def monophyletic_partition_discordance(tree, taxon_set_partition):
"""
Returns the number of deep coalescences on tree `tree` that would result
if the taxa in `tax_sets` formed K mutually-exclusive monophyletic groups,
where K = len(tax_sets)
`taxon_set_partition` == TaxonSetPartition
"""
tax_sets = taxon_set_partition.subsets()
dc_tree = dataobject.Tree()
dc_tree.taxon_set = dataobject.TaxonSet()
for t in range(len(tax_sets)):
dc_tree.taxon_set.append(dataobject.Taxon(label=str(t)))
def _get_dc_taxon(nd):
for idx, tax_set in enumerate(tax_sets):
if nd.taxon in tax_set:
return dc_tree.taxon_set[idx]
assert "taxon not found in partition: '%s'" % nd.taxon.label
src_dc_map = {}
for snd in tree.postorder_node_iter():
nnd = dataobject.Node()
src_dc_map[snd] = nnd
children = snd.child_nodes()
if len(children) == 0:
nnd.taxon = _get_dc_taxon(snd)
else:
taxa_set = []
for cnd in children:
dc_node = src_dc_map[cnd]
if len(dc_node.child_nodes()) > 1:
nnd.add_child(dc_node)
else:
ctax = dc_node.taxon
if ctax is not None and ctax not in taxa_set:
taxa_set.append(ctax)
del src_dc_map[cnd]
if len(taxa_set) > 1:
for t in taxa_set:
cnd = dataobject.Node()
cnd.taxon = t
nnd.add_child(cnd)
else:
if len(nnd.child_nodes()) == 0:
nnd.taxon = taxa_set[0]
elif len(taxa_set) == 1:
cnd = dataobject.Node()
cnd.taxon = taxa_set[0]
nnd.add_child(cnd)
dc_tree.seed_node = nnd
return len(dc_tree.leaf_nodes()) - len(tax_sets)
def _ncl_taxa_block_to_native(self, ncl_tb):
_LOG.debug("Converting NCL taxa block to native")
_LOG.debug("calling NxsTaxaBlock.GetInstanceIdentifierString()")
tbiid = ncl_tb.GetInstanceIdentifierString()
_LOG.debug("got %s" % tbiid)
taxa_block = self.ncl_taxa_to_native.get(tbiid)
if taxa_block is not None:
return taxa_block
_LOG.debug("calling NxsTaxaBlock.GetAllLabels()")
labels = ncl_tb.GetAllLabels()
_LOG.debug("labels = %s" % ' '.join(labels))
if self._taxa_to_fill is None:
taxa_block = dataobject.TaxonSet(labels)
else:
taxa_block = self._taxa_to_fill
self._taxa_to_fill = None
taxa_block.extend([dataobject.Taxon(label=i) for i in labels])
self.ncl_taxa_to_native[tbiid] = taxa_block
return taxa_block
def constrained_kingman(pop_tree,
gene_tree_list=None,
rng=None,
gene_node_label_func=None,
num_genes_attr='num_genes',
pop_size_attr='pop_size',
decorate_original_tree=False):
"""
Given a population tree, `pop_tree` this will return a *pair of
trees*: a gene tree simulated on this population tree based on
Kingman's n-coalescent, and population tree with the additional
attribute 'gene_nodes' on each node, which is a list of
uncoalesced nodes from the gene tree associated with the given
node from the population tree.
`pop_tree` should be a DendroPy Tree object or an object
of a class derived from this with the following attribute
`num_genes` -- the number of gene samples from each population in the
present. Each edge on the tree should also have the attribute
`pop_size_attr` is the attribute name of the edges of `pop_tree` that
specify the population size. By default it is `pop_size`. The should
specify the effective *haploid* population size; i.e., number of gene
in the population: 2 * N in a diploid population of N individuals,
or N in a haploid population of N individuals.
If `pop_size` is 1 or 0 or None, then the edge lengths of `pop_tree` is
taken to be in haploid population units; i.e. where 1 unit equals 2N
generations for a diploid population of size N, or N generations for a
haploid population of size N. Otherwise the edge lengths of `pop_tree` is
taken to be in generations.
