def mutations():
n = 10
# num_reps = 1000
num_reps = 1
num_loci = 10001
# recomb_rates = [(1000, 0.005), (2000, 0.01), (3000, 0), (10001, 0.05)]
recomb_rates = [(10001, 0.05)]
last_pos = 0
mean_rate = 0
for pos, rate in recomb_rates:
d = (pos - last_pos - 1) / (num_loci - 1)
mean_rate += d * rate
# print("mean_rate + ", d, rate)
# print("rate = ", rate, rate / (4 * 10**4))
last_pos = pos
assert last_pos == num_loci
print("mean_rate = ", mean_rate)
num_trees = 0
for j in range(num_reps):
simulator = msprime.TreeSimulator(n)
simulator.set_num_loci(num_loci)
simulator.set_scaled_recombination_rate(mean_rate)
# simulator.set_random_seed(j)
simulator.run()
num_trees += simulator.get_num_breakpoints()
ts = simulator.get_tree_sequence()
for t in ts.trees():
print(t.get_interval()[0])
# Construct the scrm command line. Use the first value as the background
# rate
simulator.set_scaled_recombination_rate(recomb_rates[0][-1])
cmd = simulator.get_ms_command_line(
"/home/jk/work/wt/papers/msprime/simulators/scrm",
num_replicates=num_reps)
for j in range(len(recomb_rates) - 1):
pos = recomb_rates[j][0]
# We still scale the recombination rate by the full locus length,
# not the subset that we are working over.
length = num_loci - 1
rate = recomb_rates[j + 1][1]
cmd += ["-sr", str(pos), str(rate * length)]
# print(cmd)
print(" ".join(cmd))
result = subprocess.check_output(cmd)
scrm_num_trees = 0
for line in result.splitlines():
# print(line)
if line.startswith(b"["):
scrm_num_trees += 1
print(num_trees / num_reps, scrm_num_trees / num_reps)
def simulations():
n = 10
m = 1000
recomb_map = msprime.RecombinationMap(m, [0, 0.5, 0.6, 0.7, 1],
[0.1, 10, 0, 0.1, 0])
sim = msprime.TreeSimulator(n)
sim.set_random_seed(1)
sim.set_num_loci(m)
sim.set_recombination_map(recomb_map)
# sim.set_scaled_recombination_rate(
# recomb_map.get_total_recombination_rate())
sim.run()
ts = sim.get_tree_sequence()
size = 0
for l, records_in, records_out in ts.diffs():
# print(l, records_in, records_out)
size += l
print("size", size, ts.get_sequence_length())
for t in ts.trees():
l, r = t.get_interval()
# print(l, r)
for l, ns in ts.newick_trees():
print(l, ns)
def run_verify(args):
"""
Checks that the distibution of events we get is the same as msprime.
"""
n = args.sample_size
m = args.num_loci
rho = args.recombination_rate
msp_events = np.zeros(args.num_replicates)
local_events = np.zeros(args.num_replicates)
for j in range(args.num_replicates):
random.seed(j)
s = Simulator(n, m, rho, 10000)
s.simulate()
local_events[j] = s.num_re_events
s = msprime.TreeSimulator(n)
s.set_num_loci(m)
s.set_scaled_recombination_rate(rho)
s.set_random_seed(j)
s.run()
msp_events[j] = s.get_num_recombination_events()
sm.graphics.qqplot(local_events)
sm.qqplot_2samples(local_events, msp_events, line="45")
pyplot.savefig(args.outfile, dpi=72)