BERTChem-DDI : Improved Drug-Drug Interaction Prediction from text using Chemical Structure Information
This work provides an incremental improvement in drug-drug interaction prediction for pharmaceutical research and drug safety.
This paper addresses the problem of predicting Drug-Drug Interactions (DDI) from text by integrating chemical structure information. The proposed method, BERTChem-DDI, combines drug embeddings derived from molecular structures with BioBERT-based relation extraction, achieving a 3.4% improvement in macro F1-score on the DDIExtraction 2013 corpus.
Traditional biomedical version of embeddings obtained from pre-trained language models have recently shown state-of-the-art results for relation extraction (RE) tasks in the medical domain. In this paper, we explore how to incorporate domain knowledge, available in the form of molecular structure of drugs, for predicting Drug-Drug Interaction from textual corpus. We propose a method, BERTChem-DDI, to efficiently combine drug embeddings obtained from the rich chemical structure of drugs along with off-the-shelf domain-specific BioBERT embedding-based RE architecture. Experiments conducted on the DDIExtraction 2013 corpus clearly indicate that this strategy improves other strong baselines architectures by 3.4\% macro F1-score.