def sim_step_indiv(N, time, dr=.0012, lr=.0011, Fd=1e-5, Fl=1e-5, pi=1e0):
"""
Run a Poisson-based D/L simulation on an individual frequency.
All inputs are assumed sanitized
"""
def chooseevent(subrate, fullrate):
return random.random() <= subrate / fullrate
drpyr = dr / 1e6 # dr in events/myr/indiv; drpyr in events/yr/indiv
lrpyr = lr / 1e6 # lr in events/myr/indiv; lrpyr in events/yr/indiv
edrpyr = drpyr * pi * N # get population dup rate per year TODO: may need *N?
elrpyr = lrpyr * pi * N # get population loss rate per year TODO: see note above
eventrate = edrpyr + elrpyr # get total event rate per year
numlosses = 0
clock = time
newp = [pi]
# simulate Poisson process for D/L events
while clock > 0.0:
eventtime = stats.exponentialvariate(eventrate) # time to next event
if eventtime > clock:
clock = 0.0
break
clock -= eventtime
if chooseevent(edrpyr, eventrate): # determine whether event is D or L
newp.append(sim_step_indiv(N, clock, dr, lr, Fd, Fl, Fd))
debugprint(" Duplication")
else:
numlosses += 1 # all losses in period grouped together (approx)
# poor approx?
if numlosses > 0:
newp[0] = max(newp[0] - numlosses * Fl, 0.0)
debugprint(" Losses: " + str(numlosses))
newp[0] = (coal.sample_freq_CDF(newp[0], N, time))
return flatten(newp) # needs flattening?
def sim_walk(node, p, walk_time=0.0, time_until_force=forcetime):
debugprint(" Sim on branch" + str(node.name) + " with frequency " + str(p) + " and walk time " + str(walk_time))
if p <= 0.0:
debugprint(" Extinction on branch " + str(node.name))
parent = node.parent
stree.remove_tree(node) # extinction event
remove_duds(parent)
return
elif p >= 1.0: # sanity check
p = 1.0
eff_dr = dr * p # * popsize #??
eff_lr = lr * p # * popsize #??
eff_bothr = eff_dr + eff_lr
event_time = stats.exponentialvariate(eff_bothr)
if event_time >= min(time_until_force, node.dist - walk_time): # >= ok?
# do not process D/L event; determine whether at force or new node
if time_until_force < node.dist - walk_time:
# force new frequency
newp = coal.sample_freq_CDF(p, popsize, forcetime * 1e6)
# scale forcetime to years (in myr)
debugprint(" Forced new frequency: " + str(newp))
## TODO: may wish to log newp in node.data
new_walk_time = walk_time + time_until_force
return sim_walk(node, newp, walk_time=new_walk_time)
# continue walk with new frequency
# increase walk_time accordingly
# reset time_until_force to forcetime
else:
# finish node, determine whether to contine walking on children
newp = coal.sample_freq_CDF(p, popsize, \
(node.dist - walk_time) * 1e6)
# scale remaining time into years (from myr)
node.data['freq'] = newp
# stores frequency of allele at the speciation event
debugprint(" Completed branch; new frequency: " + str(newp))
return node.recurse(sim_walk, newp)
else:
# process D/L event
# no WF updates for these events (modelling decision)
new_walk_time = walk_time + event_time
new_time_until_force = time_until_force - event_time
if event_is_dup(eff_dr, eff_bothr):
# perform duplication event
new_node = treelib.TreeNode(stree.new_name())
# create a node new_node for the duplication event
stree.add_child(node.parent, new_node) # add the dup node
subtree_copy = treelib.subtree(stree, node)
# make a copy of node's subtree (dup tree)
stree.remove(node) # pull node off of parent node
stree.add_child(new_node, node) # attach node to dup node
stree.add_tree(new_node, subtree_copy) # attach dup copy
new_node.dist = new_walk_time # set dist to dup
node.dist = node.dist - new_walk_time # correct for dup dist
subtree_copy.root.dist = node.dist # also correct for dup dist
new_node.data['freq'] = p # set frequency at dup event
debugprint(" Duplication occurred at walk time " + str(new_walk_time))
sim_walk(node, p, time_until_force = new_time_until_force)
# recurse on remainder of original branch
sim_walk(subtree_copy.root, freqdup, time_until_force = new_time_until_force)
# recurse on dup tree with correct starting frequency
return
else:
# perform loss event
newp = p - freqloss
debugprint(" Loss occurred at walk time " + str(new_walk_time) + " yielding new frequency " + str(newp))
return sim_walk(node, newp, walk_time=new_walk_time, \
time_until_force=new_time_until_force)
def sim_walk(gtree, snode, gnode, p, s_walk_time=0.0, g_walk_time=0.0, \
time_until_force=forcetime, eventlog=[]):
