KEDRec-LM: A Knowledge-distilled Explainable Drug Recommendation Large Language Model

TL;DR

This paper introduces KEDRec-LM, an instruction-tuned large language model that leverages medical knowledge graphs and publications for explainable drug recommendation, aiming to enhance biomedical NLP applications.

Contribution

It presents a novel knowledge-distilled LLM, KEDRec-LM, trained on a comprehensive biomedical dataset for explainable drug discovery, and releases both the model and dataset for future research.

Findings

KEDRec-LM effectively generates drug recommendations with explanations.

The dataset expRxRec enables research in explainable drug discovery.

The approach improves interpretability in biomedical NLP tasks.

Abstract

Drug discovery is a critical task in biomedical natural language processing (NLP), yet explainable drug discovery remains underexplored. Meanwhile, large language models (LLMs) have shown remarkable abilities in natural language understanding and generation. Leveraging LLMs for explainable drug discovery has the potential to improve downstream tasks and real-world applications. In this study, we utilize open-source drug knowledge graphs, clinical trial data, and PubMed publications to construct a comprehensive dataset for the explainable drug discovery task, named \textbf{expRxRec}. Furthermore, we introduce \textbf{KEDRec-LM}, an instruction-tuned LLM which distills knowledge from rich medical knowledge corpus for drug recommendation and rationale generation. To encourage further research in this area, we will publicly release\footnote{A copy is attached with this submission} both the dataset and KEDRec-LM.