def test_emit_internal():
"""
Calculate emission probabilities for internal branches
"""
k = 10
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8 * 20
length = int(10e3) / 20
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
arg = argweaver.sample_arg_dsmc(k,
2 * n,
rho,
start=0,
end=length,
times=times)
muts = argweaver.sample_arg_mutations(arg, mu, times)
seqs = argweaver.make_alignment(arg, muts)
trees, names = argweaverc.arg2ctrees(arg, times)
seqs2, nseqs, seqlen = argweaverc.seqs2cseqs(seqs, names)
assert argweaverc.argweaver_assert_emit_internal(trees, len(times), times,
mu, seqs2, nseqs, seqlen)
def test_trans_switch():
"""
Calculate transition probabilities for switch matrix
Only calculate a single matrix
"""
k = 12
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
popsizes = [n] * len(times)
recombs = []
while len(recombs) == 0:
arg = argweaver.sample_arg_dsmc(k,
2 * n,
rho,
start=0,
end=length,
times=times)
recombs = [x.pos for x in arg if x.event == "recomb"]
pos = recombs[0]
tree = arg.get_marginal_tree(pos - .5)
rpos, r, c = arglib.iter_arg_sprs(arg, start=pos - .5).next()
spr = (r, c)
assert argweaverc.assert_transition_switch_probs(tree, spr, times,
popsizes, rho)
def test_emit():
"""
Calculate emission probabilities
"""
k = 10
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8 * 20
length = int(1e3) / 20
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
arg = argweaver.sample_arg_dsmc(k,
2 * n,
rho,
start=0,
end=length,
times=times)
muts = argweaver.sample_arg_mutations(arg, mu, times)
seqs = argweaver.make_alignment(arg, muts)
new_name = "n%d" % (k - 1)
arg = argweaver.remove_arg_thread(arg, new_name)
trees, names = argweaverc.arg2ctrees(arg, times)
seqs2, nseqs, seqlen = argweaverc.seqs2cseqs(seqs, names + [new_name])
assert argweaverc.argweaver_assert_emit(trees, len(times), times, mu,
seqs2, nseqs, seqlen)
def test_node_numbering():
"""
Test node numbering across ARG.
A node should keep the same numbering until it is broken by
recombination. The new recoal node should take the index of the broken
node.
"""
k = 10
n = 1e4
rho = 1.5e-8 * 20
length = 10000
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
arg = argweaver.sample_arg_dsmc(k, 2*n, rho, start=0, end=length,
times=times)
(ptrees, ages, sprs, blocks), all_nodes = (
argweaverc.get_treeset(arg, times))
# check nodes list
nnodes = len(all_nodes[0])
last_nodes = None
for i, nodes in enumerate(all_nodes):
if last_nodes:
recombj = sprs[i][0]
brokenj = ptrees[i][recombj]
for j in range(nnodes):
if j != brokenj:
nose.tools.assert_equal(last_nodes[j], nodes[j])
last_nodes = nodes
def test_emit():
"""
Calculate emission probabilities
"""
k = 10
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8 * 20
length = int(1e3) / 20
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
arg = argweaver.sample_arg_dsmc(k, 2*n, rho, start=0, end=length,
times=times)
muts = argweaver.sample_arg_mutations(arg, mu, times)
seqs = argweaver.make_alignment(arg, muts)
new_name = "n%d" % (k-1)
arg = argweaver.remove_arg_thread(arg, new_name)
trees, names = argweaverc.arg2ctrees(arg, times)
seqs2, nseqs, seqlen = argweaverc.seqs2cseqs(seqs, names + [new_name])
assert argweaverc.argweaver_assert_emit(trees, len(times), times, mu,
seqs2, nseqs, seqlen)
def test_node_numbering():
"""
Test node numbering across ARG.
A node should keep the same numbering until it is broken by
recombination. The new recoal node should take the index of the broken
node.
"""
k = 10
n = 1e4
rho = 1.5e-8 * 20
length = 10000
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
arg = argweaver.sample_arg_dsmc(k, 2*n, rho, start=0, end=length,
times=times)
(ptrees, ages, sprs, blocks), all_nodes = (
argweaverc.get_treeset(arg, times))
# check nodes list
nnodes = len(all_nodes[0])
last_nodes = None
for i, nodes in enumerate(all_nodes):
if last_nodes:
recombj = sprs[i][0]
brokenj = ptrees[i][recombj]
for j in range(nnodes):
if j != brokenj:
nose.tools.assert_equal(last_nodes[j], nodes[j])
last_nodes = nodes
def test_trans_switch():
"""
Calculate transition probabilities for switch matrix
Only calculate a single matrix
"""
k = 12
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
popsizes = [n] * len(times)
recombs = []
while len(recombs) == 0:
arg = argweaver.sample_arg_dsmc(k, 2*n, rho, start=0, end=length,
times=times)
recombs = [x.pos for x in arg if x.event == "recomb"]
pos = recombs[0]
tree = arg.get_marginal_tree(pos-.5)
rpos, r, c = arglib.iter_arg_sprs(arg, start=pos-.5).next()
spr = (r, c)
assert argweaverc.assert_transition_switch_probs(
tree, spr, times, popsizes, rho)
def test_trans_switch():
"""
Calculate transition probabilities for switch matrix
Only calculate a single matrix
"""
create_data = False
if create_data:
make_clean_dir('test/data/test_trans_switch')
# model parameters
k = 12
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
popsizes = [n] * len(times)
ntests = 100
# generate test data
if create_data:
for i in range(ntests):
