def test_with_recurrent_mutations(self):
# actually with only ONE site, at 0.0
N = 10
ngens = 100
tables = wf_sim(N=N,
ngens=ngens,
deep_history=False,
seed=self.random_seed)
tables.sort()
ts = tables.tree_sequence()
ts = tsutil.jukes_cantor(ts, 1, 10, seed=self.random_seed)
tables = ts.tables
self.assertEqual(tables.sites.num_rows, 1)
self.assertGreater(tables.mutations.num_rows, 0)
# before simplify
for h in ts.haplotypes():
self.assertEqual(len(h), 1)
# after simplify
tables.sort()
tables.simplify()
self.assertGreater(tables.nodes.num_rows, 0)
self.assertGreater(tables.edges.num_rows, 0)
self.assertEqual(tables.sites.num_rows, 1)
self.assertGreater(tables.mutations.num_rows, 0)
ts = tables.tree_sequence()
self.assertEqual(ts.sample_size, N)
for hap in ts.haplotypes():
self.assertEqual(len(hap), ts.num_sites)
def test_jukes_cantor_balanced_ternary_multiroot(self):
ts = tskit.Tree.generate_balanced(50, arity=3).tree_sequence
ts = tsutil.decapitate(ts, ts.num_edges // 3)
ts = tsutil.jukes_cantor(ts, 15, 2, seed=3)
self.verify(ts)
assert ts.num_sites > 1
self.verify(tsutil.jiggle_samples(ts))
def test_jukes_cantor_n20_felsenstein_matrix(self):
cost_matrix = np.array(
[[0, 2.5, 1, 2.5], [2.5, 0, 2.5, 1], [1, 2.5, 0, 2.5], [2.5, 1, 2.5, 0]]
)
ts = msprime.simulate(20, random_seed=1)
ts = tsutil.jukes_cantor(ts, 5, 2, seed=1)
self.verify_jukes_cantor(ts, cost_matrix)
def test_with_recurrent_mutations(self):
# actually with only ONE site, at 0.0
N = 10
ngens = 100
tables = wf_sim(N=N,
ngens=ngens,
deep_history=False,
seed=self.random_seed)
msprime.sort_tables(**tables.asdict())
ts = msprime.load_tables(**tables.asdict())
ts = tsutil.jukes_cantor(ts, 1, 10, seed=self.random_seed)
tables = ts.tables
self.assertEqual(tables.sites.num_rows, 1)
self.assertGreater(tables.mutations.num_rows, 0)
nodes = tables.nodes
samples = np.where(nodes.flags == msprime.NODE_IS_SAMPLE)[0].astype(
np.int32)
# before simplify
for h in ts.haplotypes():
self.assertEqual(len(h), 1)
# after simplify
msprime.simplify_tables(samples=samples,
nodes=tables.nodes,
edges=tables.edges,
sites=tables.sites,
mutations=tables.mutations)
self.assertGreater(tables.nodes.num_rows, 0)
self.assertGreater(tables.edges.num_rows, 0)
self.assertEqual(tables.sites.num_rows, 1)
self.assertGreater(tables.mutations.num_rows, 0)
ts = msprime.load_tables(**tables.asdict())
self.assertEqual(ts.sample_size, N)
for hap in ts.haplotypes():
self.assertEqual(len(hap), ts.num_sites)
def test_with_mutations(self):
N = 10
ngens = 100
tables = wf_sim(N=N,
ngens=ngens,
deep_history=False,
seed=self.random_seed)
tables.sort()
ts = tables.tree_sequence()
ts = tsutil.jukes_cantor(ts, 10, 0.1, seed=self.random_seed)
tables = ts.tables
assert tables.sites.num_rows > 0
assert tables.mutations.num_rows > 0
samples = np.where(
tables.nodes.flags == tskit.NODE_IS_SAMPLE)[0].astype(np.int32)
tables.sort()
tables.simplify(samples)
assert tables.nodes.num_rows > 0
assert tables.edges.num_rows > 0
assert tables.nodes.num_rows > 0
assert tables.edges.num_rows > 0
assert tables.sites.num_rows > 0
assert tables.mutations.num_rows > 0
ts = tables.tree_sequence()
assert ts.sample_size == N
for hap in ts.haplotypes():
assert len(hap) == ts.num_sites
def test_with_recurrent_mutations(self):
# actually with only ONE site, at 0.0
N = 10
ngens = 100
tables = wf_sim(N=N,
ngens=ngens,
deep_history=False,
seed=self.random_seed)
tables.sort()
ts = tables.tree_sequence()
ts = tsutil.jukes_cantor(ts, 1, 10, seed=self.random_seed)
tables = ts.tables
assert tables.sites.num_rows == 1
assert tables.mutations.num_rows > 0
# before simplify
for h in ts.haplotypes():
assert len(h) == 1
# after simplify
tables.sort()
tables.simplify()
assert tables.nodes.num_rows > 0
assert tables.edges.num_rows > 0
assert tables.sites.num_rows == 1
assert tables.mutations.num_rows > 0
ts = tables.tree_sequence()
assert ts.sample_size == N
for hap in ts.haplotypes():
assert len(hap) == ts.num_sites
def test_with_mutations(self):
N = 10
ngens = 100
tables = wf_sim(N=N,
ngens=ngens,
