Google's DeepMind AI unit pioneered the application of AI large language models to biology, which has led to a medical revolution that includes spatial genomics scanning millions of cells within tissue in 3-D. AI can "think" of drug models that a human would not, potentially improving success rates and reducing the time taken for drug discovery. The University of Texas at Austin has purchased one of the largest NVIDIA computing clusters for its new Center for Generative AI, which is learning to distinguish drugs from non-drugs and to create new drugs.
Key takeaways:
- Eli Lilly has been using generative AI to search through millions of molecules for drug discovery, with the AI able to generate as many molecules in five minutes as Lilly could synthesize in a year in traditional labs.
- AI is expected to completely generate medicines in the near future, reshaping the pharmaceutical industry and the scientific method that has been in place for centuries.
- Google's DeepMind's AlphaFold was a pivotal moment in AI and healthcare, demonstrating how AI can be used to go from amino acid sequence to a protein structure, which is crucial for drug development and design.
- AI is not only speeding up the drug discovery process but also improving success rates, with AI-augmented processes showing a success rate of 90% compared to a 50/50 chance after a two-year traditional development process.