Figure 1
From: Drug repurposing for COVID-19 using graph neural network and harmonizing multiple evidence
Study workflow. (a) We collected 27 SARS-CoV-2 baits, 322 host genes interacting with baits, 1783 host genes on 609 pathways, 3635 drugs, 4427 drugs’ targets, and 1285 phenotypes, and their corresponding interactions from a curated list of COVID-19 literature in CTDbase. (b) We built the COVID-19 knowledge graph with nodes (baits, host genes, drugs,targets, pathways, and phenotypes) and edges (virus–host protein–protein interaction, gene–gene in pathways, drug-target, gene-phenotype, drug-phenotype interaction). (c) We derived the node’s embedding using the multi-relational and variational graph autoencoder20. We transferred extensive representation in DRKG using transfer learning. (d) We built a drug ranking model based on the drug’s embedding as features and clinical trials as silver-standard labels. (e) The drug ranking was validated using drug’s gene profiles, in vitro drug screening efficacy8, and large-scale electronic health records. (f) We presented validated drugs with their genetic, mechanistic, and epidemiological evidence. (g) Using the highly ranked drug candidates, we searched for drug combinations that satisfy complementary exposure patterns17.
