EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PERADIGM: Phenotype embedding similarity-based rare disease gene mapping

Wangjie Zheng, Yuhan Xie iD, Jianlei Gu, Hongyu Li, Stefan Somlo, Whitney Besse iD, Hongyu Zhao iD

PLOS Genetics · 2025

DOI: 10.1371/journal.pgen.1011976 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Genetics, 2025. Verfasst von Wangjie Zheng und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, Yale University, New Haven, Connecticut, United States of America. Hauptthemen laut MEDLINE: Rare Diseases, Marfan Syndrome, Neurofibromatosis 1, Polycystic Kidney, Autosomal Dominant. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHGRI NIH HHS, National Institute of Child Health and Human Development, National Institute of General Medical Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Identifying genes associated with rare diseases remains challenging due to the scarcity of patients and the limited statistical power of traditional association methods. Here, we introduce PERADIGM ( P henotype E mbedding similarity-based RA re DI sease G ene M apping), a novel framework that leverages natural language processing techniques to integrate comprehensive phenotype information from electronic health records for rare disease gene discovery. PERADIGM employs an embedding model to capture relationships between ICD-10 codes, providing a nuanced representation of individual phenotypes. By utilizing patient similarity scores, it enhances the identification of candidate genes associated with disease-specific phenotypes, surpassing conventional methods that rely on binary disease status. We applied PERADIGM to the UK Biobank dataset for three rare diseases: autosomal dominant polycystic kidney disease (ADPKD), Marfan syndrome, and neurofibromatosis type 1 (NF1). PERADIGM identified additional candidate genes associated with ADPKD-related and Marfan syndrome-related phenotypes, some of which are supported by existing literature, and demonstrated enhanced signal detection for NF1-specific phenotypes beyond traditional methods. Our findings demonstrate the potential of PERADIGM to identify genes associated with rare diseases and related phenotypes by incorporating phenotype embeddings and patient similarity, providing a powerful tool for precision medicine and a deeper understanding of rare disease genetics and clinical manifestations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Rare DiseasesMarfan SyndromeNeurofibromatosis 1Polycystic Kidney, Autosomal DominantChromosome MappingHumansPhenotypeElectronic Health RecordsGenetic Association StudiesGenetic Predisposition to Disease

Autor:innen und Institutionen

  • Department of Biostatistics, Yale University, New Haven, Connecticut, United States of America.
  • Department of Internal Medicine, Section of Nephrology, Yale School of Medicine, New Haven, Connecticut, United States of America.

ORCID-Profile: Yuhan Xie, Whitney Besse, Hongyu Zhao

Förderung

  • NHGRI NIH HHS
  • National Institute of Child Health and Human Development
  • National Institute of General Medical Sciences

Zitieren

APA

Zheng, W., Xie, Y., Gu, J., Li, H., Somlo, S., Besse, W., & Zhao, H. (2025). PERADIGM: Phenotype embedding similarity-based rare disease gene mapping. PLOS Genetics. https://doi.org/10.1371/journal.pgen.1011976

Vancouver

Zheng W, Xie Y, Gu J, Li H, Somlo S, Besse W, et al. PERADIGM: Phenotype embedding similarity-based rare disease gene mapping. PLOS Genetics. 2025. doi:10.1371/journal.pgen.1011976

BibTeX
@article{Zheng2025,
  author = {Zheng, Wangjie and Xie, Yuhan and Gu, Jianlei and Li, Hongyu and Somlo, Stefan and Besse, Whitney and Zhao, Hongyu},
  title = {PERADIGM: Phenotype embedding similarity-based rare disease gene mapping},
  journal = {PLOS Genetics},
  year = {2025},
  doi = {10.1371/journal.pgen.1011976}
}
Kostenlos starten →