def create_gene_terms():
print('Creating gene terms')
handle = os.path.join(FIXTURE_DIR, 'hgnc.json')
with open(handle, 'r', encoding='utf-8') as f:
hgnc_json = f.read()
g = obograph_util.convert_json_object(json.loads(hgnc_json))
ont = Ontology(handle=handle, payload=g)
gene_terms = []
for n_id in ont.nodes():
n_dict = ont.node(n_id)
if 'type' in n_dict:
if ont.node_type(n_id) == 'CLASS':
for t in n_dict['meta']['basicPropertyValues']:
if t['pred'] == 'http://ncicb.nci.nih.gov/xml/owl/EVS/Hugo.owl#Approved_Symbol':
symbol = t['val']
if not symbol.endswith('~withdrawn'):
# print('{} {}'.format(n_id, symbol))
gene_terms.append(
GeneTerm(term_id=n_id, label=symbol))
break
GeneTerm.objects.bulk_create(gene_terms)
def get_all_paths_to_root(node_id: str,
ontology: Ontology,
min_distance_from_root: int = 0,
relations: List[str] = None,
nodeids_blacklist: List[str] = None,
previous_path: Union[None, List[str]] = None,
root_node=None) -> Set[Tuple[str]]:
"""get all possible paths connecting a go term to its root terms
Args:
node_id (str): a valid GO id for the starting term
ontology (Ontology): the go ontology
min_distance_from_root (int): return only terms at a specified minimum distance from root terms
relations (List[str]): the list of relations to be used
nodeids_blacklist (List[str]): a list of node ids to exclude from the paths
previous_path (Union[None, List[str]]): the path to get to the current node
Returns:
Set[Tuple[str]]: the set of paths connecting the specified term to its root terms, each of which contains a
sequence of terms ids
"""
if previous_path is None:
previous_path = []
new_path = previous_path[:]
if not nodeids_blacklist or node_id not in nodeids_blacklist:
new_path.append(node_id)
parents = [
parent
for parent in ontology.parents(node=node_id, relations=relations)
if ontology.node(parent)["depth"] >= min_distance_from_root
]
parents_same_root = []
if root_node:
for parent in parents:
parent_node = ontology.node(parent)
parent_root = None
if "meta" in parent_node and "basicPropertyValues" in parent_node[
"meta"]:
for basic_prop_val in parent_node["meta"][
"basicPropertyValues"]:
if basic_prop_val["pred"] == "OIO:hasOBONamespace":
parent_root = basic_prop_val["val"]
if parent_root and parent_root == root_node:
parents_same_root.append(parent)
parents = parents_same_root
if len(parents) > 0:
# go up the tree, following a depth first visit
paths_to_return = set()
for parent in parents:
for path in TrimmingAlgorithmNaive.get_all_paths_to_root(
node_id=parent,
ontology=ontology,
previous_path=new_path,
min_distance_from_root=min_distance_from_root,
relations=relations,
nodeids_blacklist=nodeids_blacklist,
root_node=root_node):
paths_to_return.add(path)
return paths_to_return
if len(new_path) == 0:
return {(node_id, )}
else:
return {tuple(new_path)}
