From language models to large-scale food and biomedical knowledge graphs

Abstract

Knowledge about the interactions between dietary and biomedical factors is scattered throughout uncountable research articles in an unstructured form (e.g., text, images, etc.) and requires automatic structuring so that it can be provided to medical professionals in a suitable format. Various biomedical knowledge graphs exist, however, they require further extension with relations between food and biomedical entities. In this study, we evaluate the performance of three state-of-the-art relation-mining pipelines (FooDis, FoodChem and ChemDis) which extract relations between food, chemical and disease entities from textual data. We perform two case studies, where relations were automatically extracted by the pipelines and validated by domain experts. The results show that the pipelines can extract relations with an average precision around 70%, making new discoveries available to domain experts with reduced human effort, since the domain experts should only evaluate the results, instead of finding, and reading all new scientific papers.

Augmented non-hallucinating large language models as medical information curators

“…In the first approach, LLMs can be used to construct, enrich and refine KGs from text, leveraging LLMs’ ability to extract and recognize structure (Fig. 1a ), e.g., as has been applied in the construction of dietary KGs 25 and KGs for precision medicine 26 . This is an important application, and it illustrates how modern KGs are generated efficiently through automated machine learning approaches, and not the output of laborious and non-scalable manual approaches.…”