def clean_ner_result(result_file):
ord_mention_list = list()
med_mention_list = list()
fin = open(result_file, 'rb')
for line in fin:
line = line.strip()
if len(line) == 0:
continue
vals = line.strip().split('\t')
# TODO
if vals[3] == 'Disease' or vals[3] == 'Chemical':
span = (int(vals[0]), int(vals[1]) - 1)
else:
span = (int(vals[0]), int(vals[1]))
mention = Mention()
mention.span = span
mention.mtype = vals[3]
if len(vals) == 4:
ord_mention_list.append(mention)
else:
if vals[4].startswith('MESH'):
mention.mesh_id = vals[4][5:]
elif vals[4].startswith('CHEBI'):
mention.chebi_id = int(vals[4][6:])
med_mention_list.append(mention)
fin.close()
merged_mention_list = list()
Mention.merge_mention_list(med_mention_list, merged_mention_list)
Mention.merge_mention_list(ord_mention_list, merged_mention_list)
return merged_mention_list
def link_text(self, text, mention_detection_result):
result_dict = dict()
mesh_mention_list = self.__find_mesh_mentions(text)
merged_mention_list = list()
Mention.merge_mention_list(mention_detection_result,
merged_mention_list)
Mention.merge_mention_list(mesh_mention_list, merged_mention_list)
self.__link_mention_to_wiki(text, merged_mention_list)
mesh_idx_dict, wiki_idx_dict, chebi_idx_dict, idx_list = MedLink.__asign_indices(
merged_mention_list)
result_dict['entities'] = entities_dict = dict()
self.__add_wiki_mention_info(wiki_idx_dict, entities_dict)
self.__add_mesh_mention_info(mesh_idx_dict, entities_dict)
self.__add_chebi_mention_info(chebi_idx_dict, entities_dict)
result_span_list = list()
mention_type_list = list()
for mention in merged_mention_list:
result_span_list.append(mention.span)
mention_type_list.append(mention.mtype)
result_dict['spans'] = result_span_list
result_dict['idx'] = idx_list
result_dict['type'] = mention_type_list
return json.dumps(result_dict, indent=2)
def link_mentions_info(self, text, mention_detection_result, find_mesh_mentions_by_dict=False):
merged_mention_list = list()
if find_mesh_mentions_by_dict:
mesh_mention_list = self.__find_mesh_mentions(text)
Mention.merge_mention_list(mention_detection_result, merged_mention_list)
Mention.merge_mention_list(mesh_mention_list, merged_mention_list)
linked_mentions = self.link_mentions(merged_mention_list, text)
if find_mesh_mentions_by_dict:
for mention in merged_mention_list:
if mention.mesh_id or mention.chebi_id > -1:
for mention1 in merged_mention_list:
if mention.name.lower() == mention1.name.lower():
mention1.mesh_id = mention.mesh_id
mention1.chebi_id = mention.chebi_id
mesh_idx_dict, wiki_idx_dict, chebi_idx_dict, idx_list = MedLink.__asign_indices(linked_mentions)
# print wiki_idx_dict
result_dict = dict()
result_dict['entities'] = entities_dict = dict()
self.__add_wiki_mention_info(wiki_idx_dict, entities_dict)
self.__add_mesh_mention_info(mesh_idx_dict, entities_dict)
self.__add_chebi_mention_info(chebi_idx_dict, entities_dict)
result_span_list = list()
mention_type_list = list()
for mention in linked_mentions:
result_span_list.append(mention.span)
mention_type_list.append(mention.mtype)
self.__fix_types(mesh_idx_dict, idx_list, mention_type_list)
result_dict['spans'] = result_span_list
result_dict['idx'] = idx_list
result_dict['type'] = mention_type_list
return json.dumps(result_dict, indent=2)
