def test_nlineages(self):
"""
Test lineage counting
"""
k = 4
n = 1e4
rho = 1.5e-8 * 1
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
times = arghmm.get_time_points(ntimes=6)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
nlineages, nrecombs, ncoals = arghmm.get_nlineages_recomb_coal(
tree, times)
treelib.draw_tree_names(tree.get_tree(), scale=4e-3)
print list(arghmm.iter_coal_states(tree, times))
print nlineages
self.assert_(nlineages == sorted(nlineages, reverse=True))
print nlineages
print nrecombs
print ncoals
def test_prior(self):
"""
Calculate state priors
"""
k = 10
n = 1e4
rho = 1.5e-8
mu = 2.5e-8
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points()
arghmm.discretize_arg(arg, times)
new_name = "n%d" % (k-1)
arg = arghmm.remove_arg_thread(arg, new_name)
model = arghmm.ArgHmm(arg, seqs, new_name=new_name, times=times)
prior = [model.prob_prior(0, j)
for j in xrange(model.get_num_states(0))]
print prior
print sum(map(exp, prior))
fequal(sum(map(exp, prior)), 1.0, rel=.01)
def test_trans():
"""
Calculate transition probabilities
"""
create_data = False
if create_data:
make_clean_dir('test/data/test_trans')
k = 8
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=10, maxtime=200000)
popsizes = [n] * len(times)
ntests = 40
# generate test data
if create_data:
for i in range(ntests):
arg = arglib.sample_arg(k, 2*n, rho, start=0, end=length)
argweaver.discretize_arg(arg, times)
arg.write('test/data/test_trans/%d.arg' % i)
for i in range(ntests):
print 'arg', i
arg = arglib.read_arg('test/data/test_trans/%d.arg' % i)
argweaver.discretize_arg(arg, times)
pos = 10
tree = arg.get_marginal_tree(pos)
assert argweaverc.assert_transition_probs(tree, times, popsizes, rho)
def test_post(self):
k = 6
n = 1e4
rho = 1.5e-8 * 10
mu = 2.5e-8 * 10
length = 10000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
print "muts", len(muts)
print "recombs", len(arglib.get_recomb_pos(arg))
times = arghmm.get_time_points(ntimes=10)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
# remove chrom
new_name = "n%d" % (k - 1)
keep = set(arg.leaf_names()) - set([new_name])
arglib.subarg_by_leaf_names(arg, keep)
arg = arglib.smcify_arg(arg)
model = arghmm.ArgHmm(arg, seqs, new_name=new_name,
times=times, rho=rho, mu=mu)
print "states", len(model.states[0])
probs = arghmm.get_posterior_probs(model, length, verbose=True)
for pcol in probs:
p = sum(map(exp, pcol))
print p, " ".join("%.3f" % f for f in map(exp, pcol))
fequal(p, 1.0, rel=1e-2)
def test_trans_single(self):
"""
Calculate transition probabilities
Only calculate a single matrix
"""
k = 4
n = 1e4
rho = 1.5e-8
mu = 2.5e-8
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(10)
arghmm.discretize_arg(arg, times)
print "recomb", arglib.get_recomb_pos(arg)
new_name = "n%d" % (k - 1)
arg = arghmm.remove_arg_thread(arg, new_name)
model = arghmm.ArgHmm(arg, seqs, new_name=new_name, times=times)
pos = 10
tree = arg.get_marginal_tree(pos)
mat = arghmm.calc_transition_probs(tree, model.states[pos],
model.nlineages, model.times,
model.time_steps, model.popsizes,
rho)
print model.states[pos]
pc(mat)
for row in mat:
print sum(map(exp, row))
def test_trans_single(self):
"""
Calculate transition probabilities
Only calculate a single matrix
"""
k = 4
n = 1e4
rho = 1.5e-8
mu = 2.5e-8
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(10)
arghmm.discretize_arg(arg, times)
print "recomb", arglib.get_recomb_pos(arg)
new_name = "n%d" % (k-1)
arg = arghmm.remove_arg_thread(arg, new_name)
model = arghmm.ArgHmm(arg, seqs, new_name=new_name, times=times)
pos = 10
tree = arg.get_marginal_tree(pos)
mat = arghmm.calc_transition_probs(
tree, model.states[pos], model.nlineages,
model.times, model.time_steps, model.popsizes, rho)
print model.states[pos]
pc(mat)
for row in mat:
print sum(map(exp, row))
def test_prior(self):
"""
Calculate state priors
"""
k = 10
n = 1e4
rho = 1.5e-8
mu = 2.5e-8
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points()
arghmm.discretize_arg(arg, times)
new_name = "n%d" % (k - 1)
arg = arghmm.remove_arg_thread(arg, new_name)
model = arghmm.ArgHmm(arg, seqs, new_name=new_name, times=times)
prior = [
model.prob_prior(0, j) for j in xrange(model.get_num_states(0))
]
print prior
