Link Prediction based on Tensor Decomposition for the Knowledge Graph of COVID-19 Antiviral Drug

ue to the large-scale spread of COVID-19, which has a significant impact on human health and socialeconomy, developing effective antiviral drugs for COVID-19 is vital to saving human lives. Various biomedicalassociations, e.g., drug-virus and viral protein-host protein interactions, can be used for building biomedicalknowledge graphs. Based on these sources, large-scale knowledge reasoning algorithms can be used topredict new links between antiviral drugs and viruses. To utilize the various heterogeneous biomedicalassociations, we proposed a fusion strategy to integrate the results of two tensor decomposition-based models(i.e., CP-N3 and ComplEx-N3). Sufficient experiments indicated that our method obtained high performance(MRR=0.2328). Compared with CP-N3, the mean reciprocal rank (MRR) is increased by 3.3% and comparedwith ComplEx-N3, the MRR is increased by 3.5%. Meanwhile, we explored the relationship between theperformance and relationship types, which indicated that there is a negative correlation (PCC=0.446,P-value=2.26e-194) between the performance of triples predicted by our method and edge betweenness.