### Most of the variables are obvious from descriptions in sim_tree or similar.
### eventlog is a log of events along the gtree branch; each entry has the form
### (time_on_branch, event_type, frequency, species_node),
### where 0.0 <= time_on_branch <= branch_node.dist
### event_type is one of {'extinction', 'frequency', 'speciation',
### duplication', 'loss', 'root', 'gene'}, where 'root' is a unique event
### not added during the sim_walk process
### frequency is the branch frequency at the event time
### species_node is the name of the node of the species tree branch
### in which the event occurs
if p <= 0.0:
## EXTINCTION EVENT
# gnode is 'parent' of extinct node
# create new_gnode
new_gnode = treelib.TreeNode(gtree.new_name())
new_gnode.dist = g_walk_time
# set new_gnode's frequency
new_gnode.data['freq'] = 0.0
gtree.add_child(gnode, new_gnode)
# add extinction event to the event log
ext_event = (g_walk_time, 'extinction', 0.0, snode.name)
eventlog.append(ext_event)
# set new_gnode's event log
new_gnode.data['log'] = eventlog
eventlog = [] # should have no effect; added for debugging on 18 Oct 2010
else: # put everything else in this block to avoid using returns
p = min(p, 1.0) # sanity check
eff_dr = dr * p # * popsize #??
eff_lr = lr * p # * popsize #??
eff_bothr = eff_dr + eff_lr
event_time = stats.exponentialvariate(eff_bothr)
remaining_s_dist = snode.dist - s_walk_time
if event_time >= min(time_until_force, remaining_s_dist):
# do not process D/L event; determine whether at force or speciation
if time_until_force < remaining_s_dist:
## FREQUENCY UPDATE EVENT
# sample a new frequency (note scaling to years from myr) # edit: not any more
newp = coal.sample_freq_CDF(p, popsize, forcetime) # * 1e6)
# TODO: if we decide not to reset time_until_force at
# speciation events, the newp generation will need to be
# altered in some form (probably using a new variable)
# update walk times
new_s_walk_time = s_walk_time + time_until_force
new_g_walk_time = g_walk_time + time_until_force
# add frequency event to event log
freq_event = (new_g_walk_time, 'frequency', newp, snode.name)
eventlog.append(freq_event)
# continue the walk with a reset forcetime
sim_walk(gtree, snode, gnode, newp, \
s_walk_time=new_s_walk_time, \
g_walk_time=new_g_walk_time, \
eventlog=eventlog)
eventlog = [] # should have no effect; debug add on 18 Oct 2010
else:
## SPECIATION EVENT
# separate into separate root, non-root speciations
# if gnode.parent: # gnode not the root
if gnode.data['log'][-1][1] != 'root':
# sample a new frequency (note scaling to years from myr) # edit: not any more
newp = coal.sample_freq_CDF(p, popsize, remaining_s_dist) # * 1e6)
# create new_gnode for this event
new_gnode = treelib.TreeNode(gtree.new_name())
new_g_walk_time = g_walk_time + remaining_s_dist
new_gnode.dist = new_g_walk_time
# set new node's frequency
new_gnode.data['freq'] = newp
gtree.add_child(gnode, new_gnode)
# add speciation event to event log and set the new node's log
if snode.is_leaf():
gene_event = (new_g_walk_time, 'gene', newp, snode.name)
eventlog.append(gene_event)
new_gnode.data['log'] = eventlog
# end of walk on species branch
eventlog = [] # should have no effect; debug add on 18 Oct 2010
else:
spec_event = (new_g_walk_time, 'speciation', newp, snode.name)
eventlog.append(spec_event)
new_gnode.data['log'] = eventlog
for schild in snode.children:
sim_walk(gtree, schild, new_gnode, newp, eventlog=[])
# TODO: if we decide not to reset time_until_force at
# speciation events, this sim_walk call will need updating
eventlog = [] # should have no effect; debug add on 18 Oct 2010
else: # gnode is the root
spec_event = (0.0, 'speciation', p, snode.name)
eventlog = gnode.data['log']
eventlog.append(spec_event)
gnode.data['log'] = eventlog
# ### debug print
# print
# print 'adding: ', eventlog
# ### end debug
for schild in snode.children:
sim_walk(gtree, schild, gnode, p, eventlog=[])
eventlog = [] # should have no effect; debug add on 18 Oct 2010
else:
# process D/L event
# no WF updates for these events (modelling decision)
new_s_walk_time = s_walk_time + event_time
new_g_walk_time = g_walk_time + event_time
new_time_until_force = time_until_force - event_time
if event_is_dup(eff_dr, eff_bothr):
## DUPLICATION EVENT
# create a node new_gnode for the duplication event
new_gnode = treelib.TreeNode(gtree.new_name())
new_gnode.dist = new_g_walk_time
# set new node's frequency
new_gnode.data['freq'] = p
gtree.add_child(gnode, new_gnode)
# add duplication event to event log and set the new node's log
dup_event = (new_g_walk_time, 'duplication', p, snode.name)