If `gene_tree_list` is given, then the gene tree is added to the
tree block, and the tree block's taxa block will be used to manage
the gene tree's `taxa`.
`gene_node_label_func` is a function that takes two arguments (a string
and an integer, respectively, where the string is the containing species
taxon label and the integer is the gene index) and returns a label for
the corresponding the gene node.
if `decorate_original_tree` is True, then the list of uncoalesced nodes at
each node of the population tree is added to the original (input) population
tree instead of a copy.
Note that this function does very much the same thing as `contained_coalescent()`,
but provides a very different API.
"""
# get our random number generator
if rng is None:
rng = GLOBAL_RNG # use the global rng by default
if gene_tree_list is not None:
gtaxa = gene_tree_list.taxon_set
else:
gtaxa = dataobject.TaxonSet()
if gene_node_label_func is None:
gene_node_label_func = lambda x, y: "%s_%02d" % (x, y)
# we create a set of gene nodes for each leaf node on the population
# tree, and associate those gene nodes to the leaf by assignment
# of 'taxon'.
for leaf_count, leaf in enumerate(pop_tree.leaf_iter()):
gene_nodes = []
for gene_count in range(getattr(leaf, num_genes_attr)):
gene_node = dataobject.Node()
gene_node.taxon = gtaxa.require_taxon(
label=gene_node_label_func(leaf.taxon.label, gene_count + 1))
gene_nodes.append(gene_node)
leaf.gene_nodes = gene_nodes
# We iterate through the edges of the population tree in post-order,
# i.e., visiting child edges before we visit parent edges. For
# each edge visited, we take the genes found in the child nodes,
# and run the coalescent simulation on them attacheded by the length
# of the edge. Any genes that have not yet coalesced at the end of
# this period are added to the genes of the tail (parent) node of
# the edge.
if decorate_original_tree:
working_poptree = pop_tree
else:
# start with a new (deep) copy of the population tree so as to not
# to change the original tree
working_poptree = copy.deepcopy(pop_tree)
# start with a new tree
gene_tree = dataobject.Tree()
gene_tree.taxon_set = gtaxa
for edge in working_poptree.postorder_edge_iter():
# if mrca root, run unconstrained coalescent
if edge.head_node.parent_node is None:
if len(edge.head_node.gene_nodes) > 1:
final = coalescent.coalesce(nodes=edge.head_node.gene_nodes,
pop_size=pop_size,
period=None,
rng=rng)
else:
final = edge.head_node.gene_nodes
gene_tree.seed_node = final[0]
else:
if hasattr(edge, pop_size_attr):
pop_size = getattr(edge, pop_size_attr)
else:
# this means all our time will be in population units
pop_size = 1
uncoal = coalescent.coalesce(nodes=edge.head_node.gene_nodes,
pop_size=pop_size,
period=edge.length,
rng=rng)
if not hasattr(edge.tail_node, 'gene_nodes'):
edge.tail_node.gene_nodes = []
edge.tail_node.gene_nodes.extend(uncoal)
gene_tree.is_rooted = True
if gene_tree_list is not None:
gene_tree_list.append(gene_tree)
return gene_tree, working_poptree
else:
return gene_tree, working_poptree
def birth_death(birth_rate,
death_rate,
birth_rate_sd=0.0,
death_rate_sd=0.0,
**kwargs):
"""
Returns a birth-death tree with birth rate specified by `birth_rate`, and
death rate specified by `death_rate`, with edge lengths in continuous (real)
units.
`birth_rate_sd` is the standard deviation of the normally-distributed mutation
added to the birth rate as it is inherited by daughter nodes; if 0, birth
rate does not evolve on the tree.
`death_rate_sd` is the standard deviation of the normally-distributed mutation
added to the death rate as it is inherited by daughter nodes; if 0, death
rate does not evolve on the tree.
Tree growth is controlled by one or more of the following arguments, of which
at least one must be specified:
- If `ntax` is given as a keyword argument, tree is grown until the number of
tips == ntax.
