‘Explainable’ AI identifies a new class of antibiotics
Nature · 2023
An artificial-intelligence graph neural network was trained on experimental data and used to identify chemical substructures that underlie selective antibiotic activity in more than 12 million compounds. This led to the discovery of a class of antibiotics with in vitro and in vivo activity against Gram-positive bacteria, including Staphylococcus aureus. How artificial-intelligence models make predictions is often unclear, but this graph neural network reveals how it designs new antibiotics.