eventlog.append(dup_event)
new_gnode.data['log'] = eventlog
# recurse on remainder of original branch
sim_walk(gtree, snode, new_gnode, p, \
s_walk_time=new_s_walk_time, \
time_until_force = new_time_until_force, \
eventlog=[])
# recurse on dup tree with correct starting frequency
sim_walk(gtree, snode, new_gnode, freqdup, \
s_walk_time=new_s_walk_time, \
time_until_force = new_time_until_force, \
eventlog=[(0.0,'daughter',freqdup,snode.name)]) # added for daughter detection
eventlog = [] # should have no effect; debug add on 18 Oct 2010
else:
## LOSS EVENT
newp = max(p - freqloss, 0.0) # sanity check
# add loss event to event log
loss_event = (new_g_walk_time, 'loss', newp, snode.name)
eventlog.append(loss_event)
sim_walk(gtree, snode, gnode, newp, \
s_walk_time=new_s_walk_time, \
g_walk_time=new_g_walk_time, \
time_until_force=new_time_until_force, \
eventlog=eventlog)
eventlog = [] # should have no effect; debug add on 18 Oct 2010
def sim_walk(gtree, snode, gnode, p, s_walk_time=0.0, g_walk_time=0.0, \
time_until_force=forcetime):
# debugprint(" Sim on branch" + str(node.name) + " with frequency " + str(p) + " and walk time " + str(walk_time))
# debugprint(" walking on " + str(gnode.name))
if p <= 0.0:
# gnode is 'parent' of extinct node
# create new_gnode, set data['freq'] = 0.0
# prune at the end
new_gnode = treelib.TreeNode(gtree.new_name())
new_gnode.dist = g_walk_time
new_gnode.data['freq'] = 0.0
gtree.add_child(gnode, new_gnode)
# debugprint(" extinction on " + str(gnode.name))
else: # put everything else in this block to avoid using returns
p = min(p, 1.0) # sanity check
eff_dr = dr * p # * popsize #??
eff_lr = lr * p # * popsize #??
eff_bothr = eff_dr + eff_lr
event_time = stats.exponentialvariate(eff_bothr)
remaining_s_dist = snode.dist - s_walk_time
if event_time >= min(time_until_force, remaining_s_dist):
# do not process D/L event; determine whether at force or speciation
if time_until_force < remaining_s_dist:
# force new frequency
newp = coal.sample_freq_CDF(p, popsize, forcetime * 1e6)
# scale forcetime to years (in myr)
# debugprint(" Forced new frequency: " + str(newp))
## TODO: may wish to log newp in node.data
new_s_walk_time = s_walk_time + time_until_force
new_g_walk_time = g_walk_time + time_until_force
sim_walk(gtree, snode, gnode, newp, \
s_walk_time=new_s_walk_time, \
g_walk_time=new_g_walk_time)
# continue walk with new frequency
# increase walk_times accordingly
# reset time_until_force to forcetime
else:
# speciation event
newp = coal.sample_freq_CDF(p, popsize, remaining_s_dist * 1e6)
# scale remaining time into years (from myr)
new_gnode = treelib.TreeNode(gtree.new_name())
new_gnode.dist = g_walk_time + remaining_s_dist
new_gnode.data['freq'] = newp
# stores frequency of allele at the speciation event
gtree.add_child(gnode, new_gnode)
# debugprint(" Completed branch; new frequency: " + str(newp))
for schild in snode.children:
sim_walk(gtree, schild, new_gnode, newp)
# return # shouldn't be necessary
else:
# process D/L event
# no WF updates for these events (modelling decision)
new_s_walk_time = s_walk_time + event_time
new_g_walk_time = g_walk_time + event_time
new_time_until_force = time_until_force - event_time
if event_is_dup(eff_dr, eff_bothr):
# perform duplication event
new_gnode = treelib.TreeNode(gtree.new_name())
# create a node new_gnode for the duplication event
new_gnode.dist = new_g_walk_time # set dist to dup
new_gnode.data['freq'] = p # set frequency at dup event
# debugprint(" Duplication occurred at walk time " + str(new_walk_time))
gtree.add_child(gnode, new_gnode)
# debugprint(" starting on orig of " + str(new_gnode.name))
sim_walk(gtree, snode, new_gnode, p, \
s_walk_time=new_s_walk_time, \
time_until_force = new_time_until_force)
# recurse on remainder of original branch
# debugprint(" starting on dup of " + str(new_gnode.name))
sim_walk(gtree, snode, new_gnode, freqdup, \
s_walk_time=new_s_walk_time, \
time_until_force = new_time_until_force)
# recurse on dup tree with correct starting frequency
# return
else:
# perform loss event
newp = max(p - freqloss, 0.0) # sanity check
# debugprint(" Loss occurred at walk time " + str(new_walk_time) + " yielding new frequency " + str(newp))
sim_walk(gtree, snode, gnode, newp, \
s_walk_time=new_s_walk_time, \
g_walk_time=new_g_walk_time, \
time_until_force=new_time_until_force)
def sim_walk(gtree, snode, gparent, p,
s_walk_time=0.0, remaining_steptime=steptime,
daughter=False):
"""
eventlog is a log of events along the gtree branch.
