def run_snip_centromere(args):
with open(args.centromeres) as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
if row["chrom"] == args.chrom:
start = int(row["start"])
end = int(row["end"])
break
else:
raise ValueError("Did not find row")
ts = tskit.load(args.input)
position = ts.tables.sites.position
s_index = np.searchsorted(position, start)
e_index = np.searchsorted(position, end)
# We have a bunch of sites within the centromere. Get the largest
# distance between these and call these the start and end. Probably
# pointless having the centromere coordinates as input in the first place,
# since we're just searching for the largest gap anyway. However, it can
# be useful in UKBB, since it's perfectly possible that the largest
# gap between sites isn't in the centromere.
X = position[s_index:e_index + 1]
j = np.argmax(X[1:] - X[:-1])
real_start = X[j] + 1
real_end = X[j + 1]
print("Centromere at", start, end, "Snipping topology from ", real_start,
real_end)
snipped_ts = tsinfer.snip_centromere(ts, real_start, real_end)
snipped_ts.dump(args.output)
def test_two_populations_high_migration_no_centromere(self):
ts = self.two_populations_high_migration_example(mutation_rate=0)
ts = tsinfer.snip_centromere(ts, 0.4, 0.6)
# simplify the output to get rid of unreferenced nodes.
ts = ts.simplify()
A = self.verify(ts, [ts.samples(0), ts.samples(1)])
total = np.sum(A, axis=0)
self.assertTrue(np.allclose(total[total != 0], 1))
def verify(self, ts, left, right):
ts1 = self.snip_centromere(ts, left, right)
ts2 = tsinfer.snip_centromere(ts, left, right)
assert ts1.equals(ts2, ignore_provenance=True)
tree_found = False
for tree in ts1.trees():
if tree.interval == (left, right):
tree_found = True
for node in ts1.nodes():
assert tree.parent(node.id) == tskit.NULL
break
assert tree_found
return ts1
def verify(self, ts, left, right):
ts1 = self.snip_centromere(ts, left, right)
ts2 = tsinfer.snip_centromere(ts, left, right)
t1 = ts1.dump_tables()
t2 = ts2.dump_tables()
t1.provenances.clear()
t2.provenances.clear()
self.assertEqual(t1, t2)
tree_found = False
for tree in ts1.trees():
if tree.interval == (left, right):
tree_found = True
for node in ts1.nodes():
self.assertEqual(tree.parent(node.id), tskit.NULL)
break
self.assertTrue(tree_found)
return ts1
def verify(self, ts, left, right):
ts1 = self.snip_centromere(ts, left, right)
ts2 = tsinfer.snip_centromere(ts, left, right)
t1 = ts1.dump_tables()
t2 = ts2.dump_tables()
t1.provenances.clear()
t2.provenances.clear()
assert t1 == t2
tree_found = False
for tree in ts1.trees():
if tree.interval == (left, right):
tree_found = True
for node in ts1.nodes():
assert tree.parent(node.id) == tskit.NULL
break
assert tree_found
return ts1
def test_position_errors(self):
ts = msprime.simulate(2,
length=10,
recombination_rate=1,
random_seed=1,
mutation_rate=2)
X = ts.tables.sites.position
assert X.shape[0] > 3
# Left cannot be on a site position.
with pytest.raises(ValueError):
tsinfer.snip_centromere(ts, X[0], X[0] + 0.001)
# Cannot go either side of a position
with pytest.raises(ValueError):
tsinfer.snip_centromere(ts, X[0] - 0.001, X[0] + 0.001)
# Cannot cover multiple positions
with pytest.raises(ValueError):
tsinfer.snip_centromere(ts, X[0] - 0.001, X[2] + 0.001)
def test_coordinate_errors(self):
ts = msprime.simulate(2,
length=10,
recombination_rate=1,
random_seed=1)
with pytest.raises(ValueError):
tsinfer.snip_centromere(ts, -1, 5)
with pytest.raises(ValueError):
tsinfer.snip_centromere(ts, 0, 5)
with pytest.raises(ValueError):
tsinfer.snip_centromere(ts, 1, 10)
with pytest.raises(ValueError):
tsinfer.snip_centromere(ts, 1, 11)
with pytest.raises(ValueError):
tsinfer.snip_centromere(ts, 6, 5)
with pytest.raises(ValueError):
tsinfer.snip_centromere(ts, 5, 5)