Complex graph neural networks for medication interaction verification

This paper presents the development and application of graph neural networks to verify drug interactions, consisting drug-protein networks. For this, DrugBank databases were used, creating four complex interactions: target proteins, transport carrier enzymes. The Louvain Girvan-Newman community detection algorithms used establish communities validate interactions between them. Positive results obtained when checking two sets drugs for disease treatments: diabetes anxiety; antibiotics. There found 371 by algorithm 58 via Louvain.