After a year of working in stealth mode, Bahl’s startup AI Proteins emerged on Thursday with $18.2 million in seed funding led by venture capital firms Cobro Ventures and Lightchain Capital. The money will help the startup, where Bahl is president and chief scientific officer, refine its protein-creating technology and advance on a dozen experimental therapies it is already developing for immune diseases and cancer.
Lightchain, a St. Louis firm that invests in life science and software companies, was shocked by how quickly the startup could design and optimize potential drugs. “It’s unlike anything we’ve seen before. It’s almost unbelievable,” said Drew Dennison, chief executive of Lightchain, who serves as chief executive of AI Proteins. “It feels like there’s no limit to the technology.”
The startup is the latest in a vast and growing field of biotech companies making bold and often untested claims about how artificial intelligence and machine learning will help them make better drugs faster and better. cheaper.
“There’s no question that this space is incredibly overhyped,” said Peter Sorger, professor of systems biology at Harvard Medical School. “Investors want to imagine that drug discovery is going to be easy now, and that will never be true.” But if artificial intelligence can help make drugs even 10% better or faster, “that’s really significant,” he added.
Most AI-driven biotechnology uses it to make small-molecule compounds, usually delivered in pill form and traditionally designed by chemists. Other companies are using machine learning to optimize existing proteins. But AI Proteins is one of the few pioneers of a technique called “de novo protein design” that promises to break free from the constraints of what nature has already done.
“It’s about creating proteins totally from scratch, with no evolutionary history compared to anything that’s come before,” Bahl said. “This is the field of synthetic biology finally becoming fully synthetic.”
Bahl said his startup writes its own software to design proteins on supercomputers. He manufactures these proteins in the lab, tests them with the help of robots, and then feeds the data from these experiments back into his computers for the next phase of design, construction and testing.
Protein therapies, commonly prescribed for cancer, immune diseases and rare genetic diseases, are part of a huge global market worth approaching $284 billion in 2020 and expected to nearly double to $567 billion. by 2030, according to a report by QY Research Medical.
Many of these proteins have already been modified by scientists to make better drugs. But some scientists say designing proteins de novo will lead to drugs that can’t be made from optimizing existing proteins.
“We don’t start from something good and improve it. We create perfection, ideally, from the start,” said David Long, chief executive of New York-based biotech startup Ordaōs, which raised $5 million in seed funding in August to design new proteins with learning. automatique.
Bahl cut his teeth making proteins when he joined the lab of David Baker at the Institute for Protein Design in Seattle in 2012. Bahl led the development of techniques to make a class of small synthetic proteins called miniproteins capable of binding to targets implicated in cancer or other diseases.
Building on the high-profile miniprotein research published in 2016, Bahl headed east the following year to start his own lab at Timothy Springer’s new Institute for Protein Innovation in Boston, where he combined software, robotics and synthetic biology to develop more miniproteins. .
Unlike most proteins, which must be infused or injected, Bahl believes the compact and sturdy structures of miniproteins could protect them from digestive juices and allow people to take them as a pill. Miniproteins might also be easier to make and store than traditional proteins and penetrate deeper into the body.
“They’re small and they go all over the body very quickly, so we can start fighting diseases that have always been very difficult for antibodies,” Bahl said.
As the approach began to attract more attention from pharmaceutical companies, Bahl began talking to investors in July 2021 about starting his own miniprotein company. A few months later, Bahl closed his university lab and launched AI Proteins in Andover. He could not find lab space on short notice in Boston.
Ten people from Bahl’s university lab joined his company, and AI Proteins’ workforce has since doubled. Later this month, the startup returns to Boston.
In theory, the company could make miniproteins for just about any disease. “One of the big challenges we’ve struggled with over the last year is trying to narrow it down,” Bahl said. For starters, the company manufactures inflammatory disease therapeutics that hit their targets more precisely to reduce the common side effects of commercial drugs.
AI Proteins already has a handful of competitors making miniproteins, including Ordaōs. Somerville biotech startup Generate Biomedicines, which uses machine learning for protein engineering, also has ambitions for de novo protein design, including miniproteins.
Generate has raised at least $470 million from investors and partners since its launch in 2018 by Flagship Pioneering, the life sciences investment firm behind Moderna. The startup’s main programs are antibodies for COVID-19 and asthma, which chief executive Michael Nally hopes will be more effective and convenient to take than existing drugs.
Improving existing drugs allows the company to minimize the risks associated with new drugs. “It’s probably the lowest fruit compared to designing something completely from scratch,” said Nicholas Polizzi, protein designer at the Dana Farber Cancer Institute. “But Generate is the company any new startup in this space needs to stand out from.”
Developing new proteins is not without risk. If the proteins really look completely different from anything in nature, chances are we’ll develop immune reactions against them, which could thwart the drug’s effectiveness and potentially cause dangerous side effects. “It’s a very significant drawback that needs to be overcome,” Springer said.
Bahl did not disclose specific diseases or targets for its initial drug programs, but he said the company is preparing to test its three lead candidates in animals. Clinical trials could take place a year or two after that.
“As soon as there is proof of concept that these are safe and effective drugs that can do things that haven’t been done before, I think a lot of people will be racing to catch up and move into this space. “, said Bahl. .
Ryan Cross can be contacted at ryan.cross@globe.com. Follow him on Twitter @RLCscienceboss.