Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologies
This work addresses gene-disease association prediction for biomedical researchers, but it is incremental as it builds on existing knowledge graph embedding methods by extending them to multiple ontologies.
The paper tackled the problem of predicting gene-disease associations by using knowledge graph embeddings over multiple ontologies, resulting in improved performance that highlights the value of richer semantic representations and closer integration of different ontologies.
Ontology-based approaches for predicting gene-disease associations include the more classical semantic similarity methods and more recently knowledge graph embeddings. While semantic similarity is typically restricted to hierarchical relations within the ontology, knowledge graph embeddings consider their full breadth. However, embeddings are produced over a single graph and complex tasks such as gene-disease association may require additional ontologies. We investigate the impact of employing richer semantic representations that are based on more than one ontology, able to represent both genes and diseases and consider multiple kinds of relations within the ontologies. Our experiments demonstrate the value of employing knowledge graph embeddings based on random-walks and highlight the need for a closer integration of different ontologies.