.0,B:1.0,D:5.0)C;")
assert_equal(expected, rerooted)
def test_newick__reroot_on_taxa__no_non_root_taxa():
source = Newick.from_string("((B,C),((D,E),A));")
assert_raises(ValueError, source.reroot_on_taxa, ("A", "B", "C", "D", "E"))
def test_newick__add_support__no_trees():
main_tree = Newick.from_string("(((A,B),C),D);")
expected = Newick.from_string("(((A,B)0,C)0,D);")
result = main_tree.add_support([])
assert_equal(expected, result)
def test_newick__parse__minimal_newick__name_only():
top_node = Newick(name = "A")
assert_equal(Newick.from_string("A;"), top_node)
def test_newick__reroot_on_midpoint__two_nodes():
source = Newick.from_string("(A:3.0,B:8.0);")
rerooted = source.reroot_on_midpoint()
expected = Newick.from_string("(A:5.5,B:5.5);")
assert_equal(expected, rerooted)
def test_newick__parse__two_taxa():
child_node_1 = Newick(name="A")
child_node_2 = Newick(name="Bc")
top_node = Newick(children=[child_node_1, child_node_2])
assert_equal(Newick.from_string("(A,Bc);"), top_node)
def test_newick__add_support__differing_leaf_names():
main_tree = Newick.from_string("(((A,B),C),D);")
bootstraps = [Newick.from_string("(((C,E),B),A);")]
assert_raises(NewickError, main_tree.add_support, bootstraps)
def _newick_str_input_equals_output(nwk_str):
nodes = Newick.from_string(nwk_str)
result = str(nodes)
assert_equal(result, nwk_str)
def test_newick__add_support__unique_names_required():
main_tree = Newick.from_string("(((A,B),C),A);")
bootstraps = [Newick.from_string("(((A,B),C),A);")]
assert_raises(NewickError, main_tree.add_support, bootstraps)
def test_newick__reroot_on_taxa__multiple_taxa__paraphylogeny():
source = Newick.from_string("((B,C),((D,E),A));")
expected = Newick.from_string("(((B,C),A),(D,E));")
assert_equal(expected, source.reroot_on_taxa(("A", "C")))
def test_newick__parse__single_taxa():
child_node = Newick(name = "Ab")
top_node = Newick(children = [child_node])
assert_equal(Newick.from_string("(Ab);"), top_node)
def test_newick__reroot_on_taxa__unknown_taxa():
source = Newick.from_string("((B,C),((D,E),A));")
assert_raises(ValueError, source.reroot_on_taxa, ("A", "Z"))
def test_newick__parse__three_taxa():
child_node_1 = Newick(name = "A")
child_node_2 = Newick(name = "Bc")
child_node_3 = Newick(name = "DeF")
top_node = Newick(children = [child_node_1, child_node_2, child_node_3])
assert_equal(Newick.from_string("(A,Bc,DeF);"), top_node)
def test_newick__reroot_on_midpoint__reroot_on_internal_node():
source = Newick.from_string("((A:5.0,B:1.0)C:2.0,D:3.0);")
rerooted = source.reroot_on_midpoint()
expected = Newick.from_string("(A:5.0,B:1.0,D:5.0)C;")
assert_equal(expected, rerooted)
def test_newick__reroot_on_taxa__unknown_taxa():
source = Newick.from_string("((B,C),((D,E),A));")
assert_raises(ValueError, source.reroot_on_taxa, ("A", "Z"))
def test_newick__add_support__differing_leaf_names():
main_tree = Newick.from_string("(((A,B),C),D);")
bootstraps = [Newick.from_string("(((C,E),B),A);")]
assert_raises(NewickError, main_tree.add_support, bootstraps)
def test_newick__reroot_on_taxa__no_non_root_taxa():
source = Newick.from_string("((B,C),((D,E),A));")
assert_raises(ValueError, source.reroot_on_taxa, ("A", "B", "C", "D", "E"))
def _test_invalid_branch_lengths(newick):
source = Newick.from_string(newick)
assert_raises(GraphError, source.reroot_on_midpoint)
def test_newick__reroot_on_midpoint__single_node():
source = Newick.from_string("(A:3.0);")
expected = Newick.from_string("(A:3.0);")
assert_equal(expected, source.reroot_on_midpoint())
def test_newick__reroot_on_midpoint__two_nodes():
source = Newick.from_string("(A:3.0,B:8.0);")
rerooted = source.reroot_on_midpoint()
expected = Newick.from_string("(A:5.5,B:5.5);")
assert_equal(expected, rerooted)
def _newick_str_input_equals_output(nwk_str):
nodes = Newick.from_string(nwk_str)
result = str(nodes)
assert_equal(result, nwk_str)
def test_newick__add_support__no_trees():
main_tree = Newick.from_string("(((A,B),C),D);")
expected = Newick.from_string("(((A,B)0,C)0,D);")
result = main_tree.add_support([])
assert_equal(expected, result)
def test_newick__reroot_on_taxa__multiple_taxa__paraphylogeny():
source = Newick.from_string("((B,C),((D,E),A));")
expected = Newick.from_string("(((B,C),A),(D,E));")
assert_equal(expected, source.reroot_on_taxa(("A", "C")))
def test_newick__reroot_on_taxa__multiple_taxa__clade():
source = Newick.from_string("((A,(B,C)),(D,E));")
expected = Newick.from_string("(((D,E),A),(B,C));")
assert_equal(expected, source.reroot_on_taxa(("B", "C")))
