How generative AI and physics can help design new antibiotics

Summary

By 2050, antibiotic-resistant infections could be associated with over eight million deaths annually worldwide. Developing new antibiotics is slow and costly, but generative AI models, guided by scientists, can propose novel molecules, and physics-based simulations can quickly assess their potential as drugs. Peptides like insulin and vancomycin serve as important starting points. A good AI model includes a generator that dreams up millions of designs and a discriminator that filters them. This combined approach offers a cost-effective way to discover new antibiotics.