Rapid and Interpretable AMR Diagnostics via Genomics and Cell Painting using Differential Geometry-based Directed-Simplicial Neural Networks on Multimodal Data

arXiv:2603.11141v1 Announce Type: new Abstract: Cross-species antimicrobial resistance (AMR) prediction is fundamentally an out-of-distribution (OOD) generalization problem: models trained on one set of bacterial taxa must transfer to phylogenetically distinct genomes that may rely on different resistance mechanisms.