- If `taxon_set` is given as a keyword argument, tree is grown until the
number of tips == len(taxon_set), and the taxa are assigned randomly to the
tips.
- If 'max_time' is given as a keyword argument, tree is grown for
a maximum of `max_time`.
- If `gsa_ntax` is given then the tree will be simulated up to this number of
tips (or 0 tips), then a tree will be randomly selected from the
intervals which corresond to times at which the tree had exactly `ntax`
leaves (or len(taxon_set) tips). This allows for simulations according to
the "General Sampling Approach" of [citeHartmannWS2010]_
If more than one of the above is given, then tree growth will terminate when
*any* of the termination conditions (i.e., number of tips == `ntax`, or number
of tips == len(taxon_set) or maximum time = `max_time`) are met.
Also accepts a Tree object (with valid branch lengths) as an argument passed
using the keyword `tree`: if given, then this tree will be used; otherwise
a new one will be created.
If `assign_taxa` is False, then taxa will *not* be assigned to the tips;
otherwise (default), taxa will be assigned. If `taxon_set` is given
(`tree.taxon_set`, if `tree` is given), and the final number of tips on the
tree after the termination condition is reached is less then the number of
taxa in `taxon_set` (as will be the case, for example, when
`ntax` < len(`taxon_set`)), then a random subset of taxa in `taxon_set` will
be assigned to the tips of tree. If the number of tips is more than the number
of taxa in the `taxon_set`, new Taxon objects will be created and added
to the `taxon_set` if the keyword argument `create_required_taxa` is not given as
False.
Under some conditions, it is possible for all lineages on a tree to go extinct.
In this case, if the keyword argument `repeat_until_success` is `True` (the
default), then a new branching process is initiated.
If `False` (default), then a TreeSimTotalExtinctionException is raised.
A Random() object or equivalent can be passed using the `rng` keyword;
otherwise GLOBAL_RNG is used.
.. [citeHartmannWS2010] Hartmann, Wong, and Stadler "Sampling Trees from Evolutionary Models" Systematic Biology. 2010. 59(4). 465-476
"""
target_num_taxa = kwargs.get('ntax')
max_time = kwargs.get('max_time')
taxon_set = kwargs.get('taxon_set')
if (target_num_taxa is None) and (taxon_set is not None):
target_num_taxa = len(taxon_set)
elif taxon_set is None:
taxon_set = dataobject.TaxonSet()
gsa_ntax = kwargs.get('gsa_ntax')
terminate_at_full_tree = False
if target_num_taxa is None:
if gsa_ntax is not None:
raise ValueError(
"When 'gsa_ntax' is used, either 'ntax' or 'taxon_set' must be used"
)
if max_time is None:
raise ValueError(
"At least one of the following must be specified: 'ntax', 'taxon_set', or 'max_time'"
)
else:
if gsa_ntax is None:
terminate_at_full_tree = True
gsa_ntax = 1 + target_num_taxa
elif gsa_ntax < target_num_taxa:
raise ValueError("gsa_ntax must be greater than target_num_taxa")
repeat_until_success = kwargs.get('repeat_until_success', True)
rng = kwargs.get('rng', GLOBAL_RNG)
# initialize tree
if "tree" in kwargs:
tree = kwargs['tree']
if "taxon_set" in kwargs and kwargs['taxon_set'] is not tree.taxon_set:
raise ValueError("Cannot specify both `tree` and `taxon_set`")
else:
tree = dataobject.Tree(taxon_set=taxon_set)
tree.is_rooted = True
tree.seed_node.edge.length = 0.0
tree.seed_node.birth_rate = birth_rate
tree.seed_node.death_rate = death_rate
# grow tree
leaf_nodes = tree.leaf_nodes()
#_LOG.debug("Will generate a tree with no more than %s leaves to get a tree of %s leaves" % (str(gsa_ntax), str(target_num_taxa)))
curr_num_leaves = len(leaf_nodes)
