Applying Domain Ontologies and Knowledge Graphs To Augment Literature-Based Discovery: Discovering Gene-Disease Associations Between COVID-19, Diabetes Mellitus, And Chronic Kidney Disease

Abstract

We present an automated knowledge synthesis and discovery framework to analyze published literature to identify and represent underlying mechanistic associations that aggravate chronic conditions due to COVID-19. Our literature-based discovery approach integrates text mining, knowledge graphs, and medical ontologies to discover hidden and previously unknown pathophysiologic relations between COVID-19 and chronic disease mechanisms as reported in literature that is dispersed across multiple public databases. Our framework applies knowledge graph augmentation methods based on external knowledge (i.e., ontologies) to address the issue of incomplete knowledge captured in relations mined from text (called semantic associations) to improve literature-based discovery of complex mechanistic associations. We applied our approach to discover gene-disease associations for COVID-19 and chronic conditions—i.e. diabetes mellitus and chronic kidney disease—to understand the long-term impact of COVID-19 on patients with chronic diseases. We discovered several novel associations that could help identify mechanisms driving COVID-19 in patients with underlying conditions.