print sum(map(exp, prior))
fequal(sum(map(exp, prior)), 1.0, rel=.01)
def test_nlineages(self):
"""
Test lineage counting
"""
k = 4
n = 1e4
rho = 1.5e-8 * 1
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
times = arghmm.get_time_points(ntimes=6)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
nlineages, nrecombs, ncoals = arghmm.get_nlineages_recomb_coal(
tree, times)
treelib.draw_tree_names(tree.get_tree(), scale=4e-3)
print list(arghmm.iter_coal_states(tree, times))
print nlineages
self.assert_(nlineages == sorted(nlineages, reverse=True))
print nlineages
print nrecombs
print ncoals
def test_post_plot(self):
k = 6
n = 1e4
rho = 1.5e-8 * 50
mu = 2.5e-8 * 50
length = 10000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(ntimes=30)
arghmm.discretize_arg(arg, times)
pause()
# save
#arglib.write_arg("test/data/k4.arg", arg)
#fasta.write_fasta("test/data/k4.fa", seqs)
new_name = "n%d" % (k - 1)
thread = list(
arghmm.iter_chrom_thread(arg, arg[new_name], by_block=False))
p = plot(cget(thread, 1), style="lines", ymin=times[1], ylog=10)
# remove chrom
new_name = "n%d" % (k - 1)
arg = arghmm.remove_arg_thread(arg, new_name)
model = arghmm.ArgHmm(arg,
seqs,
new_name=new_name,
times=times,
rho=rho,
mu=mu)
print "states", len(model.states[0])
print "muts", len(muts)
print "recomb", len(model.recomb_pos) - 2, model.recomb_pos[1:-1]
p.plot(model.recomb_pos, [10000] * len(model.recomb_pos),
style="points")
probs = arghmm.get_posterior_probs(model, length, verbose=True)
print "done"
high = list(arghmm.iter_posterior_times(model, probs, .95))
low = list(arghmm.iter_posterior_times(model, probs, .05))
p.gnuplot("set linestyle 2")
p.plot(high, style="lines")
p.gnuplot("set linestyle 2")
p.plot(low, style="lines")
#write_list("test/data/post_real.txt", cget(thread, 1))
#write_list("test/data/post_high.txt", high)
#write_list("test/data/post_low.txt", low)
pause()
def test_post_plot(self):
k = 6
n = 1e4
rho = 1.5e-8 * 50
mu = 2.5e-8 * 50
length = 10000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(ntimes=30)
arghmm.discretize_arg(arg, times)
pause()
# save
#arglib.write_arg("test/data/k4.arg", arg)
#fasta.write_fasta("test/data/k4.fa", seqs)
new_name = "n%d" % (k-1)
thread = list(arghmm.iter_chrom_thread(arg, arg[new_name],
by_block=False))
p = plot(cget(thread, 1), style="lines", ymin=times[1],
ylog=10)
# remove chrom
new_name = "n%d" % (k-1)
arg = arghmm.remove_arg_thread(arg, new_name)
model = arghmm.ArgHmm(arg, seqs, new_name=new_name, times=times,
rho=rho, mu=mu)
print "states", len(model.states[0])
print "muts", len(muts)
print "recomb", len(model.recomb_pos) - 2, model.recomb_pos[1:-1]
p.plot(model.recomb_pos, [10000] * len(model.recomb_pos),
style="points")
probs = arghmm.get_posterior_probs(model, length, verbose=True)
print "done"
high = list(arghmm.iter_posterior_times(model, probs, .95))
low = list(arghmm.iter_posterior_times(model, probs, .05))
p.gnuplot("set linestyle 2")
p.plot(high, style="lines")
p.gnuplot("set linestyle 2")
p.plot(low, style="lines")
#write_list("test/data/post_real.txt", cget(thread, 1))
#write_list("test/data/post_high.txt", high)
#write_list("test/data/post_low.txt", low)
pause()
def test_norecomb_plot(self):
k = 50
n = 1e4
rho = 1.5e-8 * .0001
rho2 = 1.5e-8 * 10
mu = 2.5e-8 * 100
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(ntimes=20)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
# get thread
new_name = "n%d" % (k - 1)
keep = ["n%d" % i for i in range(k - 1)]
arglib.subarg_by_leaf_names(arg, keep)
arg.set_ancestral()
arg.prune()
model = arghmm.ArgHmm(arg,
seqs,
new_name=new_name,
times=times,
rho=rho2,
mu=mu)
print "states", len(model.states[0])
print "muts", len(muts)
# simulate a new thread
states = list(islice(hmm.sample_hmm_states(model), 0, arg.end))
data = list(hmm.sample_hmm_data(model, states))
seqs[new_name] = "".join(data)
#alignlib.print_align(seqs)
thread = [
model.times[model.states[i][s][1]] for i, s in enumerate(states)
]
p = plot(thread, style="lines")
probs = arghmm.get_posterior_probs(model, length, verbose=True)
print "done"
high = list(arghmm.iter_posterior_times(model, probs, .75))
low = list(arghmm.iter_posterior_times(model, probs, .25))
p.plot(high, style="lines")
p.plot(low, style="lines")
