HeCiX: Integrating Knowledge Graphs and Large Language Models for Biomedical Research

TL;DR

HeCiX integrates knowledge graphs from clinical trials and biomedical data with GPT-4 to enhance clinical research, offering a comprehensive resource and promising system for drug development and target validation.

Contribution

This paper introduces HeCiX-KG, a novel knowledge graph combining clinical trial and biomedical data, and HeCiX, a system integrating it with GPT-4 for improved clinical research insights.

Findings

HeCiX-KG effectively consolidates clinical and biological data.

HeCiX demonstrates high performance on clinically relevant tasks.

The approach enhances the understanding of drug development processes.

Abstract

Despite advancements in drug development strategies, 90% of clinical trials fail. This suggests overlooked aspects in target validation and drug optimization. In order to address this, we introduce HeCiX-KG, Hetionet-Clinicaltrials neXus Knowledge Graph, a novel fusion of data from ClinicalTrials.gov and Hetionet in a single knowledge graph. HeCiX-KG combines data on previously conducted clinical trials from ClinicalTrials.gov, and domain expertise on diseases and genes from Hetionet. This offers a thorough resource for clinical researchers. Further, we introduce HeCiX, a system that uses LangChain to integrate HeCiX-KG with GPT-4, and increase its usability. HeCiX shows high performance during evaluation against a range of clinically relevant issues, proving this model to be promising for enhancing the effectiveness of clinical research. Thus, this approach provides a more holistic view of clinical trials and existing biological data.