SPOKE: A massive biomedical knowledge graph for precision health and drug discovery

Описание: Massive amounts of data and information are available for analysis in biomedicine. However, integrating these resources in a powerful statistical framework that is also biologically meaningful poses a considerable challenge. SPOKE is a large knowledge graph containing information from more than 40 specialized databases and spanning multiple disciplines within biomedicine. Currently, SPOKE contains approximately 50 million concepts and over 130 million relationships, organized in a semantic graph. This talk will cover the creation of SPOKE and some of its cutting-edge applications. Some examples include the embedding of more than 2 million electronic health records onto SPOKE, which enabled the training of machine learning models to predict diagnoses and outcomes in multiple sclerosis (MS), Parkinson’s disease (PD), and Alzheimer’s disease (AD). Additionally, efforts focused on applications in drug development and repurposing will be presented. Ultimately, automated integrative strategies are necessary to fully leverage the potential of biomedical information. To that end, efforts towards integrating SPOKE with LLMs via knowledge graph-based retrieval augmentation (KG-RAG) and agentic-AI will be discussed.

Sergio E. Baranzini, PhD, is a Distinguished Professor of Neurology I at the University of California, San Francisco (UCSF). He holds the Heidrich Friends and Family Endowed Chair in Neurology and actively contributes to several UCSF initiatives, including the Graduate Program in Bioinformatics, the Institute for Human Genetics, the Bakar Computational Health Sciences Institute, ImmunoX, and the California Institute for Quantitative Biology (QB3).

Dr. Baranzini earned his degree in clinical biochemistry in 1992 and his PhD in human molecular genetics in 1997 from the University of Buenos Aires. Since joining UCSF, his research has focused on unraveling the genetics and molecular mechanisms underlying complex diseases, with a particular emphasis on multiple sclerosis (MS). His laboratory employs an integrative approach that combines computational and experimental methods, including large-scale genome-wide association studies, molecular profiling to understand disease progression and treatment response, and immunological research to elucidate the mechanisms of neuroinflammation.

Dr. Baranzini is a member of the International MS Genetics Consortium and serves as the lead investigator of the International Multiple Sclerosis Microbiome Study (iMSMS), a global initiative exploring the role of the gut microbiome in MS susceptibility and disease progression. He is also the principal investigator of SPOKE, a groundbreaking NIH- and NSF-supported project that builds a comprehensive biomedical knowledge graph to advance discovery and translational research.

Dr. Baranzini’s work has been published in high-impact journals, including Science, Nature, PNAS, The Journal of Immunology, and PLOS Biology. He is a member of the American Association of Immunologists, the International Multiple Sclerosis Genetics Consortium, and an elected member of both the American Neurological Association and the International Society of Neuroimmunology. In addition to serving on multiple editorial boards, he was honored with the prestigious Barancik Prize for Innovation in MS Research in 2024.