Towards Incorporating Entity-specific Knowledge Graph Information in Predicting Drug-Drug Interactions
This work provides an incremental improvement in drug-drug interaction prediction for pharmaceutical research and drug safety.
This paper addresses the prediction of Drug-Drug Interactions (DDI) from text by integrating entity-specific knowledge graph (KG) information. The proposed BERTKG-DDI method, which combines drug embeddings from KGs with BioBERT-based relation classification, achieved a 4.1% improvement in macro F1-score on the DDIExtraction 2013 corpus compared to baseline architectures.
Off-the-shelf biomedical embeddings obtained from the recently released various pre-trained language models (such as BERT, XLNET) have demonstrated state-of-the-art results (in terms of accuracy) for the various natural language understanding tasks (NLU) in the biomedical domain. Relation Classification (RC) falls into one of the most critical tasks. In this paper, we explore how to incorporate domain knowledge of the biomedical entities (such as drug, disease, genes), obtained from Knowledge Graph (KG) Embeddings, for predicting Drug-Drug Interaction from textual corpus. We propose a new method, BERTKG-DDI, to combine drug embeddings obtained from its interaction with other biomedical entities along with domain-specific BioBERT embedding-based RC architecture. Experiments conducted on the DDIExtraction 2013 corpus clearly indicate that this strategy improves other baselines architectures by 4.1% macro F1-score.