It’s no secret that drugs don’t work equally well for everyone. Doug Cole, chairman and co-founder of Vesalius Therapeutics, saw these limitations as a practicing physician in the 1990s. Even when doctors diagnose patients with the same disease, the condition can lead to differences in symptoms and disease progression from one person to another, he said.
Generations of doctors have known about these variants, but they couldn’t do much about them because the drugs were largely cookie-cutter, Cole said. Vesalius wants to change that. The startup is using artificial intelligence to analyze data, looking for disease patterns, to identify groups of people with common disease biology. Armed with this information, Vesalius aims to develop drugs to treat specific patient populations.Startup company in Cambridge, Massachusetts roll out On Wednesday, Flagship Pioneering secured $75 million in backing, the venture capital firm that has been incubating the young company for the past two years.
Today, the application of AI to understand disease and guide drug development is becoming more common, but much of the AI work is for rare diseases, situations in which genetic mutations can be identified, allowing scientists to focus on specific targets. This approach works for about 10 percent of diseases, Cole said. Vesalius is developing drugs to address the other 90%. Attempts to delve deeper into the disease to find patient populations have been successful. Cole pointed to cancer, where radiation therapy was widely used decades ago. Research over the years has led to the development of more targeted therapies for patients with specific genetic makeup.
“In some ways, this is a precedent [Vesalius’s approach],” he said. “How this applies to diseases where a single genetic cause cannot be found is something that people haven’t really figured out. “
Vesalius tried to figure this out. Differences in a common disease from one person to another do have a genetic basis, but these differences do not stem from a single gene mutation, but from what Vesalius called a genetic circuit in the genome. In many common diseases, these circuits don’t work properly, says Christopher Austin, former founding director of the National Center for Advanced Translational Science at the National Institutes of Health and now CEO of Vesalius. Vesalius analyzes data from a wide range of sources. Clinical data shows what disease the patient has. Billing codes provide insight into symptoms. Genetic data reveal the biology of the disease.
All data is processed in Diamond, Vesalius’ artificial intelligence-driven technology platform. The analysis divided patients into different groups based on their disease biology. Armed with this information, Vesalius can conduct experiments to screen for molecules that have the potential to restore the function of the genetic circuit. Vesalius didn’t specify which diseases it was designed to treat, but Cole said examples of common diseases include diabetes, Alzheimer’s disease and various cardiovascular diseases. Thus, startup drugs may be of various types, such as small molecules or antibodies, depending on the best way to intervene and restore the function of gene circuits in specific patient populations.
Identifying patient groups is often one of the things people think about later in the drug development process, Austin said. Often, drug research begins with a protein or gene that scientists want to target. Years later, when a drug candidate is ready for human trials, scientists consider which patients to enroll in clinical trials.
“In our view, it’s really the opposite of what you should be doing,” Austin said. “What you should be doing is pre-define who your patient population is going to be. As someone who has done a lot of recruiting for clinical trials, I think we’re going to have more success recruiting for these diseases.”
The launch of Vesalius comes amid a surge in data and new technologies for analyzing it. It’s not just a question of analyzing the data, Austin said. The experiments Vesalius ran generated additional data that had to be analyzed. Until recently, the technical tools to perform these analyses were up to the task, he said.
Vesalius is the latest company to emerge from Flagship Labs, a startup incubator for venture capital firms. Senda Biosciences, a flagship startup developing drugs based on AI analysis of how humans interact with bacteria, launched last summer.Other flagship companies Bringing AI to Drug Discovery including Generate Biomedicines and Vallo Health.
Vesalius’ main focus is developing its own medicines. But the startup’s technology also presents an opportunity to help other pharmaceutical companies. For some currently available drugs, as well as many that have failed, large numbers of people do not respond to treatment. Austin said Diamond’s ability to identify groups of patients who may respond may enable recovery or reinstatement of the drug program. The company has not yet used Diamond for such applications, but Austin said the company is now looking to partner with pharmaceutical companies for this purpose.
“It’s on our to-do list, probably as early as later this year,” he said.
Photo: metamorworks, Getty Images
