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_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_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_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_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_forward():
k = 4
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8 * 20
length = int(100e3 / 20)
times = argweaver.get_time_points(ntimes=100)
arg = arglib.sample_arg_smc(k, 2 * n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
print "muts", len(muts)
print "recomb", len(arglib.get_recomb_pos(arg))
argweaver.discretize_arg(arg, times)
# remove chrom
new_name = "n%d" % (k - 1)
arg = argweaver.remove_arg_thread(arg, new_name)
carg = argweaverc.arg2ctrees(arg, times)
util.tic("C fast")
probs1 = argweaverc.argweaver_forward_algorithm(carg, seqs, times=times)
util.toc()
util.tic("C slow")
probs2 = argweaverc.argweaver_forward_algorithm(carg,
seqs,
times=times,
slow=True)
util.toc()
for i, (col1, col2) in enumerate(izip(probs1, probs2)):
for a, b in izip(col1, col2):
fequal(a, b, rel=.0001)
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_forward():
k = 4
n = 1e4
rho = 1.5e-8 * 20
mu = 2.5e-8 * 20
length = int(100e3 / 20)
times = argweaver.get_time_points(ntimes=100)
arg = arglib.sample_arg_smc(k, 2*n, rho, start=0, end=length)
muts = arglib.sample_arg_mutations(arg, mu)
seqs = arglib.make_alignment(arg, muts)
print "muts", len(muts)
print "recomb", len(arglib.get_recombs(arg))
argweaver.discretize_arg(arg, times)
# remove chrom
new_name = "n%d" % (k - 1)
arg = argweaver.remove_arg_thread(arg, new_name)
carg = argweaverc.arg2ctrees(arg, times)
util.tic("C fast")
probs1 = argweaverc.argweaver_forward_algorithm(carg, seqs, times=times)
util.toc()
util.tic("C slow")
probs2 = argweaverc.argweaver_forward_algorithm(carg, seqs, times=times,
slow=True)
util.toc()
for i, (col1, col2) in enumerate(izip(probs1, probs2)):
for a, b in izip(col1, col2):
fequal(a, b, rel=.0001)
def show_plots(arg_file, sites_file, stats_file, output_prefix,
rho, mu, popsize, ntimes=20, maxtime=200000):
"""
Show plots of convergence.
"""
# read true arg and seqs
times = argweaver.get_time_points(ntimes=ntimes, maxtime=maxtime)
arg = arglib.read_arg(arg_file)
argweaver.discretize_arg(arg, times, ignore_top=False, round_age="closer")
arg = arglib.smcify_arg(arg)
seqs = argweaver.sites2seqs(argweaver.read_sites(sites_file))
# compute true stats
arglen = arglib.arglen(arg)
arg = argweaverc.arg2ctrees(arg, times)
nrecombs = argweaverc.get_local_trees_ntrees(arg[0]) - 1
lk = argweaverc.calc_likelihood(
arg, seqs, mu=mu, times=times,
delete_arg=False)
prior = argweaverc.calc_prior_prob(
arg, rho=rho, times=times, popsizes=popsize,
delete_arg=False)
joint = lk + prior
data = read_table(stats_file)
# joint
y2 = joint
y = data.cget("joint")
rplot_start(output_prefix + ".trace.joint.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="joint probability",
xlab="iterations",
ylab="joint probability")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# lk
y2 = lk
y = data.cget("likelihood")
rplot_start(output_prefix + ".trace.lk.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="likelihood",
xlab="iterations",
ylab="likelihood")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# prior
y2 = prior
y = data.cget("prior")
rplot_start(output_prefix + ".trace.prior.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="prior probability",
xlab="iterations",
ylab="prior probability")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# nrecombs
y2 = nrecombs
y = data.cget("recombs")
rplot_start(output_prefix + ".trace.nrecombs.pdf",
width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="number of recombinations",
xlab="iterations",
ylab="number of recombinations")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# arglen
y2 = arglen
y = data.cget("arglen")
rplot_start(output_prefix + ".trace.arglen.pdf",
width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="ARG branch length",
xlab="iterations",
ylab="ARG branch length")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
def show_plots(arg_file, sites_file, stats_file, output_prefix,
rho, mu, popsize, ntimes=20, maxtime=200000):
"""
Show plots of convergence.
"""
# read true arg and seqs
times = argweaver.get_time_points(ntimes=ntimes, maxtime=maxtime)
arg = arglib.read_arg(arg_file)
argweaver.discretize_arg(arg, times, ignore_top=False, round_age="closer")
arg = arglib.smcify_arg(arg)
seqs = argweaver.sites2seqs(argweaver.read_sites(sites_file))
# compute true stats
arglen = arglib.arglen(arg)
arg = argweaverc.arg2ctrees(arg, times)
nrecombs = argweaverc.get_local_trees_ntrees(arg[0]) - 1
lk = argweaverc.calc_likelihood(
arg, seqs, mu=mu, times=times,
delete_arg=False)
prior = argweaverc.calc_prior_prob(
arg, rho=rho, times=times, popsizes=popsize,
delete_arg=False)
joint = lk + prior
data = read_table(stats_file)
# joint
y2 = joint
y = data.cget("joint")
rplot_start(output_prefix + ".trace.joint.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="joint probability",
xlab="iterations",
ylab="joint probability")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# lk
y2 = lk
y = data.cget("likelihood")
rplot_start(output_prefix + ".trace.lk.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="likelihood",
xlab="iterations",
ylab="likelihood")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# prior
y2 = prior
y = data.cget("prior")
rplot_start(output_prefix + ".trace.prior.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="prior probability",
xlab="iterations",
ylab="prior probability")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# nrecombs
y2 = nrecombs
y = data.cget("recombs")
rplot_start(output_prefix + ".trace.nrecombs.pdf",
width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="number of recombinations",
xlab="iterations",
ylab="number of recombinations")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# arglen
y2 = arglen
y = data.cget("arglen")
rplot_start(output_prefix + ".trace.arglen.pdf",
width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="ARG branch length",
xlab="iterations",
ylab="ARG branch length")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
