Hoai An Nguyen - AMR-GNN genomic antimicrobial-resistance prediction framework | MVIF48 S05

Title of the presentation: AMR-GNN: A multi-representation graph neural network framework to enable genomic antimicrobial resistance prediction Speaker: Hoai An Nguyen More info on this event: https://www.microbiome-vif.org/en-US/... Join us at the next meeting (free registration!): https://www.microbiome-vif.org/ And you can join us on Twitter:   / microbiomevif   Abstract of this talk: Whole-genome sequencing (WGS) data are an invaluable resource for understanding antimicrobial resistance (AMR) mechanisms. However, WGS data are high-dimensional and the lack of standardised genomic representations is a key barrier to AMR phenotype prediction. To fully explore these high-resolution data, we propose AMR-GNN, a graph deep learning-based framework that integrates multiple genomic representations with graph neural networks (GNN) to enable AMR phenotype prediction from genomic sequence data. We test AMR-GNN with *Pseudomonas aeruginosa*, a clinically relevant Gram-negative bacterial pathogen known for its complex AMR mechanisms. We present AMR-GNN as a proof-of-concept framework designed to address several key problems in AMR phenotype prediction with data-driven machine learning (ML) approaches, including using multiple genomic representations to enhance performance, to mitigate the influence of clonal relationships and to identify informative biomarkers to provide explainability. Follow-up validation on the largest publicly available dataset spanning both Gram-negative and Gram-positive pathogens highlights AMR-GNN’s broad applicability in detecting AMR in diverse and clinically relevant pathogen-drug combinations.