def ms_simulate_wrapper(tree, **kwargs):
no_pops= get_number_of_leaves(tree)
#ms_command, minmaxv=tree_to_ms_command(tree, #TO CHANGE BACK
if kwargs['time_adjust']:
ms_command=time_adjusted_tree_to_ms_command(tree, #TO CHANGE BACK
sample_per_pop=kwargs['sample_per_pop'],
nreps=kwargs['nreps'],
theta=kwargs['theta'],
sites=kwargs['sites'],
recomb_rate=kwargs['recomb_rate'],
leaf_keys=kwargs['full_nodes'],
final_pop_size=kwargs['final_pop_size'])
else:
ms_command=tree_to_ms_command(tree, #TO CHANGE BACK
sample_per_pop=kwargs['sample_per_pop'],
nreps=kwargs['nreps'],
theta=kwargs['theta'],
sites=kwargs['sites'],
recomb_rate=kwargs['recomb_rate'],
leaf_keys=kwargs['full_nodes'])
#kwargs['pks']['minmaxv']=minmaxv #TO CHANGE BACK
#print ms_command
call_ms_string(ms_command, kwargs['ms_file'])
filename_gz=ms_to_treemix3(kwargs['ms_file'],
samples_per_pop=kwargs['sample_per_pop'],
no_pops=no_pops,
n_reps=kwargs['nreps'],
filename2=kwargs['treemix_file'],
nodes=kwargs['full_nodes'])
return filename_gz
def prior(x,
p=0.5,
use_skewed_distr=False,
pks={},
use_uniform_prior=False,
unadmixed_populations=[],
r=0):
tree, add = x
no_leaves = get_number_of_leaves(tree)
admixtures = get_all_admixture_proportions(tree)
if not all(prop >= 0 and prop <= 1 for prop in admixtures):
return -float('inf')
branches = get_all_branch_lengths(tree)
if not all(branch >= 0 for branch in branches):
return -float('inf')
branch_prior = calculate_branch_prior(branches, no_leaves)
no_admix_prior = no_admixes(p, len(admixtures), r=r)
if use_skewed_distr:
admix_prop_prior = linear_admixture_proportions(admixtures)
else:
admix_prop_prior = 0
if use_uniform_prior:
top_prior = uniform_topological_prior_function(tree)
else:
top_prior = topological_prior(tree)
if unadmixed_populations:
if illegal_admixtures(unadmixed_populations, tree):
return -float('inf')
logsum = branch_prior + no_admix_prior + admix_prop_prior + top_prior - add
pks['branch_prior'] = branch_prior
pks['no_admix_prior'] = no_admix_prior
pks['admix_prop_prior'] = admix_prop_prior
pks['top_prior'] = top_prior
return logsum
def get_rank(tree, add_one_column=True):
'''
the rank of a tree is the rank of the coefficient matrix
'''
coef,_,_=make_coefficient_matrix(tree)
if add_one_column:
coef=insert(coef, coef.shape[1], 1, axis=1)
n=get_number_of_leaves(tree)
r=matrix_rank(coef)
return r
def rescale(tree, sigma=0.01, pks={}):
n = get_number_of_leaves(tree)
k = get_number_of_admixes(tree)
pks['rescale_adap_param'] = sigma
new_tree = deepcopy(tree)
updat = updater(sigma / sqrt(2 * n - 2 + 4 * k))
new_tree = update_all_branches(new_tree, updat)
if new_tree is None:
return tree, 1, 0 #rejecting by setting backward jump probability to 0.