deep_history=False,
seed=self.random_seed)
tables.sort()
ts = msprime.load_tables(**tables.asdict())
ts = tsutil.jukes_cantor(ts, 10, 0.1, seed=self.random_seed)
tables = ts.tables
self.assertGreater(tables.sites.num_rows, 0)
self.assertGreater(tables.mutations.num_rows, 0)
samples = np.where(
tables.nodes.flags == msprime.NODE_IS_SAMPLE)[0].astype(np.int32)
tables.sort()
tables.simplify(samples)
self.assertGreater(tables.nodes.num_rows, 0)
self.assertGreater(tables.edges.num_rows, 0)
self.assertGreater(tables.nodes.num_rows, 0)
self.assertGreater(tables.edges.num_rows, 0)
self.assertGreater(tables.sites.num_rows, 0)
self.assertGreater(tables.mutations.num_rows, 0)
ts = msprime.load_tables(**tables.asdict())
self.assertEqual(ts.sample_size, N)
for hap in ts.haplotypes():
self.assertEqual(len(hap), ts.num_sites)
def create_data(length):
ts = msprime.simulate(sample_size=10,
length=length,
mutation_rate=1e-2,
random_seed=123)
ts = tsutil.jukes_cantor(ts, length, 1.0, seed=123)
assert ts.num_sites == length
return ts
def test_silent_mutations(self):
ts = msprime.simulate(50, random_seed=1)
ts = tsutil.jukes_cantor(ts, 5, 2, seed=2)
num_silent = 0
for m in ts.mutations():
if (m.parent != -1 and ts.mutation(m.parent).derived_state
== m.derived_state):
num_silent += 1
assert num_silent > 20
def get_wf_sims(seed):
wf_sims = []
for N in [5, 10, 20]:
for surv in [0.0, 0.5, 0.9]:
for mut in [0.01, 1.0]:
for nloci in [1, 2, 3]:
tables = wf_sim(N=N, ngens=N, survival=surv, seed=seed)
tables.sort()
ts = tables.tree_sequence()
ts = tsutil.jukes_cantor(ts, num_sites=nloci, mu=mut, seed=seed)
wf_sims.append(ts)
return wf_sims
def get_wf_sims(self, seed):
"""
Returns an iterator of example tree sequences produced by the WF simulator.
"""
for N in [5, 10, 20]:
for surv in [0.0, 0.5, 0.9]:
for mut in [0.01, 1.0]:
for nloci in [1, 2, 3]:
tables = wf_sim(N=N, ngens=N, survival=surv, seed=seed)
msprime.sort_tables(**tables.asdict())
ts = msprime.load_tables(**tables.asdict())
ts = tsutil.jukes_cantor(ts,
num_sites=nloci,
mu=mut,
seed=seed)
self.verify_simulation(ts, ngens=N)
yield ts
def test_jukes_cantor_n50_internal_samples(self):
ts = msprime.simulate(50, random_seed=1)
ts = tsutil.jukes_cantor(ts, 5, 2, seed=2)
self.verify(tsutil.jiggle_samples(ts))
def test_jukes_cantor_n50(self):
ts = msprime.simulate(50, random_seed=1)
ts = tsutil.jukes_cantor(ts, 5, 2, seed=2)
self.verify(ts)
def test_jukes_cantor_n20_simple_matrix(self):
cost_matrix = np.ones((4, 4))
np.fill_diagonal(cost_matrix, 0)
ts = msprime.simulate(20, random_seed=1)
ts = tsutil.jukes_cantor(ts, 5, 2, seed=1)
self.verify_jukes_cantor(ts, cost_matrix)
def test_jukes_cantor_n15_multiroot(self):
ts = msprime.simulate(15, random_seed=1)
ts = tsutil.decapitate(ts, ts.num_edges // 3)
ts = tsutil.jukes_cantor(ts, 15, 2, seed=3)
self.verify(ts)
def test_jukes_cantor_balanced_ternary_internal_samples(self):
tree = tskit.Tree.generate_balanced(27, arity=3)
ts = tsutil.jukes_cantor(tree.tree_sequence, 5, 2, seed=1)
assert ts.num_sites > 1
self.verify(tsutil.jiggle_samples(ts))
def test_jukes_cantor_n_15(self):
ts = msprime.simulate(15, mutation_rate=2, random_seed=2)
ts = tsutil.jukes_cantor(ts, num_sites=10, mu=0.1, seed=10)
self.verify(ts, tskit.ALLELES_ACGT)
def test_jukes_cantor_n_8_high_recombination(self):
ts = msprime.simulate(8, recombination_rate=20, random_seed=2)
ts = tsutil.jukes_cantor(ts, num_sites=20, mu=5, seed=4)
self.verify(ts, tskit.ALLELES_ACGT)
def test_jukes_cantor_balanced_ternary(self):
ts = tskit.Tree.generate_balanced(27, arity=3).tree_sequence
ts = tsutil.jukes_cantor(ts, num_sites=10, mu=0.1, seed=10)
self.verify(ts, tskit.ALLELES_ACGT)
def test_jukes_cantor_n50_multiroot(self):
ts = msprime.simulate(50, random_seed=1)
ts = tsutil.decapitate(ts, ts.num_edges // 2)
ts = tsutil.jukes_cantor(ts, 5, 2, seed=2)
self.verify(ts)
def test_jukes_cantor_leaf_polytomy_n5(self):
tree = tskit.Tree.unrank(5, (7, 0))
ts = tsutil.jukes_cantor(tree.tree_sequence, 5, 2, seed=1)
assert ts.num_sites > 2
self.verify(ts)