Hierarchical Relationship Prediction in the Disease Ontology

The Disease Ontology is an open-source, community-driven resource that provides a structured vocabulary for human diseases. By integrating data from biomedical sources such as Medical Subject Headings (MeSH) and the Systematized Nomenclature of Medicine (SNOMED), it captures a comprehensive range of disease concepts, characteristics, and associated terminology. Ontologies like this enable formal reasoning and have been increasingly leveraged in machine learning and deep learning applications. In this study, we investigate ontology-based embeddings for predicting relationships within the disease knowledge graph, aiming to evaluate their effectiveness in enhancing computational understanding of disease-related information and reasoning.