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 normalize_sif_names(sif_df: DataFrame):
"""Try to normalize names in the sif dump dataframe
This function tries to normalize the names of the entities in the sif
dump. The 'bio_ontology' is the arbiter of what constitutes a normalized
name. If no name exists, no further attempt to change the name is made.
Parameters
----------
sif_df :
The sif dataframe
"""
from indra.ontology.bio import bio_ontology
bio_ontology.initialize()
logger.info('Getting ns, id, name tuples')
# Get the set of grounded entities
ns_id_name_tups = set(
zip(sif_df.agA_ns, sif_df.agA_id, sif_df.agA_name)).union(
set(zip(sif_df.agB_ns, sif_df.agB_id, sif_df.agB_name))
)
# Get the ontology name, if it exists, and check if the name in the
# dataframe needs update
logger.info('Checking which names need updating')
inserted_set = set()
for ns_, id_, cur_name in tqdm(ns_id_name_tups):
oname = bio_ontology.get_name(ns_, id_)
# If there is a name in the ontology and it is different than the
# original, insert it
if oname and oname != cur_name and (ns_, id_, oname) not in inserted_set:
inserted_set.add((ns_, id_, oname))
if len(inserted_set) > 0:
logger.info(f'Found {len(inserted_set)} names in dataframe that need '
f'renaming')
# Make dataframe of rename dict
logger.info('Making rename dataframe')
df_dict = defaultdict(list)
for ns_, id_, name in inserted_set:
df_dict['ns'].append(ns_)
df_dict['id'].append(id_)
df_dict['name'].append(name)
rename_df = pd.DataFrame(df_dict)
# Do merge on with relevant columns from sif for both A and B
logger.info('Getting temporary dataframes for renaming')
# Get dataframe with ns, id, new name column
rename_a = sif_df[['agA_ns', 'agA_id']].merge(
right=rename_df,
left_on=['agA_ns', 'agA_id'],
right_on=['ns', 'id'], how='left'
).drop('ns', axis=1).drop('id', axis=1)
# Check which rows have name entries
truthy_a = pd.notna(rename_a.name)
# Rename in sif_df from new names
sif_df.loc[truthy_a, 'agA_name'] = rename_a.name[truthy_a]
# Repeat for agB_name
rename_b = sif_df[['agB_ns', 'agB_id']].merge(
right=rename_df,
left_on=['agB_ns', 'agB_id'],
right_on=['ns', 'id'], how='left'
).drop('ns', axis=1).drop('id', axis=1)
truthy_b = pd.notna(rename_b.name)
sif_df.loc[truthy_b, 'agB_name'] = rename_b.name[truthy_b]
# Check that there are no missing names
logger.info('Performing sanity checks')
assert sum(pd.isna(sif_df.agA_name)) == 0
assert sum(pd.isna(sif_df.agB_name)) == 0
# Get the set of ns, id, name tuples and check diff
ns_id_name_tups_after = set(
zip(sif_df.agA_ns, sif_df.agA_id, sif_df.agA_name)).union(
set(zip(sif_df.agB_ns, sif_df.agB_id, sif_df.agB_name))
)
# Check that rename took place
assert ns_id_name_tups_after != ns_id_name_tups
# Check that all new names are used
assert set(rename_df.name).issubset({n for _, _, n in ns_id_name_tups_after})
logger.info('Sif dataframe renamed successfully')
else:
logger.info('No names need renaming')
"""This service implements all base functions of the ontology graph as a REST
service. The three key functions that most ontology methods rely on are
child_rel, parent_rel, and get_node_property. There are a few other bookkeeping
functions that also need to be implemented here since they access ontology
attributes directly."""
import argparse
from flask import Flask, request, jsonify
from indra.ontology.bio import bio_ontology
app = Flask(__name__)
bio_ontology.initialize()
ontologies = {'bio': bio_ontology}
@app.route('/child_rel', methods=['GET'])
def child_rel():
ont = request.json.get('ontology')
ontology = ontologies.get(ont)
kwargs = ('ns', 'id', 'rel_types')
return jsonify(list(ontology.child_rel(
**{k: v for k, v in request.json.items() if k in kwargs})))
@app.route('/parent_rel', methods=['GET'])
def parent_rel():
ont = request.json.get('ontology')
ontology = ontologies.get(ont)
kwargs = ('ns', 'id', 'rel_types')
return jsonify(list(ontology.parent_rel(