search

TranslatorSRI / NodeNormalization

Service that produces Translator compliant nodes given a curie
MIT License
10 stars 6 forks source link

Unrelated identifiers clustered with tocilizumab #297

Open amykglen opened 3 weeks ago

amykglen commented 3 weeks ago

@jaredroach brought an issue with naming of tocilizumab in RTX-KG2c to our attention and we traced it to the fact that the NodeNormalizer's cluster for tocilizumab includes a couple identifiers with names that seemingly have nothing to do with tocilizumab:

https://nodenorm.ci.transltr.io/get_normalized_nodes?curie=UNII:I031V2H011

"equivalent_identifiers": [
...
{
"identifier": "PUBCHEM.COMPOUND:10150081",
"label": "2-[(4-Ethynyl-2-Fluorophenyl)amino]-3,4-Difluoro-N-(2-Hydroxyethoxy)benzamide"
},
{
...
{
"identifier": "DRUGBANK:DB08208",
"label": "2-[(4-ETHYNYL-2-FLUOROPHENYL)AMINO]-3,4-DIFLUORO-N-(2-HYDROXYETHOXY)BENZAMIDE"
},

are these two identifiers mistakenly assigned to this cluster?