total_time = 0
# for the GSA simulations targetted_time_slices is a list of tuple
# the first element in the tuple is the duration of the amount
# that the simulation spent at the (targetted) number of taxa
# and a list of edge information. The list of edge information includes
# a list of terminal edges in the tree and the length for that edge
# that marks the beginning of the time slice that corresponds to the
# targetted number of taxa.
targetted_time_slices = []
extinct_tips = []
while True:
if gsa_ntax is None:
assert (max_time is not None)
if total_time >= max_time:
break
elif curr_num_leaves >= gsa_ntax:
break
# get vector of birth/death probabilities, and
# associate with nodes/events
event_rates = []
event_nodes = []
for nd in leaf_nodes:
if not hasattr(nd, 'birth_rate'):
nd.birth_rate = birth_rate
if not hasattr(nd, 'death_rate'):
nd.death_rate = death_rate
event_rates.append(nd.birth_rate)
event_nodes.append((nd, True)) # birth event = True
event_rates.append(nd.death_rate)
event_nodes.append((nd, False)) # birth event = False; i.e. death
# get total probability of any birth/death
rate_of_any_event = sum(event_rates)
# waiting time based on above probability
#_LOG.debug("rate_of_any_event = %f" % (rate_of_any_event))
waiting_time = rng.expovariate(rate_of_any_event)
#_LOG.debug("Drew waiting time of %f from hazard parameter of %f" % (waiting_time, rate_of_any_event))
if (gsa_ntax is not None) and (curr_num_leaves == target_num_taxa):
edge_and_start_length = []
for nd in leaf_nodes:
e = nd.edge
edge_and_start_length.append((e, e.length))
targetted_time_slices.append((waiting_time, edge_and_start_length))
#_LOG.debug("Recording slice with %d edges" % len(edge_and_start_length))
if terminate_at_full_tree:
break
# add waiting time to nodes
for nd in leaf_nodes:
try:
nd.edge.length += waiting_time
except TypeError:
nd.edge.length = waiting_time
#_LOG.debug("Next waiting_time = %f" % waiting_time)
total_time += waiting_time
# if event occurs within time constraints
if max_time is None or total_time <= max_time:
# normalize probability
for i in xrange(len(event_rates)):
event_rates[i] = event_rates[i] / rate_of_any_event
# select node/event and process
nd, birth_event = probability.weighted_choice(event_nodes,
event_rates,
rng=rng)
leaf_nodes.remove(nd)
curr_num_leaves -= 1
if birth_event:
#_LOG.debug("Speciation")
c1 = nd.new_child()
c2 = nd.new_child()
c1.edge.length = 0
c2.edge.length = 0
c1.birth_rate = nd.birth_rate + rng.gauss(0, birth_rate_sd)
c1.death_rate = nd.death_rate + rng.gauss(0, death_rate_sd)
c2.birth_rate = nd.birth_rate + rng.gauss(0, birth_rate_sd)
c2.death_rate = nd.death_rate + rng.gauss(0, death_rate_sd)
leaf_nodes.append(c1)
leaf_nodes.append(c2)
curr_num_leaves += 2
else:
#_LOG.debug("Extinction")
if curr_num_leaves > 0:
#_LOG.debug("Will delete " + str(id(nd)) + " with parent = " + str(id(nd.parent_node)))
extinct_tips.append(nd)
else:
if (gsa_ntax is not None):
if (len(targetted_time_slices) > 0):
break
if not repeat_until_success:
raise TreeSimTotalExtinctionException()
# We are going to basically restart the simulation because the tree has gone extinct (without reaching the specified ntax)
leaf_nodes = [tree.seed_node]
curr_num_leaves = 1
for nd in tree.seed_node.child_nodes():
treemanip.prune_subtree(tree,
nd,
delete_outdegree_one=False)
extinct_tips = []
total_time = 0
assert (curr_num_leaves == len(leaf_nodes))
#_LOG.debug("Current tree \n%s" % (tree.as_ascii_plot(plot_metric='length', show_internal_node_labels=True)))
#tree._debug_tree_is_valid()
