def is_mesh_subroot_node(bio_ontology, node):
ns, id = bio_ontology.get_ns_id(node)
if ns == 'MESH':
tree_numbers = mesh_client.get_mesh_tree_numbers(id)
if len(tree_numbers) == 1 and '.' not in tree_numbers[0]:
return tree_numbers[0][0]
return None
def add_mesh_parents(bio_ontology: BioOntology):
"""Add missing root level nodes to the MeSH ontology."""
for letter, name in mesh_roots_map.items():
bio_ontology.add_node(bio_ontology.label('MESH', letter), name=name)
edges_to_add = []
for node in bio_ontology.nodes():
# First deal with subtree root nodes
subtree = is_mesh_subroot_node(bio_ontology, node)
if subtree is not None:
edges_to_add.append((
node,
bio_ontology.label('MESH', subtree),
{'type': 'isa'}
))
db_ns, db_id = bio_ontology.get_ns_id(node)
# Then deal with supplementary concepts
if db_ns == 'MESH' and db_id.startswith('C') \
and db_id != 'C': # To skip the previously added subroot node
edges_to_add.append((
node,
bio_ontology.label('MESH', 'S'),
{'type': 'isa'}
))
bio_ontology.add_edges_from(edges_to_add)
def get_categories(fplx_node):
"""Return category labels for a given protein family ontology node."""
children = bio_ontology.get_children(*bio_ontology.get_ns_id(fplx_node),
ns_filter='HGNC')
children_names = {bio_ontology.get_name(*ch) for ch in children}
child_categories = {categories[name] for name in children_names
if name in categories}
return child_categories
def get_category(node):
"""Return a category label for a given specific protein ontology node."""
name = bio_ontology.get_name(*bio_ontology.get_ns_id(node))
category = categories.get(name)
if category:
category_node = category_map[category]
return category_node
return None
def add_ido_parents(bio_ontology: BioOntology):
ido_root = bio_ontology.label('IDO', '0')
bio_ontology.add_node(ido_root, name='infectious disease concept')
edges_to_add = []
for node in bio_ontology.nodes():
if bio_ontology.get_ns(node) == 'IDO' and not \
bio_ontology.get_parents(*bio_ontology.get_ns_id(node)):
edges_to_add.append((node, ido_root, {'type': 'isa'}))
bio_ontology.add_edges_from(edges_to_add)
def add_efo_parents(bio_ontology):
edges_to_add = []
efo_root = 'EFO:0000001'
for node in bio_ontology.nodes():
if bio_ontology.get_ns(node) == 'EFO' and \
not bio_ontology.get_parents(*bio_ontology.get_ns_id(node)):
edges_to_add.append((node, efo_root, {'type': 'isa'}))
print('Adding %d EFO isa edges.' % len(edges_to_add))
bio_ontology.add_edges_from(edges_to_add)
def _make_famplex_lookup():
"""Create a famplex lookup dictionary.
Keys are sorted tuples of HGNC gene names and values are
the corresponding FamPlex ID.
"""
fplx_lookup = {}
bio_ontology.initialize()
for node in bio_ontology.nodes:
ns, id = bio_ontology.get_ns_id(node)
if ns == 'FPLX':
children = bio_ontology.get_children(ns, id)
hgnc_children = [
bio_ontology.get_name(*c) for c in children if c[0] == 'HGNC'
]
fplx_lookup[tuple(sorted(hgnc_children))] = id
return fplx_lookup
def has_fplx_parents(bio_ontology, node):
"""Return True if the given ontology node has FamPlex parents."""
parents = bio_ontology.get_parents(*bio_ontology.get_ns_id(node))
if any(p[0] == 'FPLX' for p in parents):
return True
return False
