Scientists from the UVA School of Medicine have developed a new approach to drug development that utilizes artificial intelligence.
They created a suite of AI-powered tools to “transform how new drugs are created.” One of the tools uses an AI form called “diffusion models to design new drug molecules tailored to fit their protein targets exactly, even accounting for the way proteins flex and shift shape during binding.” A companion tool “identifies exactly where on a protein a drug can attach,” while another “ensures the chemical bonds in designed molecules are accurate.”
The average cost of developing a drug is somewhere around $2.6 billion, and “almost 90% of new drugs fail when they reach human testing. That is due, in no small part, to the difficulty of predicting how molecules in a drug will interact, or bind, with their targets in the body. If a molecule doesn’t bind exactly as intended, at exactly the right spot, the drug won’t work, or could have unwanted, harmful side effects.” These tools leverage AI to design “drug molecules while treating proteins as flexible, dynamic structures.”
The researchers’ ultimate goal is to “make drug discovery faster, cheaper, and more likely to succeed, so that promising treatments can reach patients sooner.” Early results have been promising.
