AI-driven drug discovery is like doing an internet search. Jacob Berlin, co-founder and CEO of Terray Therapeutics, says that with every query, your search engine learns more about you — information that influences the next set of results. The same thing happens when you scan for a movie on Netflix or shop on Amazon.com. These algorithms might not be very good at predicting what you’re looking for at first, but with more searches and more time, they improve their suggestions.
“The opportunity exists in drug discovery, but only if we have the data,” Berlin said.
There are many companies developing artificial intelligence techniques for drug research aimed at predicting which molecules are most likely to be used in therapeutic applications. But Berlin believes that the fundamental problem with AI in drug discovery is not algorithms but data, or rather the lack of data.
The data Terray generates powers its drug research, and the company is gathering better and better insights from its analysis to find small molecules that address difficult-to-treat diseases. The Pasadena, California-based startup has been quietly developing its technology for the past three years.company Appeared Secretly secured $60 million in new funding on Tuesday and plans to enter the clinic in less than two years.
Terray grew out of Berlin’s struggle to overcome the challenges he faced early in his career. He recalled his experiences doing small molecule research at Harvard, MIT and Caltech. Berlin said the process was slow, and even if he was able to find success, there were still a lot of problems left unresolved. He wanted to find a way to discover small molecules, but faster and on a larger scale.
The solution that will become Terray is the result of research that Berlin began while running a lab at City of Hope. There, his team placed the molecules in microarrays, each about the size of a nickel. These microarrays are then used to analyze molecules and select molecules for further study.
In 2018, Berlin co-founded Terray with his brother, Eli Berlin, the company’s chief financial and operating officer. Similar to Jacob Berlin’s City of Hope study, Terray uses microarrays, small chips with 32 million holes, each containing a molecule of interest. The company’s technology, called tNova, exposes these chips to targets of interest and measures the binding affinity of each molecule. Each chip can be read in less than five minutes, Eli Berlin said. In a single day, tNova can measure billions of data points. Just as Netflix and Amazon’s recommendations improve with more data and more time, so do Terray’s technology’s molecular predictions. The accumulated data becomes part of a molecular library, and the company’s technology builds up within weeks.
“AI alone is not a solution, AI is a tool that works with data,” Jacob Berlin said. “When the two are matched, the opportunities are endless. If you have the right type of data and the right AI and machine learning tools, they can work together. The data gets better and the predictions get better.”
Terray technology is not limited to any specific treatment area or target. The company’s initial focus was immunology, a field plagued by selectivity issues — molecules hitting other places than their intended target, creating side effects. By measuring many molecules and creating maps showing how they interact with their targets, Terray was able to select selective molecules from the start, Jacob Berlin said.
The targets of these molecules, and the diseases the company aims to treat, remain undisclosed. Jacob Berlin would only say that Terray is developing small molecules that can go after some of the most difficult and untreatable targets in immunology. The startup’s progress has attracted interest from some of the biotech and pharma companies that have signed up as partners to use tNova to solve their drug discovery challenges.
With the new capital, Terray will be able to advance preclinical research to support an FDA application for human trials, Jacob Berlin said. Terray’s first molecule could reach the clinic within 18 months. In addition to internal drug research, Eli Berlin said the new capital will support the startup’s efforts to collaborate more with partners (current partners remain undisclosed). Terray currently has 50 employees. With internal research and collaborative work on the rise, Eli Berlin expects that headcount could double by summer 2023.
The Series A financing announced Tuesday was led by Madrona Venture Group. Terray previously raised $20 million in an undisclosed seed round co-led by Digitalis Ventures and Two Sigma Ventures. The companies joined the Series A round, which also included participation from KdT Ventures, Goldcrest Capital, XTX Ventures, Sahsen Ventures, Greentrail Capital and Alexandria Venture Investments.