return new_tree, 1, 1
def get_numbers(tree, add_one_column=True):
'''
the rank of a tree is the rank of the coefficient matrix
'''
n=get_number_of_leaves(tree)
max_rank=n*(n+1)/2
min_rank=2*n-1
coef,_,_=make_coefficient_matrix(tree)
if add_one_column:
coef=insert(coef, coef.shape[1], 1, axis=1)
r=matrix_rank(coef)
return min_rank, r, max_rank
def generate_phylogeny(size,
admixes=None,
p=0.5,
leaf_nodes=None,
skewed_admixture_prior=False):
if admixes is None:
admixes = simulate_number_of_admixture_events(p)
tree = generate_admix_topology(size, admixes, leaf_nodes)
n = get_number_of_leaves(tree)
factor = get_admixture_factor(n, admixes)
for node in tree.values():
node = _resimulate(node, factor, skewed_admixture_prior)
return tree
def add_sadmixes(tree, final_no_sadmixes):
k=get_number_of_admixes(tree)
n=get_number_of_leaves(tree)
maxrank=n*(n+1)/2
#print pretty_string(tree)
for i in range(k,final_no_sadmixes):
pops=get_rank(tree)
assert pops<maxrank, 'Admixture event number '+str(i+1)+' cant be added because the model is already maxed out'
names=['sad'+str(i)+'a','sad'+str(i)+'b']
candidate_tree,_,_=addadmix(tree,new_node_names=names, preserve_root_distance=False)
candidate_pops=get_rank(candidate_tree)
#print 'cand_res', candidate_pops, pops
while candidate_pops<=pops:
#print 'rejected addition'
candidate_tree,_,_=addadmix(tree,new_node_names=names, preserve_root_distance=False)
candidate_pops=get_rank(candidate_tree)
#print 'cand_res', candidate_pops, pops
tree=candidate_tree
#print '----------'
#print pretty_string(tree)
return tree
def initialize_posterior2(emp_cov=None,
true_tree=None,
M=None,
use_skewed_distr=False,
p=0.5,
rescale=False,
model_choice=[
'empirical covariance', 'true tree covariance',
'wishart on true tree covariance',
'empirical covariance on true tree',
'no likelihood'
],
simulate_true_tree=False,
true_tree_no_leaves=None,
true_tree_no_admixes=None,
nodes=None,
simulate_true_tree_with_skewed_prior=False,
reduce_cov=None,
add_outgroup_to_true_tree=False,
reduce_true_tree=False):
if not isinstance(model_choice, basestring):
model_choice = model_choice[0]
if model_choice == 'no likelihood':
return initialize_prior_as_posterior(), {}
if (model_choice == 'true tree covariance'
or model_choice == 'wishart on true tree covariance'
or model_choice == 'empirical covariance on true tree'):
if simulate_true_tree:
true_tree = generate_phylogeny(
true_tree_no_leaves, true_tree_no_admixes, nodes,
simulate_true_tree_with_skewed_prior)
elif isinstance(true_tree, basestring):
if ';' in true_tree: #this means that the true tree is a s_tree
true_tree_s = true_tree
true_tree = identifier_to_tree_clean(true_tree_s)
else:
with open(true_tree, 'r') as f:
true_tree_s = f.readline().rstrip()
true_tree = identifier_to_tree_clean(true_tree_s)
true_tree = Rtree_operations.simple_reorder_the_leaves_after_removal_of_s1(
true_tree)
no_leaves = get_number_of_leaves(true_tree)
no_admixes = get_number_of_admixes(true_tree)
cov = make_covariance(true_tree)
if reduce_cov is not None:
pass
if reduce_true_tree is not None:
true_tree = Rtree_operations.remove_outgroup(
true_tree, reduce_true_tree)
if reduce_true_tree == 's1' or reduce_true_tree == 0:
pass
if emp_cov is not None:
if isinstance(emp_cov, basestring):
pass
if M is None:
M = n_mark(emp_cov)
if rescale:
emp_cov, multiplier = rescale_empirical_covariance(emp_cov)
print 'multiplier is', multiplier
def posterior(x, pks={}):
#print tot_branch_length
prior_value = prior(x, p=p, use_skewed_distr=use_skewed_distr, pks=pks)
if prior_value == -float('inf'):
return -float('inf'), prior_value
likelihood_value = likelihood(x, emp_cov, M=M)
pks['prior'] = prior_value
pks['likelihood'] = likelihood_value
#pks['posterior']=prior_value+likelihood_value
return likelihood_value, prior_value
if rescale:
return posterior, multiplier
return posterior
def uniform_topological_prior_function(tree):
up = uniform_prior(get_number_of_leaves(tree))
return up.probability(tree=tree)
def effective_number_of_admixes(tree):
n=get_number_of_leaves(tree)
Zero_tree=tree_to_0tree(tree)
return get_rank(tree)-get_rank(Zero_tree)
def get_empirical_matrix(stree, factor=1.0, pop_size=20, reps=400):
tree= identifier_to_tree_clean(stree)
ms_command=tree_to_ms_command(scale_tree_copy(tree, factor), pop_size, reps)
#print ms_command
call_ms_string(ms_command, 'tmp.txt')
empirical_covariance=ms_to_treemix2(filename='tmp.txt', samples_per_pop=pop_size, no_pops=get_number_of_leaves(tree), n_reps=reps, filename2='tmp.treemix_in')
return reduce_covariance(empirical_covariance,0)