#_LOG.debug("Terminated with %d leaves (%d, %d according to len(leaf_nodes))" % (curr_num_leaves, len(leaf_nodes), len(tree.leaf_nodes())))
if gsa_ntax is not None:
total_duration_at_target_n_tax = 0.0
for i in targetted_time_slices:
total_duration_at_target_n_tax += i[0]
r = rng.random() * total_duration_at_target_n_tax
#_LOG.debug("Selected rng = %f out of (0, %f)" % (r, total_duration_at_target_n_tax))
selected_slice = None
for n, i in enumerate(targetted_time_slices):
r -= i[0]
if r < 0.0:
selected_slice = i
assert (selected_slice is not None)
#_LOG.debug("Selected time slice index %d" % n)
edges_at_slice = selected_slice[1]
last_waiting_time = selected_slice[0]
for e, prev_length in edges_at_slice:
daughter_nd = e.head_node
for nd in daughter_nd.child_nodes():
treemanip.prune_subtree(tree, nd, delete_outdegree_one=False)
#_LOG.debug("After pruning %s:\n%s" % (str(id(nd)), tree.as_ascii_plot(plot_metric='length', show_internal_node_labels=True)))
try:
extinct_tips.remove(nd)
except:
pass
try:
extinct_tips.remove(daughter_nd)
except:
pass
e.length = prev_length + last_waiting_time
# tree._debug_tree_is_valid()
# for nd in extinct_tips:
# _LOG.debug("Will be deleting " + str(id(nd)))
for nd in extinct_tips:
bef = len(tree.leaf_nodes())
while (nd.parent_node is not None) and (len(
nd.parent_node.child_nodes()) == 1):
_LOG.debug("Will be pruning %d rather than its only child (%d)" %
(id(nd.parent_node), id(nd)))
nd = nd.parent_node
# _LOG.debug("Deleting " + str(nd.__dict__) + '\n' + str(nd.edge.__dict__))
# for n, pnd in enumerate(tree.postorder_node_iter()):
# _LOG.debug("%d %s" % (n, repr(pnd)))
# _LOG.debug("Before prune of %s:\n%s" % (str(id(nd)), tree.as_ascii_plot(plot_metric='length', show_internal_node_labels=True)))
if nd.parent_node:
treemanip.prune_subtree(tree, nd, delete_outdegree_one=False)
_LOG.debug("After prune (went from %d to %d leaves):\n%s" %
(bef, len(tree.leaf_nodes()),
tree.as_ascii_plot(plot_metric='length',
show_internal_node_labels=True)))
# _LOG.debug("Deleted " + str(nd.__dict__))
# for n, pnd in enumerate(tree.postorder_node_iter()):
# _LOG.debug("%d %s" % (n, repr(pnd)))
# tree._debug_tree_is_valid()
tree.delete_outdegree_one_nodes()
# tree._debug_tree_is_valid()
# _LOG.debug("After deg2suppression:\n%s" % (tree.as_ascii_plot(plot_metric='length', show_internal_node_labels=True)))
if kwargs.get("assign_taxa", True):
tree.randomly_assign_taxa(create_required_taxa=True, rng=rng)
# return
return tree
def discrete_birth_death(birth_rate,
death_rate,
birth_rate_sd=0.0,
death_rate_sd=0.0,
**kwargs):
"""
Returns a birth-death tree with birth rate specified by `birth_rate`, and
death rate specified by `death_rate`, with edge lengths in discrete (integer)
units.
`birth_rate_sd` is the standard deviation of the normally-distributed mutation
added to the birth rate as it is inherited by daughter nodes; if 0, birth
rate does not evolve on the tree.
`death_rate_sd` is the standard deviation of the normally-distributed mutation
added to the death rate as it is inherited by daughter nodes; if 0, death
rate does not evolve on the tree.
Tree growth is controlled by one or more of the following arguments, of which
at least one must be specified:
- If `ntax` is given as a keyword argument, tree is grown until the number of
tips == ntax.
- If `taxon_set` is given as a keyword argument, tree is grown until the
number of tips == len(taxon_set), and the taxa are assigned randomly to the
tips.
- If 'max_time' is given as a keyword argument, tree is grown for `max_time`
number of generations.