pause()
def test_local_trees(self):
rho = 1.5e-8 # recomb/site/gen
l = 10000 # length of locus
k = 10 # number of lineages
n = 2*1e4 # effective popsize
arg = arglib.sample_arg(k, n, rho, 0, l)
blocks1 = util.cget(arglib.iter_local_trees(arg, 200, 1200), 0)
blocks2 = list(arglib.iter_recomb_blocks(arg, 200, 1200))
self.assertEqual(blocks1, blocks2)
def test_post_real(self):
k = 3
n = 1e4
rho = 1.5e-8
mu = 2.5e-8
length = 100000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
#arg = arglib.read_arg("test/data/real.arg")
#seqs = fasta.read_fasta("test/data/real.fa")
#arglib.write_arg("test/data/real.arg", arg)
#fasta.write_fasta("test/data/real.fa", seqs)
times = arghmm.get_time_points(maxtime=50000, ntimes=20)
arghmm.discretize_arg(arg, times)
new_name = "n%d" % (k - 1)
thread = list(
arghmm.iter_chrom_thread(arg, arg[new_name], by_block=False))
tree = arg.get_marginal_tree(0)
print tree.root.age
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
p = plot(cget(thread, 1), style="lines", ymin=10, ylog=10)
#alignlib.print_align(seqs)
# remove chrom
keep = ["n%d" % i for i in range(k - 1)]
arglib.subarg_by_leaf_names(arg, keep)
arg = arglib.smcify_arg(arg)
model = arghmm.ArgHmm(arg,
seqs,
new_name=new_name,
times=times,
rho=rho,
mu=mu)
print "states", len(model.states[0])
#print "muts", len(muts)
print "recomb", len(model.recomb_pos) - 2, model.recomb_pos[1:-1]
probs = arghmm.get_posterior_probs(model, length, verbose=True)
high = list(arghmm.iter_posterior_times(model, probs, .95))
low = list(arghmm.iter_posterior_times(model, probs, .05))
p.plot(high, style="lines")
p.plot(low, style="lines")
pause()
def test_iter_sprs(self):
rho = 1.5e-8 # recomb/site/gen
l = 100000 # length of locus
k = 6 # number of lineages
n = 2*10000 # effective popsize
arg = arglib.sample_arg(k, n, rho, 0, l)
for a, b in izip(arglib.iter_arg_sprs(arg),
arglib.iter_arg_sprs_simple(arg)):
self.assertEqual(a, b)
def test_smcify_arg(self):
rho = 1.5e-8 # recomb/site/gen
l = 100000 # length of locus
k = 6 # number of lineages
n = 2*10000 # effective popsize
arg = arglib.sample_arg(k, n, rho, 0, l)
arg = arglib.smcify_arg(arg)
for pos, (rnode, rtime), (cnode, ctime) in arglib.iter_arg_sprs(arg):
self.assertNotEqual(rnode, cnode)
def test_trans_switch_single(self):
"""
Calculate transitions probabilities for switching between blocks
Only calculate a single matrix
"""
k = 5
n = 1e4
rho = 1.5e-8 * 100
mu = 2.5e-8
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
#arglib.write_arg("tmp/a.arg", arg)
#arg = arglib.read_arg("tmp/a.arg")
#arg.set_ancestral()
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(5)
arghmm.discretize_arg(arg, times)
new_name = "n%d" % (k - 1)
arg = arghmm.remove_arg_thread(arg, new_name)
model = arghmm.ArgHmm(arg, seqs, new_name=new_name, times=times)
# get recombs
recombs = list(x.pos for x in arghmm.iter_visible_recombs(arg))
print "recomb", recombs
pos = recombs[0] + 1
tree = arg.get_marginal_tree(pos - .5)
last_tree = arg.get_marginal_tree(pos - 1 - .5)
print "states1>>", model.states[pos - 1]
print "states2>>", model.states[pos]
treelib.draw_tree_names(last_tree.get_tree(), minlen=5, maxlen=5)
treelib.draw_tree_names(tree.get_tree(), minlen=5, maxlen=5)
print "pos>>", pos
recomb = [x for x in tree
if x.event == "recomb" and x.pos + 1 == pos][0]
mat = arghmm.calc_transition_probs_switch(tree, last_tree, recomb.name,
model.states[pos - 1],
model.states[pos],
model.nlineages, model.times,
model.time_steps,
model.popsizes, rho)
pc(mat)
def test_norecomb_plot(self):
k = 50
n = 1e4
rho = 1.5e-8 * .0001
rho2 = 1.5e-8 * 10
mu = 2.5e-8 * 100
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(ntimes=20)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
# get thread
new_name = "n%d" % (k-1)
keep = ["n%d" % i for i in range(k-1)]
arglib.subarg_by_leaf_names(arg, keep)
arg.set_ancestral()
arg.prune()
model = arghmm.ArgHmm(arg, seqs, new_name=new_name, times=times,
rho=rho2, mu=mu)
print "states", len(model.states[0])
print "muts", len(muts)
# simulate a new thread
states = list(islice(hmm.sample_hmm_states(model), 0, arg.end))
data = list(hmm.sample_hmm_data(model, states))
seqs[new_name] = "".join(data)
#alignlib.print_align(seqs)
