def update_biomappings():
"""Update mappings from the BioMappings project."""
from indra.databases import mesh_client
from indra.databases.identifiers import get_ns_id_from_identifiers
from biomappings.resources import load_mappings, load_predictions
# We now construct a mapping dict of these mappings
biomappings = defaultdict(list)
mappings = load_mappings()
predictions = load_predictions()
exclude_ns = {'kegg.pathway', 'depmap', 'ccle', 'reactome'}
for mappings, mapping_type in ((mappings, 'curated'),
(predictions, 'predicted')):
for mapping in mappings:
# We skip anything that isn't an exact match
if mapping['relation'] != 'skos:exactMatch':
continue
# Skip excluded name spaces that aren't relevant here
if mapping['source prefix'] in exclude_ns or \
mapping['target prefix'] in exclude_ns:
continue
# We only accept curated mappings for NCIT
if mapping_type == 'predicted' and \
(mapping['source prefix'] == 'ncit' or
mapping['target prefix'] == 'ncit'):
continue
source_ns, source_id = \
get_ns_id_from_identifiers(mapping['source prefix'],
mapping['source identifier'])
target_ns, target_id = \
get_ns_id_from_identifiers(mapping['target prefix'],
mapping['target identifier'])
# We only take real xrefs, not refs within a given ontology
if source_ns == target_ns:
continue
biomappings[(source_ns, source_id, mapping['source name'])].append(
(target_ns, target_id, mapping['target name']))
biomappings[(target_ns, target_id, mapping['target name'])].append(
(source_ns, source_id, mapping['source name']))
def _filter_ncit(values):
if len(values) > 1 and 'NCIT' in {v[0] for v in values}:
return [v for v in values if v[0] != 'NCIT']
else:
return values
mesh_mappings = {k: _filter_ncit(v) for k, v in biomappings.items()
if k[0] == 'MESH'}
non_mesh_mappings = {k: [vv for vv in v if vv[0] != 'MESH']
for k, v in biomappings.items()
if k[0] != 'MESH' and k[1] != 'MESH'}
rows = []
for k, v in non_mesh_mappings.items():
for vv in v:
rows.append(list(k + vv))
rows = sorted(rows, key=lambda x: x[1])
write_unicode_csv(get_resource_path('biomappings.tsv'), rows,
delimiter='\t')
# We next look at mappings to MeSH from EFO/HP/DOID
for ns in ['efo', 'hp', 'doid']:
for entry in load_resource_json('%s.json' % ns):
db, db_id, name = ns.upper(), entry['id'], entry['name']
if (db, db_id) in biomappings:
continue
# We first need to decide if we prioritize another name space
xref_dict = {xr['namespace']: xr['id']
for xr in entry.get('xrefs', [])}
if 'MESH' in xref_dict or 'MSH' in xref_dict:
mesh_id = xref_dict.get('MESH') or xref_dict.get('MSH')
if not mesh_id.startswith('D'):
continue
mesh_name = mesh_client.get_mesh_name(mesh_id)
if not mesh_name:
continue
key = ('MESH', mesh_id, mesh_name)
if db_id.startswith('BFO'):
db_to_use = 'BFO'
db_id_to_use = db_id[4:]
else:
db_to_use = db
db_id_to_use = db_id
if key not in mesh_mappings:
mesh_mappings[key] = [(db_to_use, db_id_to_use,
entry['name'])]
else:
mesh_mappings[key].append((db_to_use, db_id_to_use,
entry['name']))
rows = []
for k, v in mesh_mappings.items():
for vv in v:
rows.append(list(k + vv))
rows = sorted(rows, key=lambda x: (x[1], x[2], x[3]))
write_unicode_csv(get_resource_path('mesh_mappings.tsv'), rows,
delimiter='\t')
def test_map_ns_id():
assert get_ns_id_from_identifiers('uniprot', 'P12345') == \
('UP', 'P12345')
assert get_ns_id_from_identifiers('go', 'GO:0005856') == \
('GO', 'GO:0005856')