Improving automated deep phenotyping through large language models using retrieval-augmented generation
RAG-HPO is a user-friendly, adaptable tool designed for secure evaluation of clinical text and outperforms standard HPO-matching tools in precision, recall, and F1. Its enhanced precision and recall represent a substantial advancement in phenotypic analysis, accelerating the identification of genetic mechanisms underlying rare diseases and driving progress in genetic research and clinical genomics. RAG-HPO is available at https://github.com/PoseyPod/RAG-HPO .
Authors
- James R. Lupski (ORCID: https://orcid.org/0000-0001-9907-9246)
- Jennifer E. Posey (ORCID: https://orcid.org/0000-0003-4814-6765)
- Nikhita Gogate (ORCID: https://orcid.org/0000-0003-2050-5084)
- E. Andres Rivera-Munoz (ORCID: https://orcid.org/0000-0002-0610-4770)
- Lauren E. Westerfield (ORCID: https://orcid.org/0000-0002-0878-6808)
- Haowei Du (ORCID: https://orcid.org/0000-0001-9052-1587)
- Brandon T. Garcia (ORCID: https://orcid.org/0000-0001-7734-8601)
- Moez Dawood (ORCID: https://orcid.org/0000-0003-0192-1277)
- Angad Jolly (ORCID: https://orcid.org/0000-0002-5663-1157)
- Priya Yelemali
Institutions
- Meharry Medical College (US)
- Baylor College of Medicine (US)
- Texas Children's Hospital (US)
Publication Details
- Journal
- Genome Medicine
- Published
- 2025-08-18
- DOI
- https://doi.org/10.1186/s13073-025-01521-w
- Citations
- 8
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 5.64
Funders
- National Institutes of Health
- National Human Genome Research Institute