Turn something old into something new. That’s the idea behind Repurpose.AI, a San Diego-based startup that combs through drug candidates that passed phase I clinical trials, but might not have made it to commercialization.
The startup recently struck a partnership with Danish drugmaker LEO Pharma, to pinpoint potential candidates for inflammatory and dermatology indications. It also began working with the Scripps Research Institute a few months ago to identify potential treatments for Covid-19.
With LEO Pharma, the partnership will be through its Open Innovation program. Repurpose.AI would be able to test any molecules it discovers using the drugmaker’s research resources.
“Collaborating with a range of partners from around the world, from academic researchers to biotechs and big pharma, allows us to connect up the dots in ways that we would not otherwise be able to,” LEO Pharma said in a news release.
Repurpose.AI searches through a library of drugs that have passed safety and tolerability tests, but have never been put to use. About 500 compounds per year fail after phase I clinical trials, CTO and Founder Dr. George Nicola said. The company can parse through roughly 15,000 of these drug candidates and another 5,000 that have gained FDA approval.
The company uses machine learning to identify patterns in the molecules that are not readily discernible. It also can extract thousands of descriptors for each molecule.
A Deep-dive Into Specialty Pharma
A specialty drug is a class of prescription medications used to treat complex, chronic or rare medical conditions. Although this classification was originally intended to define the treatment of rare, also termed “orphan” diseases, affecting fewer than 200,000 people in the US, more recently, specialty drugs have emerged as the cornerstone of treatment for chronic and complex diseases such as cancer, autoimmune conditions, diabetes, hepatitis C, and HIV/AIDS.
“It’s those subtle similarities that result in molecular activity that can only be attributable to the binding of the protein receptor,” Nicola said in a phone interview. “It’s inputting into the AI all of the features, letting it crunch the numbers and various patterns, to find those responsible for the binding. It’s much more of a brute force approach to discovery.”
Nicola teamed up with Nex Cubed Healthcare Managing Director Daniel Haders to start the company last year. Prior to founding it, he had spent time researching cheminformatics and molecular modeling at the Scripps Research Institute and at UC San Diego.
Repurpose.AI has also been developing three candidates internally for the treatment of gastric, neurological and weight disorders. Nicola said the company was still looking to move those forward, including preparing an investigational new drug filing.
Photo credit: AnuStudio, Getty Images