thread = [model.times[model.states[i][s][1]]
for i, s in enumerate(states)]
p = plot(thread, style="lines")
probs = arghmm.get_posterior_probs(model, length, verbose=True)
print "done"
high = list(arghmm.iter_posterior_times(model, probs, .75))
low = list(arghmm.iter_posterior_times(model, probs, .25))
p.plot(high, style="lines")
p.plot(low, style="lines")
pause()
def test_trans_switch_single(self):
"""
Calculate transitions probabilities for switching between blocks
Only calculate a single matrix
"""
k = 5
n = 1e4
rho = 1.5e-8 * 100
mu = 2.5e-8
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
#arglib.write_arg("tmp/a.arg", arg)
#arg = arglib.read_arg("tmp/a.arg")
#arg.set_ancestral()
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(5)
arghmm.discretize_arg(arg, times)
new_name = "n%d" % (k-1)
arg = arghmm.remove_arg_thread(arg, new_name)
model = arghmm.ArgHmm(arg, seqs, new_name=new_name, times=times)
# get recombs
recombs = list(x.pos for x in arghmm.iter_visible_recombs(arg))
print "recomb", recombs
pos = recombs[0] + 1
tree = arg.get_marginal_tree(pos-.5)
last_tree = arg.get_marginal_tree(pos-1-.5)
print "states1>>", model.states[pos-1]
print "states2>>", model.states[pos]
treelib.draw_tree_names(last_tree.get_tree(), minlen=5, maxlen=5)
treelib.draw_tree_names(tree.get_tree(), minlen=5, maxlen=5)
print "pos>>", pos
recomb = [x for x in tree
if x.event == "recomb" and x.pos+1 == pos][0]
mat = arghmm.calc_transition_probs_switch(
tree, last_tree, recomb.name,
model.states[pos-1], model.states[pos],
model.nlineages, model.times,
model.time_steps, model.popsizes, rho)
pc(mat)
def test_post_c(self):
k = 3
n = 1e4
rho = 1.5e-8 * 30
mu = 2.5e-8 * 100
length = 100
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
arg.prune()
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
print arglib.get_recomb_pos(arg)
print "muts", len(muts)
print "recomb", len(arglib.get_recomb_pos(arg))
times = arghmm.get_time_points(ntimes=10)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
print tree.root.age
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
# remove chrom
keep = ["n%d" % i for i in range(k - 1)]
arglib.subarg_by_leaf_names(arg, keep)
model = arghmm.ArgHmm(arg,
seqs,
new_name="n%d" % (k - 1),
times=times,
rho=rho,
mu=mu)
print "states", len(model.states[0])
util.tic("C")
probs1 = list(arghmm.get_posterior_probs(model, length, verbose=True))
util.toc()
util.tic("python")
probs2 = list(hmm.get_posterior_probs(model, length, verbose=True))
util.toc()
print "probs1"
pc(probs1)
print "probs2"
pc(probs2)
for col1, col2 in izip(probs1, probs2):
for a, b in izip(col1, col2):
fequal(a, b)
def test_smcify_arg_remove_thread(self):
rho = 1.5e-8 # recomb/site/gen
l = 100000 # length of locus
k = 6 # number of lineages
n = 2*10000 # effective popsize
arg = arglib.sample_arg(k, n, rho, 0, l)
remove_chroms = set("n%d" % (k-1))
keep = [x for x in arg.leaf_names() if x not in remove_chroms]
arg = arg.copy()
arglib.subarg_by_leaf_names(arg, keep)
arg = arglib.smcify_arg(arg)
def test_post_real(self):
k = 3
n = 1e4
rho = 1.5e-8
mu = 2.5e-8
length = 100000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
#arg = arglib.read_arg("test/data/real.arg")
#seqs = fasta.read_fasta("test/data/real.fa")
#arglib.write_arg("test/data/real.arg", arg)
#fasta.write_fasta("test/data/real.fa", seqs)
times = arghmm.get_time_points(maxtime=50000, ntimes=20)
arghmm.discretize_arg(arg, times)
new_name = "n%d" % (k - 1)
thread = list(arghmm.iter_chrom_thread(arg, arg[new_name],
by_block=False))
tree = arg.get_marginal_tree(0)
print tree.root.age
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
p = plot(cget(thread, 1), style="lines", ymin=10, ylog=10)
#alignlib.print_align(seqs)
# remove chrom
keep = ["n%d" % i for i in range(k-1)]
arglib.subarg_by_leaf_names(arg, keep)
arg = arglib.smcify_arg(arg)
model = arghmm.ArgHmm(arg, seqs, new_name=new_name, times=times,
rho=rho, mu=mu)
print "states", len(model.states[0])
#print "muts", len(muts)
print "recomb", len(model.recomb_pos) - 2, model.recomb_pos[1:-1]
probs = arghmm.get_posterior_probs(model, length, verbose=True)
high = list(arghmm.iter_posterior_times(model, probs, .95))
low = list(arghmm.iter_posterior_times(model, probs, .05))
