def generate_contained_trees(
containing_tree,
contained_taxon_namespace=None,
population_size=1,
num_individuals_per_population=4,
num_gene_trees=5,
rng=None):
if contained_taxon_namespace is None:
contained_taxon_namespace = dendropy.TaxonNamespace()
contained_to_containing_map = {}
assert len(containing_tree.taxon_namespace) > 0
for sp_idx, sp_tax in enumerate(containing_tree.taxon_namespace):
for gidx in range(num_individuals_per_population):
glabel = "{sp}_{ind}^{sp}_{ind}".format(sp=sp_tax.label, ind=gidx+1)
# glabel = "{sp}^{sp}_{ind}".format(sp=sp_tax.label, ind=gidx+1)
g = contained_taxon_namespace.require_taxon(label=glabel)
g.population_label = sp_tax.label
contained_to_containing_map[g] = sp_tax
ct = reconcile.ContainingTree(
containing_tree=containing_tree,
contained_taxon_namespace=contained_taxon_namespace,
contained_to_containing_taxon_map=contained_to_containing_map)
gene_trees = dendropy.TreeList(taxon_namespace=contained_taxon_namespace)
for gtidx in range(num_gene_trees):
gt = ct.embed_contained_kingman(
default_pop_size=population_size,
rng=rng)
gene_trees.append(gt)
return gene_trees
def generate_contained_trees(
containing_tree,
contained_taxon_namespace=None,
population_size=1,
total_number_of_individuals=200,
num_gene_trees=5,
rng=None):
if contained_taxon_namespace is None:
contained_taxon_namespace = dendropy.TaxonNamespace()
contained_to_containing_map = {}
assert len(containing_tree.taxon_namespace) > 0
containing_tree = process_containing_tree_for_gene_samples(
containing_tree=containing_tree,
total_number_of_individuals=total_number_of_individuals,
rng=rng)
containing_tree_leaf_nodes = containing_tree.leaf_nodes()
for sp_idx, sp_node in enumerate(containing_tree_leaf_nodes):
sp_tax = sp_node.taxon
for gidx in range(sp_node.num_individuals_sampled):
glabel = "{sp}_{ind}^{sp}".format(sp=sp_tax.label, ind=gidx+1)
# glabel = "{sp}^{sp}_{ind}".format(sp=sp_tax.label, ind=gidx+1)
g = contained_taxon_namespace.require_taxon(label=glabel)
g.population_label = sp_tax.label
contained_to_containing_map[g] = sp_tax
ct = reconcile.ContainingTree(
containing_tree=containing_tree,
contained_taxon_namespace=contained_taxon_namespace,
contained_to_containing_taxon_map=contained_to_containing_map)
gene_trees = dendropy.TreeList(taxon_namespace=contained_taxon_namespace)
for gtidx in range(num_gene_trees):
gt = ct.embed_contained_kingman(
default_pop_size=population_size,
rng=rng)
gene_trees.append(gt)
return containing_tree, gene_trees
def testFittedEdgesDeepCoalCount(self):
for idx, gt in enumerate(self.gene_trees):
gt.encode_bipartitions()
ct = reconcile.ContainingTree(
containing_tree=self.species_tree,
contained_taxon_namespace=self.gene_trees.taxon_namespace,
contained_to_containing_taxon_map=self.
gene_taxon_to_population_taxon_map,
contained_trees=[gt],
fit_containing_edge_lengths=True,
)
dc = ct.num_deep_coalescences()
def testFixedEdgesDeepCoalCount(self):
results = []
for idx, gt in enumerate(self.gene_trees):
ct = reconcile.ContainingTree(
containing_tree=self.species_tree,
contained_taxon_namespace=self.gene_trees.taxon_namespace,
contained_to_containing_taxon_map=self.
gene_taxon_to_population_taxon_map,
contained_trees=[gt],
fit_containing_edge_lengths=False,
)
dc = ct.num_deep_coalescences()
results.append(dc)
## FOR DEBUGGING
# mesqf = pathmap.named_output_stream("ContainingTreeDeepCoalescence_Small_FixedEdges_t%02d_dc%02d.nex" % (idx+1, dc), False)
# with mesqf:
# ct.write_as_mesquite(mesqf)
self.assertEqual(results, self.expected_under_original_brlens)
data=stepwise_tree_str,
schema="newick",
taxon_namespace=containing_taxa)
frag_tree = dendropy.Tree.get(
data=frag_tree_str,
schema="newick",
taxon_namespace=containing_taxa)
# taxon set association
genes_to_species = dendropy.TaxonNamespaceMapping.create_contained_taxon_mapping(
containing_taxon_namespace=containing_taxa,
num_contained=8)
# convert to containing tree
stepwise_tree = reconcile.ContainingTree(stepwise_tree,
contained_taxon_namespace=genes_to_species.domain_taxon_namespace,
contained_to_containing_taxon_map=genes_to_species)
frag_tree = reconcile.ContainingTree(frag_tree,
contained_taxon_namespace=genes_to_species.domain_taxon_namespace,
contained_to_containing_taxon_map=genes_to_species)
# for each rep
for rep in range(num_reps):
gene_tree1 = treesim.contained_coalescent_tree(containing_tree=stepwise_tree,
gene_to_containing_taxon_map=genes_to_species,
default_pop_size=40000)
stepwise_tree.embed_tree(gene_tree1)
gene_tree2 = treesim.contained_coalescent_tree(containing_tree=frag_tree,
gene_to_containing_taxon_map=genes_to_species,
default_pop_size=40000)
frag_tree.embed_tree(gene_tree2)