BRIDGE: Biological Antimicrobial Resistance Inference via Domain-Knowledge Graph Embeddings

Abstract

Antimicrobial resistance (AMR) is a growing global health crisis, responsible for an estimated 1.27 million deaths in 2019 alone. Traditional approaches to identifying antibiotic resistance genes (ARGs) are often labour-intensive and limited in their ability to detect novel resistance mechanisms. In this study, we propose BRIDGE, a knowledge graph-based framework, to improve AMR gene prediction by integrating gene neighbourhood information and protein-protein interaction (PPI) networks. Focusing on Klebsiella pneumoniae and Escherichia coli, we con- struct a comprehensive and biologically grounded knowl- edge graph using curated data from CARD, STRING, and DrugBank. We apply knowledge graph embedding models which are fed into neural networks to infer novel AMR links, achieving classification accuracy of up to 97%. Our results demonstrate that incorporating biologically meaningful re- lationships, such as gene neighbourhood information and PPIs, enhances the predictive accuracy and interpretability of AMR link predictions. This work contributes to the de- velopment of scalable and data-integrated approaches for advancing antimicrobial resistance surveillance and drug discovery. BRIDGE implementation and data are available at https://github.com/GraphML-lab/BRIDGE.