p.plot(high, style="lines")
p.plot(low, style="lines")
pause()
def test_iter_sprs_time(self):
rho = 1.5e-8 # recomb/site/gen
l = 100000 # length of locus
k = 40 # number of lineages
n = 2*10000 # effective popsize
arg = arglib.sample_arg(k, n, rho, 0, l)
x = list(arglib.iter_arg_sprs(arg))
x = list(arglib.iter_arg_sprs_simple(arg))
x = list(arglib.iter_arg_sprs(arg, use_leaves=True))
x = list(arglib.iter_arg_sprs_simple(arg, use_leaves=True))
x
def test_post_c(self):
k = 3
n = 1e4
rho = 1.5e-8 * 30
mu = 2.5e-8 * 100
length = 100
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
arg.prune()
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
print arglib.get_recomb_pos(arg)
print "muts", len(muts)
print "recomb", len(arglib.get_recomb_pos(arg))
times = arghmm.get_time_points(ntimes=10)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
print tree.root.age
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
# remove chrom
keep = ["n%d" % i for i in range(k-1)]
arglib.subarg_by_leaf_names(arg, keep)
model = arghmm.ArgHmm(arg, seqs, new_name="n%d" % (k-1), times=times,
rho=rho, mu=mu)
print "states", len(model.states[0])
util.tic("C")
probs1 = list(arghmm.get_posterior_probs(model, length, verbose=True))
util.toc()
util.tic("python")
probs2 = list(hmm.get_posterior_probs(model, length, verbose=True))
util.toc()
print "probs1"
pc(probs1)
print "probs2"
pc(probs2)
for col1, col2 in izip(probs1, probs2):
for a, b in izip(col1, col2):
fequal(a, b)
def test_post3(self):
k = 3
n = 1e4
rho = 1.5e-8 * 3
mu = 2.5e-8 * 100
length = 10000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
arg.prune()
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(ntimes=10)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
thread = list(arghmm.iter_chrom_thread(arg, arg["n2"], by_block=False))
p = plot(cget(thread, 1), style="lines", ymin=0)
# remove chrom
keep = ["n0", "n1"]
arglib.subarg_by_leaf_names(arg, keep)
arg.set_ancestral()
arg.prune()
model = arghmm.ArgHmm(arg,
seqs,
new_name="n2",
times=times,
rho=rho,
mu=mu)
print "states", len(model.states[0])
print "muts", len(muts)
print "recomb", len(model.recomb_pos) - 2, model.recomb_pos[1:-1]
p.plot(model.recomb_pos, [1000] * len(model.recomb_pos),
style="points")
probs = arghmm.get_posterior_probs(model, length, verbose=True)
high = list(arghmm.iter_posterior_times(model, probs, .95))
low = list(arghmm.iter_posterior_times(model, probs, .05))
p.plot(high, style="lines")
p.plot(low, style="lines")
pause()
def test_iter_sprs_remove_thread(self):
rho = 1.5e-8 # recomb/site/gen
l = 100000 # length of locus
k = 6 # number of lineages
n = 2*10000 # effective popsize
arg = arglib.sample_arg(k, n, rho, 0, l)
remove_chroms = set("n%d" % (k-1))
keep = [x for x in arg.leaf_names() if x not in remove_chroms]
arg = arg.copy()
arglib.subarg_by_leaf_names(arg, keep)
for a, b in izip(arglib.iter_arg_sprs(arg),
arglib.iter_arg_sprs_simple(arg)):
self.assertEqual(a, b)
def test_iter_sprs_leaves(self):
rho = 1.5e-8 # recomb/site/gen
l = 100000 # length of locus
k = 40 # number of lineages
n = 2*10000 # effective popsize
arg = arglib.sample_arg(k, n, rho, 0, l)
for a, b in izip(arglib.iter_arg_sprs(arg, use_leaves=True),
arglib.iter_arg_sprs_simple(arg, use_leaves=True)):
a[1][0].sort()
a[2][0].sort()
b[1][0].sort()
b[2][0].sort()
self.assertEqual(a, b)
def test_marginal_leaves(self):
rho = 1.5e-8 # recomb/site/gen
l = 10000 # length of locus
k = 10 # number of lineages
n = 2*10000 # effective popsize
arg = arglib.sample_arg(k, n, rho, 0, l)
for (start, end), tree in arglib.iter_local_trees(arg):
arglib.remove_single_lineages(tree)
mid = (start + end) / 2.0
for node in tree:
a = set(tree.leaves(node))
b = set(arglib.get_marginal_leaves(arg, node, mid))
self.assertEqual(a, b)
def test_post3(self):
k = 3
n = 1e4
rho = 1.5e-8 * 3
mu = 2.5e-8 * 100
length = 10000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
arg.prune()
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(ntimes=10)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
thread = list(arghmm.iter_chrom_thread(arg, arg["n2"], by_block=False))
p = plot(cget(thread, 1), style="lines", ymin=0)
# remove chrom
keep = ["n0", "n1"]
arglib.subarg_by_leaf_names(arg, keep)
