UKB-KG: Knowledge Graph for Integrating and Enhancing Biomedical Insights from the UK Biobank

The UK Biobank (UKB) is a cornerstone of modern biomedical research, providing unparalleled data to advance the understanding, prediction, and treatment of diseases. Its contributions span genetics, genomics, disease prediction, and long-term follow-up studies, driving transformative advancements in public health and precision medicine. However, the fragmentation of research outcomes across numerous publications limits analytic efficiency and cross-study integration. To address this, we developed UKB Knowledge Graph (UKB-KG), a high-quality medical knowledge graph constructed using large language models (LLMs) with 88.8% precision as assessed by GPT-5.4. Integrating data from approximately 9,200 UKB-related publications. UKB-KG comprises 292,328 triples enriched with contextual attributes such as source information and demographic details. It reveals intricate relationships among diseases, genes, chemicals, lifestyle factors, and other biomedical entities, while a dynamic scoring mechanism enhances triple retrieval accuracy. Evaluations highlight UKB-KG's transformative potential. (i) Embedding UKB-KG into multi-disease prediction models improves AUROC, AUPRC, and F1 scores by 8.1%, 6.2%, and 2.7%, respectively, for rare diseases. (ii) A tailored retrieval-augmented generation (RAG) approach boosted LLM accuracy by 13.2% on PubMedQA. and (iii) A user-friendly platform enhances accessibility for researchers. By unifying fragmented research and enabling robust data exploration, UKB-KG emerges as a powerful tool for advancing biomedical research and driving innovative healthcare applications.