Clustering rare diseases within an ontology-enriched knowledge graph
Journal of the American Medical Informatics Association · 22.12.2023 · 31 (1) · 154-164
DOI: 10.1093/jamia/ocad186 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 27.09.2023. Verfasst von Jaleal Sanjak und 4 weiteren Autor:innen. Beteiligte Einrichtung: Division of Pre-Clinical Innovation, National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), Rockville, MD…. Hauptthemen laut MEDLINE: Rare Diseases, Pattern Recognition, Automated. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Intramural NIH HHS, NCATS NIH HHS, NIH HHS.
Abstract (Originalsprache)
Objective
Identifying sets of rare diseases with shared aspects of etiology and pathophysiology may enable drug repurposing. Toward that aim, we utilized an integrative knowledge graph to construct clusters of rare diseases. Materials and Methods Data on 3242 rare diseases were extracted from the National Center for Advancing Translational Science Genetic and Rare Diseases Information center internal data resources. The rare disease data enriched with additional biomedical data, including gene and phenotype ontologies, biological pathway data, and small molecule-target activity data, to create a knowledge graph (KG). Node embeddings were trained and clustered. We validated the disease clusters through semantic similarity and feature enrichment analysis.
Results
Thirty-seven disease clusters were created with a mean size of 87 diseases. We validate the clusters quantitatively via semantic similarity based on the Orphanet Rare Disease Ontology. In addition, the clusters were analyzed for enrichment of associated genes, revealing that the enriched genes within clusters are highly related.
Discussion
We demonstrate that node embeddings are an effective method for clustering diseases within a heterogenous KG. Semantically similar diseases and relevant enriched genes have been uncovered within the clusters. Connections between disease clusters and drugs are enumerated for follow-up efforts.
Conclusion
We lay out a method for clustering rare diseases using graph node embeddings. We develop an easy-to-maintain pipeline that can be updated when new data on rare diseases emerges. The embeddings themselves can be paired with other representation learning methods for other data types, such as drugs, to address other predictive modeling problems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Pre-Clinical Innovation, National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), Rockville, MD, United States.
- Chief Technology Office, Booz Allen Hamilton, Bethesda, MD, United States.
ORCID-Profile: Jaleal Sanjak, Arjun Singh Yadaw
Förderung
- Intramural NIH HHS
- NCATS NIH HHS
- NIH HHS
- Intramural Research Program
- National Center for Advancing Translational Sciences
- National Institutes of Health
Zitieren
APA
Sanjak, J., Binder, J., Yadaw, A. S., Zhu, Q., & Mathé, E. A. (2023). Clustering rare diseases within an ontology-enriched knowledge graph. Journal of the American Medical Informatics Association, 31(1), 154-164. https://doi.org/10.1093/jamia/ocad186
Vancouver
Sanjak J, Binder J, Yadaw AS, Zhu Q, Mathé EA. Clustering rare diseases within an ontology-enriched knowledge graph. Journal of the American Medical Informatics Association. 2023;31(1):154-164. doi:10.1093/jamia/ocad186
BibTeX
@article{Sanjak2023,
author = {Sanjak, Jaleal and Binder, Jessica and Yadaw, Arjun Singh and Zhu, Qian and Mathé, Ewy A},
title = {Clustering rare diseases within an ontology-enriched knowledge graph},
journal = {Journal of the American Medical Informatics Association},
year = {2023},
volume = {31},
number = {1},
pages = {154--164},
doi = {10.1093/jamia/ocad186}
}
EUVIMED