arg.set_ancestral()
arg.prune()
model = arghmm.ArgHmm(arg, seqs, new_name="n2", times=times,
rho=rho, mu=mu)
print "states", len(model.states[0])
print "muts", len(muts)
print "recomb", len(model.recomb_pos) - 2, model.recomb_pos[1:-1]
p.plot(model.recomb_pos, [1000] * len(model.recomb_pos),
style="points")
probs = arghmm.get_posterior_probs(model, length, verbose=True)
high = list(arghmm.iter_posterior_times(model, probs, .95))
low = list(arghmm.iter_posterior_times(model, probs, .05))
p.plot(high, style="lines")
p.plot(low, style="lines")
pause()
def test_post2(self):
k = 2
n = 1e4
rho = 1.5e-8 * 10
mu = 2.5e-8 * 10
length = 10000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
print "muts", len(muts)
times = arghmm.get_time_points()
arghmm.discretize_arg(arg, times)
thread = list(arghmm.iter_chrom_thread(arg, arg["n1"], by_block=False))
tree = arg.get_marginal_tree(0)
print tree.root.age
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
p = plot(cget(thread, 1), style="lines", ymin=0)
#alignlib.print_align(seqs)
# remove chrom
keep = ["n0"]
arglib.subarg_by_leaf_names(arg, keep)
arg = arglib.smcify_arg(arg)
model = arghmm.ArgHmm(arg,
seqs,
new_name="n1",
times=times,
rho=rho,
mu=mu)
print "states", len(model.states[0])
probs = arghmm.get_posterior_probs(model, length, verbose=True)
high = list(arghmm.iter_posterior_times(model, probs, .95))
low = list(arghmm.iter_posterior_times(model, probs, .05))
p.plot(high, style="lines")
p.plot(low, style="lines")
pause()
def test_plot_thread(self):
"""
Test thread retrieval
"""
k = 60
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8 * 20
length = int(1000e3) / 20
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
node = arg.leaves().next()
x = range(length)
y = cget(arghmm.iter_chrom_thread(arg, node, by_block=False), 1)
p = plot(x, y, style='lines')
pause()
def test_plot_thread(self):
"""
Test thread retrieval
"""
k = 60
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8 * 20
length = int(1000e3) / 20
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
node = arg.leaves().next()
x = range(length)
y = cget(arghmm.iter_chrom_thread(arg, node, by_block=False), 1)
p = plot(x, y, style='lines')
pause()
def test_trans():
"""
Calculate transition probabilities
"""
k = 4
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=4, maxtime=200000)
popsizes = [n] * len(times)
arg = arglib.sample_arg(k, 2*n, rho, start=0, end=length)
argweaver.discretize_arg(arg, times)
pos = 10
tree = arg.get_marginal_tree(pos)
assert argweaverc.assert_transition_probs(tree, times, popsizes, rho)
def test_trans():
"""
Calculate transition probabilities
"""
k = 4
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=4, maxtime=200000)
popsizes = [n] * len(times)
arg = arglib.sample_arg(k, 2 * n, rho, start=0, end=length)
argweaver.discretize_arg(arg, times)
pos = 10
tree = arg.get_marginal_tree(pos)
assert argweaverc.assert_transition_probs(tree, times, popsizes, rho)
def test_read_write(self):
"""Read and write an ARG"""
rho = 1.5e-8 # recomb/site/gen
l = 10000 # length of locus
k = 10 # number of lineages
n = 2*10000 # effective popsize
arg = arglib.sample_arg(k, n, rho, 0, l)
# round ages and pos for easy equality
for node in arg:
node.age = round(node.age)
node.pos = round(node.pos)
stream = StringIO.StringIO()
arglib.write_arg(stream, arg)
stream.seek(0)
arg2 = arglib.read_arg(stream)
self.assertTrue(arg.equal(arg2))
def test_thread(self):
"""
Test thread retrieval
"""
k = 10
n = 1e4
rho = 1.5e-8 * 10
mu = 2.5e-8 * 100
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
for (block, tree), threadi in izip(
arglib.iter_tree_tracks(arg),
arghmm.iter_chrom_thread(arg, arg["n9"], by_block=True)):
print block
print threadi
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
def test_thread(self):
"""
Test thread retrieval
"""
k = 10
n = 1e4
rho = 1.5e-8 * 10
mu = 2.5e-8 * 100
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
for (block, tree), threadi in izip(
arglib.iter_tree_tracks(arg),
arghmm.iter_chrom_thread(arg, arg["n9"], by_block=True)):
print block
print threadi
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
def test_post2(self):
k = 2
n = 1e4
rho = 1.5e-8 * 10
mu = 2.5e-8 * 10
