DrugGen 2: A disease-aware language model for enhancing drug discovery
AI that designs drugs while understanding the disease they'll treat
Researchers created DrugGen-2, an AI model that designs drug molecules by considering both the disease being treated and the specific protein target involved. When tested on diabetic kidney disease, the model generated drugs with stronger predicted binding to their targets than existing approved treatments like enalapril, while also producing more diverse and chemically valid candidates than earlier AI systems.
Current drug discovery AI tools ignore disease context, potentially missing how the same protein behaves differently across conditions. DrugGen-2 bridges this gap, which could speed up finding treatments for complex diseases where target proteins change behavior. This matters because it compresses a lengthy trial-and-error process—generating better drug candidates faster could accelerate development for conditions like diabetic nephropathy where current treatments remain suboptimal.