BIOS: An Algorithmically Generated Biomedical Knowledge Graph
This addresses the bottleneck in biomedical AI development by providing an algorithmically generated knowledge graph to replace slow expert curation, though it is incremental as it builds on existing BioMedKG concepts.
The authors tackled the problem of creating biomedical knowledge graphs (BioMedKGs) by introducing BIOS, the first large-scale publicly available BioMedKG generated entirely by machine learning algorithms, which contains 4.1 million concepts, 7.4 million terms, and 7.3 million relation triplets, showing it as a viable alternative to expert curation.
Biomedical knowledge graphs (BioMedKGs) are essential infrastructures for biomedical and healthcare big data and artificial intelligence (AI), facilitating natural language processing, model development, and data exchange. For decades, these knowledge graphs have been developed via expert curation; however, this method can no longer keep up with today's AI development, and a transition to algorithmically generated BioMedKGs is necessary. In this work, we introduce the Biomedical Informatics Ontology System (BIOS), the first large-scale publicly available BioMedKG generated completely by machine learning algorithms. BIOS currently contains 4.1 million concepts, 7.4 million terms in two languages, and 7.3 million relation triplets. We present the methodology for developing BIOS, including the curation of raw biomedical terms, computational identification of synonymous terms and aggregation of these terms to create concept nodes, semantic type classification of the concepts, relation identification, and biomedical machine translation. We provide statistics on the current BIOS content and perform preliminary assessments of term quality, synonym grouping, and relation extraction. The results suggest that machine learning-based BioMedKG development is a viable alternative to traditional expert curation.