def geneNormalization(documents):
print("Gene Normalization:", file=sys.stderr)
for document in tqdm.tqdm(documents):
ids_by_pmid = getGeneByPMID(document['id'])
for passage in document['passages']:
for ann in passage['annotations']:
ids_by_mention = getGeneByMention(ann['text'])
flag = False
for id_by_mention in ids_by_mention:
if id_by_mention in ids_by_pmid:
flag = True
Annotation.setNCBIID(ann, id_by_mention)
break
if not flag:
Annotation.setNCBIID(
ann, ids_by_mention[0]
if len(ids_by_mention) > 0 else 'TBD')
