Biomedical knowledge graph-optimized prompt generation for large language models
SPOKE KG can be accessed at https://spoke.rbvi.ucsf.edu/neighborhood.html. It can also be accessed using REST-API (https://spoke.rbvi.ucsf.edu/swagger/). KG-RAG code is made available at https://github.com/BaranziniLab/KG_RAG. Biomedical benchmark datasets used in this study are made available to the research community in the same GitHub repository.
Authors
- Sergio E. Baranzini (ORCID: https://orcid.org/0000-0003-0067-194X)
- Sui Huang (ORCID: https://orcid.org/0000-0002-3545-4665)
- Karthik Soman (ORCID: https://orcid.org/0000-0002-3490-9306)
- Charlotte Nelson (ORCID: https://orcid.org/0000-0002-3687-1102)
- Yongmei Shi
- Gabriel Cerono (ORCID: https://orcid.org/0000-0002-9411-2526)
- Angela Rizk‐Jackson (ORCID: https://orcid.org/0000-0002-1732-8550)
- John H. Morris (ORCID: https://orcid.org/0000-0003-0290-7979)
- Rabia E Akbas (ORCID: https://orcid.org/0009-0009-0217-9554)
- Sharat Israni
- Peter W. Rose (ORCID: https://orcid.org/0000-0001-9981-9750)
- Braian Peetoom
- Catalina Villouta-Reyes
- Brett Smith (ORCID: https://orcid.org/0000-0002-2586-5014)
Institutions
- University of California, San Francisco (US)
- San Diego Supercomputer Center (US)
- Institute for Systems Biology (US)
- University of California San Diego (US)
- Fisher Bioservices (United States) (US)
Publication Details
- Journal
- Bioinformatics
- Published
- 2024-09-01
- DOI
- https://doi.org/10.1093/bioinformatics/btae560
- Citations
- 84
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 29.18
Funders
- National Science Foundation
- National Institutes of Health
- University of California, San Francisco
- National Center for Advancing Translational Sciences