The effects of biological knowledge graph topology on classical embedding-based link prediction

Due to the limited information available about rare diseases and their causal variants, knowledge graphs are often used to augment our understanding and make inferences about new gene-disease connections. Classical knowledge graph embedding methods with fixed scoring functions have been successfully applied to various biomedical link prediction tasks but have yet to be adopted for rare disease variant prioritization. Here, using the Monarch knowledge graph as a representative case study, we explore the effect of knowledge graph topology on classical knowledge graph embedding link prediction performance and challenge the assumption that massively aggregating knowledge graphs is beneficial in deciphering rare disease cases and improving prediction outcomes. We find that using a filtered version of the Monarch knowledge graph with only 11% of the original size results in notably improved model predictive performance. Additionally, these findings suggest that successful knowledge graph optimization depends on selecting high-quality information rather than simply maximizing the amount of data included.