Oct 16, 2024

Machine learning in drug discovery speeds up development SHARE Machine learning in drug discovery, along with artificial intelligence, is transforming the pharmaceutical industry by accelerating the development of new treatments. Historically, the process of discovering and developing new drugs has been painstakingly slow, fraught with high failure rates and incredibly expensive. However, new developments in AI-driven methodologies, particularly in digital chemistry and biology, are creating unprecedented opportunities to accelerate drug discovery , according to Stephen Mackinnon (pictured), vice president of applied machine learning at Recursion Pharmaceuticals Inc. Recursion Pharmaceutical’s Stephen Mackinnon talks to theCUBE about machine learning in drug discovery. “Machine learning helps us understand more about the world. It helps us understand more about biology so that when we take that risk, when we go through that grand experiment of a clinical trial,” he said. “We’re better equipped with knowledge of what that drug is doing, what that drug is doing to the system, what the drug is doing to the body so that we can make a more informed decision as what goes through.” Mackinnon spoke with theCUBE Research’s Savannah Peterson at Anyscale Ray Summit , during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed how AI and machine learning are transforming drug discovery by accelerating research, improving predictions and enabling new experimental approaches. (* Disclosure below.) How machine learning in drug discovery is revolutionizing pharmaceutical research By leveraging AI and machine learning, companies can now conduct millions of experiments simultaneously. This scale is unthinkable without automation and advanced data analytics, Mackinnon explained. “The world of external data and the way that drug discoveries happened over the last 20, 40 years has been very targeted,” he said. “Scientists have created very specific assays and experiments that they would run just for one program at a time to develop one drug at a time. And those do exist. There are little pockets of information here or there. But really at Recursion, what we do is challenge that to some extent.” As AI continues to evolve, its role in drug discovery will only grow more significant. Companies are already seeing success in clinical trials, with new drug candidates emerging from AI-driven research methods, according to Mackinnon. “Recursion is one of the companies with the largest portfolios at the moment of clinical assets. There is a lag phase associated with that. A lot of the clinical trials going on now come from those earlier days of the research,” he said. “But, ultimately, a lot of that was enabled by the compute. A lot of that was enabled by our ability to reconsider the scientific model for disease being right, looking at the cells and trying to perturb them in different ways. So, we definitely are seeing a lot more opportunities come up.” Here’s the complete video interview, part of SiliconANGLE’s and theCUBE Research’s coverage of the Anyscale Ray Summit 2024 event : (* Disclosure: Anyscale Inc. sponsored this segment of theCUBE. Neither Anyscale nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.) Photo: SiliconANGLE A message from John Furrier, co-founder of SiliconANGLE: Your vote of support is important to us and it helps us keep the content FREE. One click below supports our mission to provide free, deep, and relevant content.