def test_random_tree(self):
t5 = trees.random_tree(5)
t10 = trees.random_tree(10)
self.assertIsInstance(t10, trees.Tree)
self.assertIsInstance(t5, trees.Tree)
self.assertEqual(len(trees.get_list_of_tree_nodes(t5)), 9)
self.assertEqual(len(trees.get_list_of_tree_nodes(t10)), 19)
nodes = trees.get_list_of_tree_nodes(t5)
self.assertTrue(all(isinstance(node.length, float) for node in nodes))
def test_compile_histories(self):
t10 = evolve.evolve_tree(models.Sequence(self.old_sequence),
taxa=10,
t=0.1,
omega=1.1,
kappa=1.5)
histories = evolve.compile_histories(t10)
self.assertIsInstance(histories, dict)
for i in trees.get_list_of_tree_nodes(t10):
self.assertIn(i.id, histories)
def compile_histories(tree):
"""
Args:
tree: Tree instance with models.Sequence as value
"""
histories = {}
nodes = trees.get_list_of_tree_nodes(tree)
for t in nodes:
histories[t.id] = t.value.history
return histories
def compile_histories(tree):
"""
Args:
tree: Tree instance with models.Sequence as value
"""
histories = {}
nodes = trees.get_list_of_tree_nodes(tree)
for t in nodes:
histories[t.id] = t.value.history
return histories
def benchmark_evolve_tree():
with open('../../data/split/Seq2_Sus', 'r') as f:
old_sequence = f.read()[10:].replace('\n', '').lower()
old_sequence = models.Sequence(old_sequence)
for i in [3, 6, 9]:
start_time = time.time()
# new_sequences, mutations = evolve.evolve(old_sequence, taxa=10, log=True)
tree = evolve.evolve_tree(old_sequence, taxa=i)
nodes = len(trees.get_list_of_tree_nodes(tree))
print("taxa:{} (nodes={}), sec:{}".format(i, nodes, time.time() - start_time))
def benchmark_evolve_tree():
with open('../../data/split/Seq2_Sus', 'r') as f:
old_sequence = f.read()[10:].replace('\n', '').lower()
old_sequence = models.Sequence(old_sequence)
for i in [3, 6, 9]:
start_time = time.time()
# new_sequences, mutations = evolve.evolve(old_sequence, taxa=10, log=True)
tree = evolve.evolve_tree(old_sequence, taxa=i)
nodes = len(trees.get_list_of_tree_nodes(tree))
print("taxa:{} (nodes={}), sec:{}".format(i, nodes,
time.time() - start_time))
def evolve_tree(sequence,
taxa=10,
t=1e-2,
omega=1.0,
kappa=2.0,
lmbda=1e-5,
ti_td=0.1,
codon_freq='F1x4',
scale_q=True,
**kwargs):
"""
Evolve a parent DNA sequence into a set of daughter sequences (taxa) by:
1. generating a random phylogenetic tree
2. intantiating a mutational model (e.g. Goldman-Yang-like by default) represented by Q-matrix, with indels
3. mutate sequence according to tree shape using model
Args:
sequence: a model.Sequence instance
taxa: number of daughter sequences to evolve
t: evolution time or branch length
omega: dN/dS
kappa: ratio of transition to transversion rates
lmbda: probability of indel at codon
ti_td: ratio of insertions to deletions
codon_freq: codon frequency model, also know as equilibrium frequencies (default is F1x4)
scale_q: scales Q so that the average rate of substitution at
equilibrium equals 1. Branch lengths are thus expected number of nucleotide
substitutions per codon. See Goldman (1994).
Returns:
tree instance populated with new sequence strings
"""
codon_freq = getattr(codon_frequencies, codon_freq)(sequence)
q = models.goldman_Q(kappa=kappa,
omega=omega,
codon_freq=codon_freq,
scale_q=scale_q,
return_dict=False)
tree = trees.random_tree(taxa)
tree.value = sequence
for node in trees.get_list_of_tree_nodes(tree)[1:]:
node.value = evolve_sequence_with_q(node.parent.value,
q,
t=t,
lmbda=lmbda,
ti_td=ti_td)
return tree
def evolve_tree(sequence,
taxa=10,
t=1e-2,
omega=1.0,
kappa=2.0,
lmbda=1e-5,
ti_td=0.1,
codon_freq='F1x4',
scale_q=True,
**kwargs
):
"""
Evolve a parent DNA sequence into a set of daughter sequences (taxa) by:
1. generating a random phylogenetic tree
2. intantiating a mutational model (e.g. Goldman-Yang-like by default) represented by Q-matrix, with indels
3. mutate sequence according to tree shape using model
Args:
sequence: a model.Sequence instance
taxa: number of daughter sequences to evolve
t: evolution time or branch length
omega: dN/dS
kappa: ratio of transition to transversion rates
lmbda: probability of indel at codon
ti_td: ratio of insertions to deletions
codon_freq: codon frequency model, also know as equilibrium frequencies (default is F1x4)
scale_q: scales Q so that the average rate of substitution at
equilibrium equals 1. Branch lengths are thus expected number of nucleotide
substitutions per codon. See Goldman (1994).
Returns:
tree instance populated with new sequence strings
"""
codon_freq = getattr(codon_frequencies, codon_freq)(sequence)
q = models.goldman_Q(kappa=kappa, omega=omega, codon_freq=codon_freq, scale_q=scale_q, return_dict=False)
tree = trees.random_tree(taxa)
tree.value = sequence
for node in trees.get_list_of_tree_nodes(tree)[1:]:
node.value = evolve_sequence_with_q(node.parent.value, q, t=t, lmbda=lmbda, ti_td=ti_td)
return tree
def test_compile_histories(self):
t10 = evolve.evolve_tree(models.Sequence(self.old_sequence), taxa=10, t=0.1, omega=1.1, kappa=1.5)
histories = evolve.compile_histories(t10)
self.assertIsInstance(histories, dict)
for i in trees.get_list_of_tree_nodes(t10):
self.assertIn(i.id, histories)
def test_get_list_of_tree_nodes(self):
t = trees.random_tree(10)
tl = trees.get_list_of_tree_nodes(t)
self.assertEqual(len(tl), 19)
def test_preorder_exec(self):
t = trees.random_tree(10)
tlist = trees.get_list_of_tree_nodes(t)
self.assertTrue(all(i.get_value() is None for i in tlist))
trees.preorder_exec(t, function='set_value', arguments=['test'])
self.assertTrue(all(i.get_value() == 'test' for i in tlist))
def test_get_two_random_orphans_returns_empty_list_if_less_than_two_orphans(self):
t5 = trees.random_tree(5)
nodes = trees.get_list_of_tree_nodes(t5)
orphans = trees.get_two_random_orphans(nodes)
self.assertEqual(orphans, [])