def test_generate_nucleotides_keep(self):
ts = msprime.sim_ancestry(4, sequence_length=10, population_size=10)
ts = pyslim.annotate_defaults(ts, model_type='nonWF', slim_generation=1)
mts1 = msprime.sim_mutations(ts,
model=msprime.SLiMMutationModel(type=1),
rate=0.1,
random_seed=23)
mts1.dump("out.trees")
nts1 = pyslim.generate_nucleotides(mts1, seed=10, keep=False)
assert nts1.num_mutations > 0
self.verify_generate_nucleotides(nts1, check_transitions=False)
mts2 = msprime.sim_mutations(nts1,
model=msprime.SLiMMutationModel(
type=2,
next_id=nts1.num_mutations,
),
rate=0.1,
random_seed=24,
)
# keep defaults to True
nts2 = pyslim.generate_nucleotides(mts2, seed=12)
assert nts2.num_mutations > nts1.num_mutations
muts1 = {}
for mut in nts1.mutations():
for i, md in zip(mut.derived_state.split(","), mut.metadata['mutation_list']):
muts1[i] = md['nucleotide']
for mut in nts2.mutations():
for i, md in zip(mut.derived_state.split(","), mut.metadata['mutation_list']):
if md['mutation_type'] == 1:
assert i in muts1
assert muts1[i] == md['nucleotide']
else:
assert md['nucleotide'] in [0, 1, 2, 3]
nts3 = pyslim.generate_nucleotides(mts2, keep=False, seed=15)
self.verify_generate_nucleotides(nts3, check_transitions=False)
def test_generate_nucleotides(self, recipe):
ts = recipe["ts"]
nts = pyslim.generate_nucleotides(ts, keep=False, seed=5)
self.verify_generate_nucleotides(
nts,
check_transitions=("adds_mutations" not in recipe),
)
def test_generate_nucleotides_errors(self):
ts = msprime.sim_ancestry(4, sequence_length=10, population_size=10)
with pytest.raises(ValueError, match="must have length equal"):
_ = pyslim.generate_nucleotides(ts, reference_sequence="AAA")
with pytest.raises(ValueError, match="must have length equal"):
_ = pyslim.generate_nucleotides(ts, reference_sequence=[1, 2, 3])
with pytest.raises(ValueError, match="must be a string of"):
_ = pyslim.generate_nucleotides(
ts,
reference_sequence="X" * int(ts.sequence_length)
)
with pytest.raises(ValueError, match="must be a string of"):
_ = pyslim.generate_nucleotides(
ts,
reference_sequence=np.arange(int(ts.sequence_length)),
)
def test_generate_and_convert(self, recipe, helper_functions, tmp_path):
ts = recipe["ts"]
nts = pyslim.generate_nucleotides(ts, seed=123)
cts = pyslim.convert_alleles(nts)
self.verify_converted_nucleotides(nts, cts)
helper_functions.run_slim_restart(
nts,
"restart_nucleotides_nonWF.slim",
tmp_path,
WF=False,
)
def test_generate_nucleotides_refseq(self):
ts = msprime.sim_ancestry(
4,
sequence_length=10,
population_size=10,
random_seed=10,
)
ts = pyslim.annotate_defaults(ts, model_type='nonWF', slim_generation=1)
mts = msprime.sim_mutations(ts,
model=msprime.SLiMMutationModel(type=1),
rate=0.5,
random_seed=23)
refseq = "A" * int(mts.sequence_length)
nts = pyslim.generate_nucleotides(mts, reference_sequence=refseq, seed=6)
self.verify_generate_nucleotides(nts, check_transitions=True)
assert nts.reference_sequence.data == refseq