length = 10000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
print "muts", len(muts)
times = arghmm.get_time_points()
arghmm.discretize_arg(arg, times)
thread = list(arghmm.iter_chrom_thread(arg, arg["n1"], by_block=False))
tree = arg.get_marginal_tree(0)
print tree.root.age
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
p = plot(cget(thread, 1), style="lines", ymin=0)
#alignlib.print_align(seqs)
# remove chrom
keep = ["n0"]
arglib.subarg_by_leaf_names(arg, keep)
arg = arglib.smcify_arg(arg)
model = arghmm.ArgHmm(arg, seqs, new_name="n1", times=times,
rho=rho, mu=mu)
print "states", len(model.states[0])
probs = arghmm.get_posterior_probs(model, length, verbose=True)
high = list(arghmm.iter_posterior_times(model, probs, .95))
low = list(arghmm.iter_posterior_times(model, probs, .05))
p.plot(high, style="lines")
p.plot(low, style="lines")
pause()
def test_states(self):
"""
Test state enumeration
"""
k = 2
n = 1e4
rho = 1.5e-8 * 100
length = 1000
for i in xrange(20):
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
times = arghmm.get_time_points(10)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
states = list(arghmm.iter_coal_states(tree, times))
treelib.draw_tree_names(tree.get_tree(), scale=4e-4,
minlen=6, maxlen=6)
print states
def test_emit_argmax(self):
"""
Calculate emission probabilities
"""
k = 10
n = 1e4
rho = 0.0
mu = 2.5e-8 * 100
length = 10000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(10)
arghmm.discretize_arg(arg, times)
new_name = "n%d" % (k-1)
thread = list(arghmm.iter_chrom_thread(arg, arg[new_name]))
arg = arghmm.remove_arg_thread(arg, new_name)
model = arghmm.ArgHmm(arg, seqs, new_name=new_name, times=times)
nstates = model.get_num_states(1)
probs = [0.0 for j in xrange(nstates)]
for i in xrange(1, length):
if i % 100 == 0:
print i
for j in xrange(nstates):
probs[j] += model.prob_emission(i, j)
print
# is the maximum likelihood emission matching truth
data = sorted(zip(probs, model.states[0]), reverse=True)
pc(data[:20])
state = (thread[0][0], times.index(thread[0][1]))
print data[0][1], state
assert data[0][1] == state
def test_emit_argmax(self):
"""
Calculate emission probabilities
"""
k = 10
n = 1e4
rho = 0.0
mu = 2.5e-8 * 100
length = 10000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(10)
arghmm.discretize_arg(arg, times)
new_name = "n%d" % (k - 1)
thread = list(arghmm.iter_chrom_thread(arg, arg[new_name]))
arg = arghmm.remove_arg_thread(arg, new_name)
model = arghmm.ArgHmm(arg, seqs, new_name=new_name, times=times)
nstates = model.get_num_states(1)
probs = [0.0 for j in xrange(nstates)]
for i in xrange(1, length):
if i % 100 == 0:
print i
for j in xrange(nstates):
probs[j] += model.prob_emission(i, j)
print
# is the maximum likelihood emission matching truth
data = sorted(zip(probs, model.states[0]), reverse=True)
pc(data[:20])
state = (thread[0][0], times.index(thread[0][1]))
print data[0][1], state
assert data[0][1] == state
def test_backward(self):
"""
Run backward algorithm
"""
k = 3
n = 1e4
rho = 1.5e-8 * 100
mu = 2.5e-8 * 100
length = 10000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
times = arghmm.get_time_points(ntimes=10)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
print tree.root.age
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
# remove chrom
new_name = "n%d" % (k - 1)
arg = arghmm.remove_arg_thread(arg, new_name)
model = arghmm.ArgHmm(arg,
seqs,
new_name=new_name,
times=times,
rho=rho,
mu=mu)
print "states", len(model.states[0])
print "recomb", model.recomb_pos
print "muts", len(muts)
probs = hmm.backward_algorithm(model, length, verbose=True)
for pcol in probs:
p = sum(map(exp, pcol))
print p, " ".join("%.3f" % f for f in map(exp, pcol))
def test_trans(self):
"""
Calculate transition probabilities for k=2
Only calculate a single matrix
"""
k = 4
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8 * 20
length = 1000
times = arghmm.get_time_points(ntimes=4, maxtime=200000)
popsizes = [n] * len(times)
arg = arglib.sample_arg(k, 2*n, rho, start=0, end=length)
arghmm.discretize_arg(arg, times)
pos = 10
tree = arg.get_marginal_tree(pos)
assert arghmm.assert_transition_probs(tree, times, popsizes, rho)
def test_trans_internal():
"""
