Biomedical Knowledge Graph Embeddings for Personalized Medicine.

Personalized medicine promises to revolutionize healthcare in the coming years. However significant challenges remain, namely in regard to integrating the vast amount of biomedical knowledge generated in the last few years. Here we describe an approach that uses Knowledge Graph Embedding (KGE) methods on a biomedical Knowledge Graph as a path to reasoning over the wealth of information stored in publicly accessible databases. We use curated databases such as Ensembl, DisGeNET and Gene Ontology as data sources to build a Knowledge Graph containing relationships between genes, diseases and other biological entities and explore the potential of KGE methods to derive medically relevant insights from this KG. To showcase the method’s usefulness we describe two use cases: a) prediction of gene-disease associations and b) clustering of disease embeddings. We show that the top gene-disease associations predicted by this approach can be confirmed in external databases or have already been identified in the literature. An analysis of clusters of diseases, with a focus on Autism Spectrum Disorder (ASD), affords novel insights into the biology of this paradigmatic complex disorder and the overlap of its genetic background with other diseases.