If more than one of the above is given, then tree growth will terminate when
*any* of the termination conditions (i.e., number of tips == `ntax`, or number
of tips == len(taxon_set) or number of generations = `max_time`) are met.
Also accepts a Tree object (with valid branch lengths) as an argument passed
using the keyword `tree`: if given, then this tree will be used; otherwise
a new one will be created.
If `assign_taxa` is False, then taxa will *not* be assigned to the tips;
otherwise (default), taxa will be assigned. If `taxon_set` is given
(`tree.taxon_set`, if `tree` is given), and the final number of tips on the
tree after the termination condition is reached is less then the number of
taxa in `taxon_set` (as will be the case, for example, when
`ntax` < len(`taxon_set`)), then a random subset of taxa in `taxon_set` will
be assigned to the tips of tree. If the number of tips is more than the number
of taxa in the `taxon_set`, new Taxon objects will be created and added
to the `taxon_set` if the keyword argument `create_required_taxa` is not given as
False.
Under some conditions, it is possible for all lineages on a tree to go extinct.
In this case, if the keyword argument `repeat_until_success` is `True`, then a new
branching process is initiated.
If `False` (default), then a TreeSimTotalExtinctionException is raised.
A Random() object or equivalent can be passed using the `rng` keyword;
otherwise GLOBAL_RNG is used.
"""
if 'ntax' not in kwargs \
and 'taxon_set' not in kwargs \
and 'max_time' not in kwargs:
raise ValueError(
"At least one of the following must be specified: 'ntax', 'taxon_set', or 'max_time'"
)
target_num_taxa = None
taxon_set = None
target_num_gens = kwargs.get('max_time', None)
if 'taxon_set' in kwargs:
taxon_set = kwargs.get('taxon_set')
target_num_taxa = kwargs.get('ntax', len(taxon_set))
elif 'ntax' in kwargs:
target_num_taxa = kwargs['ntax']
if taxon_set is None:
taxon_set = dataobject.TaxonSet()
repeat_until_success = kwargs.get('repeat_until_success', False)
rng = kwargs.get('rng', GLOBAL_RNG)
# grow tree
if "tree" in kwargs:
tree = kwargs['tree']
if "taxon_set" in kwargs and kwargs['taxon_set'] is not tree.taxon_set:
raise ValueError("Cannot specify both `tree` and `taxon_set`")
else:
tree = dataobject.Tree(taxon_set=taxon_set)
tree.is_rooted = True
tree.seed_node.edge.length = 0
tree.seed_node.birth_rate = birth_rate
tree.seed_node.death_rate = death_rate
leaf_nodes = tree.leaf_nodes()
num_gens = 0
while (target_num_taxa is None or len(leaf_nodes) < target_num_taxa) \
and (target_num_gens is None or num_gens < target_num_gens):
for nd in leaf_nodes:
if not hasattr(nd, 'birth_rate'):
nd.birth_rate = birth_rate
if not hasattr(nd, 'death_rate'):
nd.death_rate = death_rate
try:
nd.edge.length += 1
except TypeError:
nd.edge.length = 1
u = rng.uniform(0, 1)
if u < nd.birth_rate:
c1 = nd.new_child()
c2 = nd.new_child()
c1.edge.length = 0
c2.edge.length = 0
c1.birth_rate = nd.birth_rate + rng.gauss(0, birth_rate_sd)
c1.death_rate = nd.death_rate + rng.gauss(0, death_rate_sd)
c2.birth_rate = nd.birth_rate + rng.gauss(0, birth_rate_sd)
c2.death_rate = nd.death_rate + rng.gauss(0, death_rate_sd)
elif u > nd.birth_rate and u < (nd.birth_rate + nd.death_rate):
if nd is not tree.seed_node:
treemanip.prune_subtree(tree, nd)
elif not repeat_until_success:
# all lineages are extinct: raise exception
raise TreeSimTotalExtinctionException()
else:
# all lineages are extinct: repeat
num_gens = 0
num_gens += 1
leaf_nodes = tree.leaf_nodes()
# If termination condition specified by ntax or taxon_set, then the last
# split will have a daughter edges of length == 0;
# so we continue growing the edges until the next birth/death event *or*
# the max number of generations condition is given and met
gens_to_add = 0
while (target_num_gens is None or num_gens < target_num_gens):
u = rng.uniform(0, 1)
if u < (birth_rate + death_rate):
break
gens_to_add += 1
for nd in tree.leaf_nodes():
nd.edge.length += gens_to_add
if kwargs.get("assign_taxa", True):
tree.randomly_assign_taxa(create_required_taxa=True, rng=rng)
# return
return tree
def tree_from_token_stream(stream_tokenizer, **kwargs):
"""
Processes a (SINGLE) TREE statement. Assumes that the input stream is
located at the beginning of the statement (i.e., the first non-comment
token should be the opening parenthesis of the tree definition).