Calculate transition probabilities for internal branch re-sampling
Only calculate a single matrix
"""
k = 5
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=5, maxtime=200000)
popsizes = [n] * len(times)
arg = arglib.sample_arg(k, 2 * n, rho, start=0, end=length)
argweaver.discretize_arg(arg, times)
pos = 10
tree = arg.get_marginal_tree(pos)
assert argweaverc.assert_transition_probs_internal(tree, times, popsizes,
rho)
def test_trans_internal():
"""
Calculate transition probabilities for internal branch re-sampling
Only calculate a single matrix
"""
k = 5
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=5, maxtime=200000)
popsizes = [n] * len(times)
arg = arglib.sample_arg(k, 2*n, rho, start=0, end=length)
argweaver.discretize_arg(arg, times)
pos = 10
tree = arg.get_marginal_tree(pos)
assert argweaverc.assert_transition_probs_internal(
tree, times, popsizes, rho)
def test_post(self):
k = 6
n = 1e4
rho = 1.5e-8 * 10
mu = 2.5e-8 * 10
length = 10000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
print "muts", len(muts)
print "recombs", len(arglib.get_recomb_pos(arg))
times = arghmm.get_time_points(ntimes=10)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
treelib.draw_tree_names(tree.get_tree(), minlen=5, scale=4e-4)
# remove chrom
new_name = "n%d" % (k - 1)
keep = set(arg.leaf_names()) - set([new_name])
arglib.subarg_by_leaf_names(arg, keep)
arg = arglib.smcify_arg(arg)
model = arghmm.ArgHmm(arg,
seqs,
new_name=new_name,
times=times,
rho=rho,
mu=mu)
print "states", len(model.states[0])
probs = arghmm.get_posterior_probs(model, length, verbose=True)
for pcol in probs:
p = sum(map(exp, pcol))
print p, " ".join("%.3f" % f for f in map(exp, pcol))
fequal(p, 1.0, rel=1e-2)
def test_trans(self):
"""
Calculate transition probabilities for k=2
Only calculate a single matrix
"""
k = 4
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8 * 20
length = 1000
times = arghmm.get_time_points(ntimes=4, maxtime=200000)
popsizes = [n] * len(times)
arg = arglib.sample_arg(k, 2 * n, rho, start=0, end=length)
arghmm.discretize_arg(arg, times)
pos = 10
tree = arg.get_marginal_tree(pos)
assert arghmm.assert_transition_probs(tree, times, popsizes, rho)
def test_pars_seq(self):
"""
Test parsimony ancestral sequence inference
"""
k = 10
n = 1e4
rho = 1.5e-8
mu = 2.5e-8 * 100
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
pos = int(muts[0][2])
tree = arg.get_marginal_tree(pos)
print "pos =", pos
treelib.draw_tree_names(tree.get_tree(), scale=4e-4, minlen=5)
arglib.remove_single_lineages(tree)
ancestral = arghmm.emit.parsimony_ancestral_seq(tree, seqs, pos)
util.print_dict(ancestral)
def test_pars_seq(self):
"""
Test parsimony ancestral sequence inference
"""
k = 10
n = 1e4
rho = 1.5e-8
mu = 2.5e-8 * 100
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
pos = int(muts[0][2])
tree = arg.get_marginal_tree(pos)
print "pos =", pos
treelib.draw_tree_names(tree.get_tree(), scale=4e-4, minlen=5)
arglib.remove_single_lineages(tree)
ancestral = arghmm.emit.parsimony_ancestral_seq(tree, seqs, pos)
util.print_dict(ancestral)
def test_states(self):
"""
Test state enumeration
"""
k = 2
n = 1e4
rho = 1.5e-8 * 100
length = 1000
for i in xrange(20):
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
times = arghmm.get_time_points(10)
arghmm.discretize_arg(arg, times)
tree = arg.get_marginal_tree(0)
states = list(arghmm.iter_coal_states(tree, times))
treelib.draw_tree_names(tree.get_tree(),
scale=4e-4,
minlen=6,
maxlen=6)
print states
def test_recomb(self):
"""
Investigate the fact that some recombinations are not visible
"""
k = 3
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8
length = 1000
arg = arglib.sample_arg(k, n, rho, start=0, end=length)
times = arghmm.get_time_points(10)
arghmm.discretize_arg(arg, times)
arg.set_ancestral()
arg.prune()
recombs = arglib.get_recomb_pos(arg)
# find recombs by walking
recombs2 = []
i = 0
while True:
tree = arg.get_marginal_tree(i-.5)
recomb = arghmm.find_tree_next_recomb(tree, i+1, tree=True)
if recomb:
recombs2.append(recomb.pos)
i = recomb.pos
else:
break
# these are suppose to differ because some recombination occur
# in the hole of ancestral sequence intervals
print recombs
print recombs2
arglib.write_arg("tmp/b.arg", arg)
