By Hessie Jones
If you ask Jeff Skinner, CEO of stoked bio, he insists they are not an AI Company — they are a drug development company. We sat down with Jeff Skinner, the winner of the First Look Pitch Competition at the Founder and Funders Event, to learn more about the company and how the marriage between AI and biology will hasten the process towards medical cures.
Stoked bio leverages AI to develop novel therapeutics to treat resistant infectious diseases in cancer. As Skinner explains, “These therapeutics are identified using a biology first process that is augmented by AI. Because it’s a biology first process, the therapeutics that we’re identifying are not just statistically significant, but biologically meaningful.” AI, Skinner explains, will help to reduce the number of failures in drug development.
In a recent Macleans article, John Stokes, cofounder and scientist at stoked bio, explained the drawbacks of current processes that hinder the time to get drug development to market quickly,
“More recently, researchers assembled libraries of millions of synthetic chemicals and individually tested which ones kill pathogenic bacteria. This process—called high-throughput screening—is time-consuming and expensive. In the end, it yielded zero clinically used antibiotics.
In 2019, there were approximately 1.3 million deaths due to drug-resistant bacterial infections. By 2050, that number is expected to increase to 10 million per year, at which point it will surpass cancer as a cause of death. Antibiotics uphold all of modern medicine. If we can’t control infection, we can’t perform a lot of the medical interventions that we take for granted, such as routine surgeries and cancer chemotherapy.”
He explains that at the earliest stages, AI can help by predicting “new chemicals to address therapeutic challenges more efficiently than testing chemicals in the laboratory.”
This creates an opportunity for these therapeutics to help scale the drug development process with significant savings in time and money with the potential to get to market “in months, not decades.”
Currently, these therapeutics are developed at McMaster University, with Stokes at the helm. They are advancing these compounds to preclinical development and will engage in partnership with a pharmaceutical company once they develop the data package.
From Lab to Market
Chris Sinclair and John Stokes were friends, and their wives are both practicing physicians in the same clinic. Sinclair, an already successful entrepreneur in and outside of biotechnology, also had a brand and merchandising business. Stokes was a pure academic scientist, and assistant professor of biochemistry and biomedical sciences at McMaster University.
During his post doctorate at the Broad Institute at MIT and Harvard, he was introduced to an approach using AI as a fantastic tool to improve the process of identifying novel therapeutics. When he returned to McMaster, he started to implement this idea in his labs — 50% wet lab for biology and the other half for computer science. This merger between biology and AI created a process to identify novel anti-infectives, in other words, medicines to prevent or treat infections.
Stokes was part of the research team behind “SyntheMol,” a “generative AI model able to create new antibiotics to fight Acinetobacter baumannii, a deadly bacterium associated with hospital-acquired infections.
Sinclair and Stokes saw an opportunity to bring this capability to market, with the potential of applying this approach to urgent clinical needs targeting bacterial, fungal, viral infections.
Jeff Skinner, who was a seasoned executive in management and business development with 25 years in the biotech and pharmaceutical industry, soon came into the picture to round out the team.
Therapeutics to Treat Cancer and Infectious Diseases
Stokes had a recent conversation with a well-known Glioblastoma surgeon, Dr. Sheila Singh, who created a bio bank of samples from brain tumors. The question she posed to Stokes: Could your process identify novel therapeutics to treat this aggressive and deadly medical condition? His response was an emphatic yes.
Today, stoked bio is developing novel therapeutics for anti-infectives and high-need oncology applications, starting with Glioblastoma.
Skinner admits they’ve identified a number of novel therapeutics to treat the disease at least in the early stages, “We’re actually reiterating that back into models to improve so we’ve got some real-world information based on our experiments.”
While they are still in the very early stages with Glioblastoma, for infectious diseases they currently have two programs — for E coli infections in the gut and the other, for staphylococcus in the skin. Their models are generating therapeutics that can “complete the task that has been set forward, first demonstrated in animal data,” which still needs to advance into full preclinical development.
Revolutionizing a Process to Accelerate Drug Discovery
Skinner explains that a typical period for discovery can take three years. Preclinical development will add another four years before human testing. In addition, clinical testing can take five to ten years before a drug is developed. For stoked bio, early-stage discovery can be done in a matter of months, not years. And in that time, this process will identify better compounds to reduce the preclinical development by reducing the number of failures. He explains,
“For every drug that is approved, you have to find 10,000 new compounds. Of these, 9,999 failed along the way. Before that one drug is finally approved, we are trying to improve that failure rate. If we improve this by an order of magnitude of 10, this will mean finding just one successful drug per 1,000 tested, instead of one per 10,000.”
This would be enormous progress. With stoke bio’s models able to identify failing compounds as early as possible, this can avoid investing millions of dollars into doomed projects quickly.
Skinner adds, “We’re optimizing the drug for 15 to 25 characteristics. Because of all this, these are the ones that have the best chance of proceeding through the entire development process. So, we’re trying to significantly condense the amount of dollars spent at these early stages.
Currently Raising
Stoked bio is currently raising $3 million, with over $1million already committed. The current pre-money valuation is $7.5 million.
This ask will be applied to advancing the Glioblastoma compound into formal preclinical development and engaging in a second cancer program. This will also be used to develop a revenue-generating partnership, with the intention to partner at the pre-clinical stage.
Jon Stokes explains how AI can discover new drug therapies. Watch the video: https://www.youtube.com/watch?v=WjDOS5Lxij0
If you’re interested in learning more about stoked bio, please contact Jeffery Skinner at jeff@stokedbio.com.