str_to_taxon kwarg (if used) must supply the StrToTaxon interface).
"""
translate_dict = kwargs.get("translate_dict", None)
encode_splits = kwargs.get("encode_splits", False)
rooting_interpreter = kwargs.get("rooting_interpreter",
RootingInterpreter(**kwargs))
finish_node_func = kwargs.get("finish_node_func", None)
edge_len_type = kwargs.get("edge_len_type", float)
taxon_set = kwargs.get("taxon_set", None)
suppress_internal_node_taxa = kwargs.get("suppress_internal_node_taxa",
False)
store_tree_weights = kwargs.get("store_tree_weights", False)
extract_comment_metadata = kwargs.get('extract_comment_metadata', False)
case_sensitive_taxon_labels = kwargs.get('case_sensitive_taxon_labels',
False)
allow_repeated_use = kwargs.get('allow_repeated_use', False)
stream_tokenizer_extract_comment_metadata_setting = stream_tokenizer.extract_comment_metadata
stream_tokenizer.extract_comment_metadata = extract_comment_metadata
if taxon_set is None:
taxon_set = dataobject.TaxonSet()
tree = dataobject.Tree(taxon_set=taxon_set)
stream_tokenizer.tree_rooting_comment = None # clear previous comment
stream_tokenizer.clear_comment_metadata()
token = stream_tokenizer.read_next_token()
if not token:
return None
tree.is_rooted = rooting_interpreter.interpret_as_rooted(
stream_tokenizer.tree_rooting_comment)
# if stream_tokenizer.tree_rooting_comment is not None:
# tree.is_rooted = rooting_interpreter.interpret_as_rooted(stream_tokenizer.tree_rooting_comment)
# elif rooting_interpreter.interpret_as_rooted(stream_tokenizer.tree_rooting_comment):
# tree_is_rooted = True
if store_tree_weights and stream_tokenizer.tree_weight_comment is not None:
try:
weight_expression = stream_tokenizer.tree_weight_comment.split(
' ')[1]
tree.weight = eval("/".join(
["float(%s)" % cv for cv in weight_expression.split('/')]))
except IndexError:
pass
except ValueError:
pass
stream_tokenizer.tree_weight_comment = None
if encode_splits:
if len(taxon_set) == 0:
raise Exception("When encoding splits on a tree as it is being parsed, a "
+ "fully pre-populated TaxonSet object must be specified using the 'taxon_set' keyword " \
+ "to avoid taxon/split bitmask values changing as new Taxon objects are created " \
+ "and added to the TaxonSet.")
