def test_create_temporary_phylip(self, temp_mock):
temp_file = StringIO()
temp_mock.return_value = temp_file
builder = TreeBuilder()
fasta_file = StringIO("""\
>cluster_A
NNAACAAAANN
>cluster_B
CCAACAAAANN
""")
expected_output = """\
2 11
cluster_A NNAACAAAAN N
cluster_B CCAACAAAAN N
"""
builder.load_fasta_sequences(fasta_file)
output_file = builder._create_temporary_phylip(builder.sequences)
self.assertEqual(output_file, temp_file)
output_file.seek(0)
self.assertEqual(output_file.read(), expected_output)
def test_build_tree(self, temp_mock):
builder = TreeBuilder()
# I could mock _run_raxml but, because I'm using a regex to parse the
# results, I want to know straight away if the output of RAxML changes in a
# way that breaks this.
random_file = tempfile.NamedTemporaryFile('w', delete=False)
random_filename = random_file.name
random_folder = tempfile.mkdtemp()
temp_mock.NamedTemporaryFile.return_value = random_file
temp_mock.mkdtemp.return_value = random_folder
fasta_file = open(os.path.join(test_data(), 'animals.mfa'), 'r')
builder.load_fasta_sequences(fasta_file)
fasta_file.close()
tree = builder.build_tree()
tree_nodes = sorted([node.name for node in tree.get_terminals()])
expected_tree_nodes = [
"Carp", "Chicken", "Cow", "Frog", "Human", "Loach", "Mouse", "Rat",
"Seal", "Whale"
]
self.assertIsInstance(tree, Bio.Phylo.Newick.Tree)
self.assertEqual(tree_nodes, expected_tree_nodes)
self.assertFalse(os.path.isdir(random_folder))
self.assertFalse(os.path.isfile(random_filename))
def test_build_tree(self, temp_mock):
builder = TreeBuilder()
# I could mock _run_raxml but, because I'm using a regex to parse the
# results, I want to know straight away if the output of RAxML changes in a
# way that breaks this.
random_file = tempfile.NamedTemporaryFile('w', delete=False)
random_filename = random_file.name
random_folder = tempfile.mkdtemp()
temp_mock.NamedTemporaryFile.return_value = random_file
temp_mock.mkdtemp.return_value = random_folder
fasta_file = open(os.path.join(test_data(), 'animals.mfa'), 'r')
builder.load_fasta_sequences(fasta_file)
fasta_file.close()
tree = builder.build_tree()
tree_nodes = sorted([node.name for node in tree.get_terminals()])
expected_tree_nodes = ["Carp", "Chicken", "Cow", "Frog", "Human", "Loach",
"Mouse", "Rat", "Seal", "Whale"]
self.assertIsInstance(tree, Bio.Phylo.Newick.Tree)
self.assertEqual(tree_nodes, expected_tree_nodes)
self.assertFalse(os.path.isdir(random_folder))
self.assertFalse(os.path.isfile(random_filename))
def test_create_temporary_phylip(self, temp_mock):
temp_file = StringIO()
temp_mock.return_value = temp_file
builder = TreeBuilder()
fasta_file = StringIO("""\
>cluster_A
NNAACAAAANN
>cluster_B
CCAACAAAANN
""")
expected_output = """\
2 11
cluster_A NNAACAAAAN N
cluster_B CCAACAAAAN N
"""
builder.load_fasta_sequences(fasta_file)
output_file = builder._create_temporary_phylip(builder.sequences)
self.assertEqual(output_file, temp_file)
output_file.seek(0)
self.assertEqual(output_file.read(), expected_output)
def test_run_raxml(self):
builder = TreeBuilder()
fasta_file = open(os.path.join(test_data(), 'animals.mfa'), 'r')
builder.load_fasta_sequences(fasta_file)
fasta_file.close()
phylip_file = builder._create_temporary_phylip(builder.sequences)
phylip_file.close()
output_directory = tempfile.mkdtemp()
raxml_stdout, raxml_stderr = builder._run_raxml('raxmlHPC', {}, phylip_file.name, output_directory)
self.assertTrue('Best-scoring ML tree written to' in raxml_stdout)
os.remove(phylip_file.name)
shutil.rmtree(output_directory)
def test_run_raxml(self):
builder = TreeBuilder()
fasta_file = open(os.path.join(test_data(), 'animals.mfa'), 'r')
builder.load_fasta_sequences(fasta_file)
fasta_file.close()
phylip_file = builder._create_temporary_phylip(builder.sequences)
phylip_file.close()
output_directory = tempfile.mkdtemp()
raxml_stdout, raxml_stderr = builder._run_raxml(
'raxmlHPC', {}, phylip_file.name, output_directory)
self.assertTrue('Best-scoring ML tree written to' in raxml_stdout)
os.remove(phylip_file.name)
shutil.rmtree(output_directory)
def test_add_hereditary_nodes(self, temp_mock):
builder = TreeBuilder()
output_directory = tempfile.mkdtemp()
temp_mock.mkdtemp.return_value = output_directory
temp_mock.NamedTemporaryFile.side_effect = \
(tempfile.NamedTemporaryFile(dir=output_directory, delete=False) for i in xrange(10))
fasta_filename = os.path.join(test_data(), 'animals.mfa')
with open(fasta_filename) as fasta_file:
builder.load_fasta_sequences(fasta_file)
tree_filename = os.path.join(test_data(), 'animals.terminal_nodes.newick')
builder.tree = Bio.Phylo.read(tree_filename, 'newick')
builder.add_hereditary_nodes()
self.assertIsInstance(builder.tree, Bio.Phylo.Newick.Tree)
tree_nodes = sorted([node.name for node in builder.tree.find_clades()])
self.assertItemsEqual(tree_nodes, builder.sequences.keys())
self.assertEqual(len(tree_nodes), 19)
self.assertFalse(os.path.isdir(output_directory))
def test_add_hereditary_nodes(self, temp_mock):
builder = TreeBuilder()
output_directory = tempfile.mkdtemp()
temp_mock.mkdtemp.return_value = output_directory
temp_mock.NamedTemporaryFile.side_effect = \
(tempfile.NamedTemporaryFile(dir=output_directory, delete=False) for i in xrange(10))
fasta_filename = os.path.join(test_data(), 'animals.mfa')
with open(fasta_filename) as fasta_file:
builder.load_fasta_sequences(fasta_file)
tree_filename = os.path.join(test_data(),
'animals.terminal_nodes.newick')
builder.tree = Bio.Phylo.read(tree_filename, 'newick')
builder.add_hereditary_nodes()
self.assertIsInstance(builder.tree, Bio.Phylo.Newick.Tree)
tree_nodes = sorted([node.name for node in builder.tree.find_clades()])
self.assertItemsEqual(tree_nodes, builder.sequences.keys())
self.assertEqual(len(tree_nodes), 19)
self.assertFalse(os.path.isdir(output_directory))