# Sample ARG with at least one recombination.
while True:
arg = argweaver.sample_arg_dsmc(k,
2 * n,
rho,
start=0,
end=length,
times=times)
if any(x.event == "recomb" for x in arg):
break
arg.write('test/data/test_trans_switch/%d.arg' % i)
for i in range(ntests):
print('arg', i)
arg = arglib.read_arg('test/data/test_trans_switch/%d.arg' % i)
argweaver.discretize_arg(arg, times)
recombs = [x.pos for x in arg if x.event == "recomb"]
pos = recombs[0]
tree = arg.get_marginal_tree(pos - .5)
rpos, r, c = next(arglib.iter_arg_sprs(arg, start=pos - .5))
spr = (r, c)
if not argweaverc.assert_transition_switch_probs(
tree, spr, times, popsizes, rho):
tree2 = tree.get_tree()
treelib.remove_single_children(tree2)
treelib.draw_tree_names(tree2, maxlen=5, minlen=5)
assert False
def test_trans_switch():
"""
Calculate transition probabilities for switch matrix
Only calculate a single matrix
"""
create_data = False
if create_data:
make_clean_dir('test/data/test_trans_switch')
# model parameters
k = 12
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
popsizes = [n] * len(times)
ntests = 100
# generate test data
if create_data:
for i in range(ntests):
# Sample ARG with at least one recombination.
while True:
arg = argweaver.sample_arg_dsmc(
k, 2*n, rho, start=0, end=length, times=times)
if any(x.event == "recomb" for x in arg):
break
arg.write('test/data/test_trans_switch/%d.arg' % i)
for i in range(ntests):
print 'arg', i
arg = arglib.read_arg('test/data/test_trans_switch/%d.arg' % i)
argweaver.discretize_arg(arg, times)
recombs = [x.pos for x in arg if x.event == "recomb"]
pos = recombs[0]
tree = arg.get_marginal_tree(pos-.5)
rpos, r, c = arglib.iter_arg_sprs(arg, start=pos-.5).next()
spr = (r, c)
if not argweaverc.assert_transition_switch_probs(
tree, spr, times, popsizes, rho):
tree2 = tree.get_tree()
treelib.remove_single_children(tree2)
treelib.draw_tree_names(tree2, maxlen=5, minlen=5)
assert False
def test_arg_convert():
"""
Test conversion for python to C args
"""
k = 10
n = 1e4
rho = 1.5e-8 * 20
length = 10000
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
arg = argweaver.sample_arg_dsmc(k, 2 * n, rho, start=0, end=length, times=times)
# convert to C++ and back
trees, names = argweaverc.arg2ctrees(arg, times)
arg2 = argweaverc.ctrees2arg(trees, names, times)
arg_equal(arg, arg2)
def test_arg_joint():
"""
Compute joint probability of an ARG
"""
k = 2
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8 * 20
length = 10000
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
arg = argweaver.sample_arg_dsmc(k, 2*n, rho, start=0, end=length,
times=times)
muts = argweaver.sample_arg_mutations(arg, mu, times=times)
seqs = arglib.make_alignment(arg, muts)
lk = argweaver.calc_joint_prob(arg, seqs, mu=mu, rho=rho, times=times)
print lk
def test_arg_convert():
"""
Test conversion for python to C args
"""
k = 10
n = 1e4
rho = 1.5e-8 * 20
length = 10000
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
arg = argweaver.sample_arg_dsmc(k, 2*n, rho, start=0, end=length,
times=times)
# convert to C++ and back
trees, names = argweaverc.arg2ctrees(arg, times)
arg2 = argweaverc.ctrees2arg(trees, names, times)
arg_equal(arg, arg2)
def test_trans_switch_internal():
"""
Calculate transition probabilities for switch matrix and internal branches
Only calculate a single matrix
"""
k = 10
n = 1e4
rho = 1.5e-8 * 20
length = int(100e3) / 20
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
popsizes = [n] * len(times)
arg = argweaver.sample_arg_dsmc(k, 2*n, rho, start=0, end=length,
times=times)
trees, names = argweaverc.arg2ctrees(arg, times)
assert argweaverc.assert_transition_probs_switch_internal(
trees, times, popsizes, rho)
def test_emit_internal():
"""
Calculate emission probabilities for internal branches
"""
k = 10
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8 * 20
length = int(10e3) / 20
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
arg = argweaver.sample_arg_dsmc(k, 2*n, rho, start=0, end=length,
times=times)
muts = argweaver.sample_arg_mutations(arg, mu, times)
seqs = argweaver.make_alignment(arg, muts)
trees, names = argweaverc.arg2ctrees(arg, times)
seqs2, nseqs, seqlen = argweaverc.seqs2cseqs(seqs, names)
assert argweaverc.argweaver_assert_emit_internal(
trees, len(times), times, mu, seqs2, nseqs, seqlen)