Each entry has the form
(time_on_branch, event_type, frequency, species_node),
where
0.0 <= time_on_branch <= branch_node.dist
event_type is one of
{'extinction', 'frequency', 'speciation', duplication',
'loss', 'root', 'gene'},
where 'root' is a unique event not added during the sim_walk process
frequency is the branch frequency at the event time
species_node is the name of the node of the species tree branch in
which the event occurs
"""
# create new node
gnode = treelib.TreeNode(gtree.new_name())
gtree.add_child(gparent, gnode)
gnode.data = {"freq": p,
"log": []}
eventlog = gnode.data["log"]
g_walk_time = 0.0
if daughter:
eventlog.append((0.0, 'daughter', freqdup, snode.name))
# grow this branch, determine next event
event = None
while True:
if p <= 0.0:
event = "extinct"
break
# determine remaing time
remaining_s_dist = snode.dist - s_walk_time
remaining_time = min(remaining_steptime, remaining_s_dist)
# sample next dup/loss event
eff_duprate = duprate * p / freqdup
eff_lossrate = lossrate * p / freqloss
eff_bothrate = eff_duprate + eff_lossrate
event_time = stats.exponentialvariate(eff_bothrate)
# advance times
time_delta = min(event_time, remaining_time)
s_walk_time += time_delta
g_walk_time += time_delta
# sample new frequency
p = coal.sample_freq_CDF(p, popsize, time_delta)
# determine event
if event_time < remaining_time:
# dup/loss occurs
if event_is_dup(eff_duprate, eff_bothrate):
# dup, stop growing
event = "dup"
break
else:
# loss, continue growing
event = "loss"
else:
if remaining_s_dist < remaining_steptime:
# we are at a speciation, stop growing
event = "spec"
break
# process step
if event == "loss":
# LOSS EVENT
p = max(p - freqloss, 0.0)
remaining_steptime -= time_delta
eventlog.append((g_walk_time, 'loss', p, snode.name))
else:
# NEXT TIME STEP
remaining_steptime = steptime
eventlog.append((g_walk_time, 'frequency', p, snode.name))
# process event
if event == "extinct":
# EXTINCTION EVENT (p <= 0)
gnode.dist = g_walk_time
gnode.data['freq'] = 0.0
eventlog.append((g_walk_time, 'extinction', 0.0, snode.name))
elif event == "spec":
# SPECIATION EVENT
gnode.dist = g_walk_time
gnode.data['freq'] = p
# add speciation event to event log and
if snode.is_leaf():
eventlog.append((g_walk_time, 'gene', p, snode.name))
else:
eventlog.append((g_walk_time, 'speciation', p, snode.name))
for schild in snode.children:
sim_walk(gtree, schild, gnode, p)
elif event == "dup":
# DUPLICATION EVENT
gnode.dist = g_walk_time
gnode.data['freq'] = p
eventlog.append((g_walk_time, 'duplication', p, snode.name))
# recurse on mother
sim_walk(gtree, snode, gnode, p,
s_walk_time=s_walk_time,
remaining_steptime=remaining_steptime)
# recurse on daughter
sim_walk(gtree, snode, gnode, freqdup,
s_walk_time=s_walk_time,
remaining_steptime=remaining_steptime,
daughter=True)
else:
raise Exception("unknown event '%s'" % event)