The Terray Therapeutics laboratory is a symphony of miniaturized automation. The robots whirl around, carrying tiny tubes of fluids to their stations. Scientists in blue coats, sterile gloves and protective glasses monitor the machines.
But the real action happens at the nanoscale: proteins in solution combine with chemical molecules contained in tiny wells in custom silicon chips that resemble microscopic muffin tins. Every interaction is recorded, millions and millions every day, generating 50 terabytes of raw data daily, the equivalent of more than 12,000 films.
The lab, about two-thirds the size of a football field, is a data factory for artificial intelligence-assisted drug discovery and development in Monrovia, California. It is part of a wave of young companies and start-ups trying to harness AI to produce more effective medicines, more quickly.
Companies are leveraging new technology – which learns from huge amounts of data to generate answers – to try to remake drug discovery. They are moving the field from painstaking craftsmanship to more automated precision, a shift powered by AI that learns and becomes smarter.
“Once you have the right kind of data, AI can work and become really, really good,” said Jacob Berlin, co-founder and CEO of Terray.
Most of the early commercial uses of generative AI, which can produce everything from poetry to computer programs, have been to simplify common office tasks, customer service and writing code. Still, drug discovery and development is a huge industry that experts say is ripe for an AI overhaul.
AI is a “once in a century opportunity” for the pharmaceutical sector, according to consulting firm McKinsey & Company.
Just as popular chatbots like ChatGPT are trained on text on the Internet and image generators like DALL-E learn from vast quantities of images and videos, AI for drug discovery relies on the data. And this is very specialized data: molecular information, protein structures and measurements of biochemical interactions. The AI learns patterns in the data to suggest possible useful drug candidates, as if it were matching chemical keys to the right protein locks.
Because AI for drug development relies on precise scientific data, toxic “hallucinations” are much less likely than with more extensively trained chatbots. And any potential drug must undergo extensive testing in the laboratory and in clinical trials before being approved for patients.
Companies like Terray are building large, high-tech labs to generate the information needed to train AI, enabling rapid experimentation and the ability to identify patterns and make predictions about what might work.
Generative AI can then digitally design a drug molecule. This design is translated, in a high-speed automated laboratory, into a physical molecule and tested for its interaction with a target protein. The results – positive or negative – are recorded and fed back into the AI software to improve its next design, thereby speeding up the overall process.
Although some AI-developed drugs are in clinical trials, they are still in their early stages.
“Generative AI is transforming the field, but the drug development process is complicated and very human,” said David Baker, a biochemist and director of the Institute for Protein Design at the University of Washington.
Drug development has traditionally been a costly, time-consuming, and uncertain endeavor. Studies on the cost of designing a drug and conducting clinical trials to final approval vary widely. But the total expenditure is estimated at $1 billion on average. It takes 10 to 15 years. And nearly 90 percent of drug candidates that enter human clinical trials fail, usually due to a lack of effectiveness or unanticipated side effects.
Young AI drug developers are working to use their technology to improve those odds, while reducing time and money.
Their most consistent source of funding comes from pharmaceutical giants, which have long served as partners and bankers for smaller research companies. Today’s AI drugmakers typically strive to accelerate preclinical stages of development, which typically last four to seven years. Some may try to embark on clinical trials themselves. But this is where big pharmaceutical companies usually take over, carrying out the costly human trials, which can take another seven years.
For established pharmaceutical companies, the partnership strategy provides a relatively inexpensive route to harnessing innovation.
“For them, it’s like taking an Uber to go somewhere instead of having to buy a car,” said Gerardo Ubaghs Carrión, a former biotechnology investment banker at Bank of America Securities.
Big pharmaceutical companies pay their research partners to achieve milestones on drug candidates, which can amount to hundreds of millions of dollars over the years. And if a drug is ultimately approved and becomes a commercial success, there is a stream of royalties.
Companies like Terray, Recursion Pharmaceuticals, Schrödinger and Isomorphic Labs continue their breakthroughs. But there are broadly two different paths: those that build large laboratories and those that don’t.
Isomorphic, the drug discovery spin-out from Google DeepMind, the tech giant’s core AI group, believes that the better the AI, the less data is needed. And it’s banking on its software prowess.
In 2021, Google DeepMind released software that accurately predicted the shapes that amino acid chains would fold into as proteins. These three-dimensional shapes determine how a protein functions. This has boosted biological understanding and has been useful in drug discovery, since proteins determine the behavior of all living things.
Last month, Google DeepMind and Isomorphic announced that their latest AI model, AlphaFold 3, could predict how molecules and proteins will interact – a further step in drug design.
“We focus on the computational approach,” said Max Jaderberg, director of AI at Isomorphic. “We believe there is enormous potential to be unlocked. »
Terray, like most drug development startups, is the product of years of scientific research combined with more recent developments in AI.
Dr. Berlin, the managing director, who received his Ph.D. in chemistry from Caltech, continued his advancements in nanotechnology and chemistry throughout his career. Terray grew out of an academic project launched more than a decade ago at the City of Hope Cancer Center near Los Angeles, where Dr. Berlin led a research group.
Terray focuses on developing small molecule drugs, essentially any drug a person can ingest in a pill like aspirin and statins. The pills are convenient to take and inexpensive to produce.
Terray’s sleek labs are a far cry from the academic days when data was stored on Excel spreadsheets and automation was a distant goal.
“I was the robot,” recalls Kathleen Elison, co-founder and principal scientist at Terray.
But in 2018, when Terray was founded, the technologies needed to build its industrial-style data lab were advancing at a rapid pace. Terray has relied on advances from outside manufacturers to make the microscale chips it designs. Its labs are filled with automated equipment, but almost all of it is custom, thanks to advances in 3D printing technology.
From the start, the Terray team recognized that AI was going to be crucial in making sense of its data reserves, but the potential for generative AI in drug development didn’t emerge until later – much earlier that ChatGPT becomes a resounding success in 2022.
Narbe Mardirossian, a senior scientist at Amgen, became Terray’s chief technology officer in 2020, thanks in part to its wealth of lab-generated data. Under the leadership of Dr. Mardirossian, Terray built its data science and AI teams and created an AI model to translate chemical data into mathematics, and vice versa. The company has released an open source version.
Terray has partnership agreements with Bristol Myers Squibb and Calico Life Sciences, a subsidiary of Alphabet, Google’s parent company, which focuses on age-related diseases. The terms of these agreements are not disclosed.
To expand, Terray will need funds beyond its $80 million in venture capital, said Eli Berlin, Dr. Berlin’s younger brother. He left a job in private equity to become co-founder and CFO of the start-up, convinced that technology could open the door to a lucrative business, he said.
Terray is developing new drugs for inflammatory diseases, including lupus, psoriasis and rheumatoid arthritis. The company, Dr. Berlin said, expects to have drugs in clinical trials by early 2026.
Pharmaceutical innovations from Terray and its peers can speed things up, but only to a certain extent.
“The ultimate test for us, and for the field in general, is whether in 10 years you can say that the clinical success rate has increased significantly and that we have better medicines for human health,” said Dr. Berlin.