if tree.is_rooted:
tree.split_edges = {}
else:
atb = taxon_set.all_taxa_bitmask()
d = containers.NormalizedBitmaskDict(mask=atb)
tree.split_edges = d
split_map = tree.split_edges
stt = kwargs.get('str_to_taxon')
if stt is None:
stt = StrToTaxon(taxon_set,
translate_dict,
allow_repeated_use=allow_repeated_use,
case_sensitive=case_sensitive_taxon_labels)
tree.seed_node = dataobject.Node()
curr_node = tree.seed_node
if encode_splits:
curr_node.edge.split_bitmask = 0L
### NHX format support ###
def store_node_comments(active_node):
if stream_tokenizer.comments:
active_node.comments.extend(stream_tokenizer.comments)
def store_comment_metadata(target):
if extract_comment_metadata:
if stream_tokenizer.has_comment_metadata():
comment_metadata = stream_tokenizer.comment_metadata
try:
target.comment_metadata.update(comment_metadata)
except AttributeError:
target.comment_metadata = comment_metadata
stream_tokenizer.clear_comment_metadata()
elif not hasattr(target, "comment_metadata"):
target.comment_metadata = {}
# store and clear comments
tree.comments = stream_tokenizer.comments
stream_tokenizer.clear_comments()
store_comment_metadata(tree)
while True:
if not token or token == ';':
if curr_node is not tree.seed_node:
raise stream_tokenizer.data_format_error(
"Unbalanced parentheses -- not enough ')' characters found in tree description"
)
if encode_splits:
split_map[curr_node.edge.split_bitmask] = curr_node.edge
break
if token == '(':
if not curr_node.parent_node:
if curr_node.child_nodes():
raise stream_tokenizer.data_format_error(
"Unexpected '(' after the tree description. Expecting a label for the root or a ;"
)
tmp_node = dataobject.Node()
if encode_splits:
tmp_node.edge.split_bitmask = 0L
curr_node.add_child(tmp_node)
curr_node = tmp_node
token = stream_tokenizer.read_next_token()
store_node_comments(curr_node)
store_comment_metadata(curr_node)
elif token == ',':
tmp_node = dataobject.Node()
if curr_node.is_leaf() and not curr_node.taxon:
# curr_node.taxon = taxon_set.Taxon(oid="UNAMED_" + str(id(curr_node)), label='')
# taxon_set.add(curr_node.taxon)
raise stream_tokenizer.data_format_error(
"Missing taxon specifier in a tree -- found either a '(,' or ',,' construct."
)
p = curr_node.parent_node
if not p:
raise stream_tokenizer.data_format_error(
"Comma found one the 'outside' of a newick tree description"
)
if encode_splits:
tmp_node.edge.split_bitmask = 0L
e = curr_node.edge
u = e.split_bitmask
split_map[u] = e
p.edge.split_bitmask |= u
if finish_node_func is not None:
finish_node_func(curr_node, tree)
p.add_child(tmp_node)
curr_node = tmp_node
token = stream_tokenizer.read_next_token()
store_node_comments(curr_node)
store_comment_metadata(curr_node)
else:
if token == ')':
if curr_node.is_leaf() and not curr_node.taxon:
raise stream_tokenizer.data_format_error(
"Missing taxon specifier in a tree -- found either a '(,' or ',,' construct."
)
p = curr_node.parent_node
if not p:
raise stream_tokenizer.data_format_error(
"Unbalanced parentheses -- too many ')' characters found in tree description"
)
if encode_splits:
e = curr_node.edge
u = e.split_bitmask
p.edge.split_bitmask |= u
split_map[u] = curr_node.edge
if finish_node_func is not None:
finish_node_func(curr_node, tree)
curr_node = p
else:
is_leaf = curr_node.is_leaf()
if is_leaf:
if curr_node.taxon:
raise stream_tokenizer.data_format_error(
"Multiple labels found for the same leaf (taxon '%s' and label '%s')"
% (str(curr_node.taxon), token))
try:
t = stt_require_taxon(stt, label=token)
except StrToTaxon.MultipleTaxonUseError, e:
raise stream_tokenizer.data_format_error(e.msg)
else:
if curr_node.label:
raise stream_tokenizer.data_format_error(
"Multiple labels found for the same leaf (taxon '%s' and label '%s')"
% (curr_node.label, token))
if suppress_internal_node_taxa:
t = None
else:
try:
t = stt.get_taxon(label=token)
except StrToTaxon.MultipleTaxonUseError, e:
raise stream_tokenizer.data_format_error(e.msg)
def _get_contained_taxon_set(self):
if self._contained_taxon_set is None:
self._contained_taxon_set = dataobject.TaxonSet()
return self._contained_taxon_set