def dup_loss_topology_prior(tree, stree, recon, birth, death, maxdoom=20, events=None):
"""
Returns the log prior of a gene tree topology according to dup-loss model
"""
def gene2species(gene):
return recon[tree.nodes[gene]].name
if events is None:
events = phylo.label_events(tree, recon)
leaves = set(tree.leaves())
phylo.add_implied_spec_nodes(tree, stree, recon, events)
pstree, snodes, snodelookup = spidir.make_ptree(stree)
# get doomtable
doomtable = calc_doom_table(stree, birth, death, maxdoom)
prod = 0.0
for node in tree:
if events[node] == "spec":
for schild in recon[node].children:
nodes2 = [x for x in node.children if recon[x] == schild]
if len(nodes2) > 0:
node2 = nodes2[0]
subleaves = get_sub_tree(node2, schild, recon, events)
nhist = birthdeath.num_topology_histories(node2, subleaves)
s = len(subleaves)
thist = stats.factorial(s) * stats.factorial(s - 1) / 2 ** (s - 1)
if len(set(subleaves) & leaves) == 0:
# internal
prod += log(num_redundant_topology(node2, gene2species, subleaves, True))
else:
# leaves
prod += log(num_redundant_topology(node2, gene2species, subleaves, False))
else:
nhist = 1.0
thist = 1.0
s = 0
t = sum(
stats.choose(s + i, i)
* birthdeath.prob_birth_death1(s + i, schild.dist, birth, death)
* exp(doomtable[snodelookup[schild]]) ** i
for i in range(maxdoom + 1)
)
prod += log(nhist) - log(thist) + log(t)
# correct for renumbering
nt = num_redundant_topology(tree.root, gene2species)
prod -= log(nt)
# phylo.removeImpliedSpecNodes(tree, recon, events)
treelib.remove_single_children(tree)
return prod
def test_birthDeathCount(self):
"""birthDeathCount"""
l = 3
u = .5
for t in frange(0, 5, .01):
for s in range(0, 20):
p1 = spidir.birthDeathCount(s, t, l, u)
p2 = birthdeath.prob_birth_death1(s, t, l, u)
fequal(p1, p2, .01)
def test_birthDeathCount(self):
"""birthDeathCount"""
l = 3
u = .5
for t in frange(0, 5, .01):
for s in range(0, 20):
p1 = spidir.birthDeathCount(s, t, l, u)
p2 = birthdeath.prob_birth_death1(s, t, l, u)
fequal(p1, p2, .01)
def test_prob_birth_death1(self):
"""Sampling and PDF for birth-death from single lineage."""
t = 1.0
birth = 0.5
death = 0.2
counts = [birthdeath.sample_birth_death_count(1, t, birth, death)
for i in xrange(10000)]
eq_sample_pmf(
counts,
lambda i: birthdeath.prob_birth_death1(i, t, birth, death),
pval=0.01)
def test_prob_birth_death1_eq(self):
"""
Sampling and PDF for birth-death from single lineage birth=death rate.
"""
t = 1.0
birth = 0.5
death = 0.5
counts = [
birthdeath.sample_birth_death_count(1, t, birth, death)
for i in xrange(10000)
]
eq_sample_pmf(
counts, lambda i: birthdeath.prob_birth_death1(i, t, birth, death))
def walk(node):
if node.is_leaf():
doomtable[nodelookup[node]] = -util.INF
else:
for child in node.children:
walk(child)
i = nodelookup[node]
p = 1.0
for child in node:
p *= sum(
birthdeath.prob_birth_death1(d, child.dist, birth, death) * exp(doomtable[nodelookup[child]]) ** d
for d in range(0, maxdoom + 1)
)
doomtable[i] = util.safelog(p, e, -util.INF)
def walk(node):
if node.is_leaf():
doomtable[nodelookup[node]] = -util.INF
else:
for child in node.children:
walk(child)
i = nodelookup[node]
p = 1.0
for child in node:
p *= sum(
birthdeath.prob_birth_death1(d, child.dist, birth, death) *
exp(doomtable[nodelookup[child]])**d
for d in range(0, maxdoom + 1))
doomtable[i] = util.safelog(p, e, -util.INF)
def dup_loss_topology_prior(tree,
stree,
recon,
birth,
death,
maxdoom=20,
events=None):
"""
Returns the log prior of a gene tree topology according to dup-loss model
"""
def gene2species(gene):
return recon[tree.nodes[gene]].name
if events is None:
events = phylo.label_events(tree, recon)
leaves = set(tree.leaves())
phylo.add_implied_spec_nodes(tree, stree, recon, events)
pstree, snodes, snodelookup = spidir.make_ptree(stree)
# get doomtable
doomtable = calc_doom_table(stree, birth, death, maxdoom)
prod = 0.0
for node in tree:
if events[node] == "spec":
for schild in recon[node].children:
nodes2 = [x for x in node.children if recon[x] == schild]
if len(nodes2) > 0:
node2 = nodes2[0]
subleaves = get_sub_tree(node2, schild, recon, events)
nhist = birthdeath.num_topology_histories(node2, subleaves)
s = len(subleaves)
thist = stats.factorial(s) * stats.factorial(s - 1) / 2**(
s - 1)
if len(set(subleaves) & leaves) == 0:
# internal
prod += log(
num_redundant_topology(node2, gene2species,
subleaves, True))
else:
# leaves
prod += log(
num_redundant_topology(node2, gene2species,
subleaves, False))
else:
nhist = 1.0
thist = 1.0
s = 0
t = sum(
stats.choose(s + i, i) * birthdeath.prob_birth_death1(
s + i, schild.dist, birth, death) *
exp(doomtable[snodelookup[schild]])**i
for i in range(maxdoom + 1))
prod += log(nhist) - log(thist) + log(t)
# correct for renumbering
nt = num_redundant_topology(tree.root, gene2species)
prod -= log(nt)
#phylo.removeImpliedSpecNodes(tree, recon, events)
treelib.remove_single_children(tree)
return prod
