Terray Therapeutics, a biotechnology company using artificial intelligence to accelerate the development of small-molecule drugs, said today it has raised $120 million in a Series B fundraise to enhance its AI platform.
New investor Bedford Ridge Capital and existing investor NVentures, Nvidia Corp.’s venture capital arm, led the funding round. The round also attracted investments from Maverick Capital, Goldcrest Capital, Madrona Ventures, Two Sigma Ventures, XTX Ventures, Digitalis Ventures and Alexandria Ventures. This new financing brings the total raised by the company to more than $200 million.
Small-molecule drugs are particularly sought after because of their low weight and simple chemical structures. That makes them more predictable for dosing and interactions. However, that’s not where their usefulness ends. Most of them can be administered orally and their small size means they can pass through biological membranes, such as cell walls or enter the brain, making them highly advantageous for dealing with many diseases.
Small molecules can also be tailored to interact with ribonucleic acid, or RNA – a molecule involved in protein formation. That opens up a host of new opportunities for customizing drugs to handle diseases that were originally considered unassailable by medications.
“Knowledge of what causes human disease has exploded in the ‘omics’ era, but the ability to discover and develop new molecules to treat those diseases hasn’t kept pace,” said Jacob Berlin, Ph.D, co-founder and chief executive of Terray Therapeutics. “Trained on rapidly iterating, precise data generated at unprecedented scale in our labs, Terray’s AI will dramatically improve the success rate of small-molecule development and bring relief to patients.”
Terray’s experimental platform includes a generative AI model called tNova, designed to improve the speed, cost and success rate of drug development. The company said it has built the world’s largest chemistry dataset, measuring more than 5 billion target-ligand interactions in the past three years – roughly 50 times the publicly available chemistry research data — and its dataset is doubling annually.
The number of small molecules that can be made is almost infinite, so searching it is difficult. Brute-forcing the problem, even with computational chemistry algorithms, can take years to find likely successful candidates, and even then the rates of success are low. Applying generative AI models to the process can help boost success rates by exploring past successful drugs and interactions and through work with human researchers.
With the new funding, Terray expects to expand tNova and progress internal immunology programs using small-molecule drugs toward clinical trials, all involving AI-driven optimization chemistry. The team published its chemistry foundation model, COATI, earlier this year and brought a latent diffusion machine learning model to small-molecule design for the first time.
The company also joined into partnerships with the global pharmaceutical company Bristol Myers Squibb Co. and Alphabet Inc. subsidiary Calico Life Sciences LLC, a biotech company looking into anti-aging and longevity research, to target a range of conditions.
“Terray’s unique, high-quality data generation enables continuous advanced generative AI development, like their COATI models,” said Kimberly Powell, vice president of healthcare at Nvidia. “Rapid experiments combined with advanced AI creates a molecule discovery and design flywheel able to take on the most difficult and yet to be discovered targets.”