After a year operating in stealth, Bahl startup, AI Proteins, emerged 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, improve its protein production technology and make further advances in the dozens of experimental treatments it is already developing for immune diseases and cancer.
Lightchain, a St. Louis company that invests in life sciences and software companies, was shocked by how quickly the startup could design and improve potential drugs. “It’s like nothing we’ve seen before. It’s almost unbelievable,” said Drew Denison, managing director of Lightchain, who is CEO of AI Proteins. “There seems to be no limit to the technology.”
The startup is the latest entrant in a large and growing field of biotech companies to make bold and often untested claims about how artificial intelligence and machine learning will help them make better drugs more quickly and at lower cost.
“There is no doubt that this space is incredibly exaggerated,” said Peter Sorger, professor of systems biology at Harvard Medical School. “Investors want to imagine that drug discovery will be easy now, and that will never be true.” He added that if AI can help make drugs 10 percent better or faster, “that’s really helpful.”
Most biotech companies focused on artificial intelligence use it to make small molecular compounds, usually administered as tablets and traditionally designed by chemists. Other companies are using machine learning to improve existing proteins. But AI proteins are one of the few pioneering technologies called “new protein design” that promise to break free from the shackles of what nature has already made.
“This produces proteins completely from scratch without an evolutionary history of anything that has been there before,” Bahl said. “It’s the field of synthetic biology that has finally become fully synthetic.”
Bahl said his startup writes its own software for designing proteins on supercomputers. He makes these proteins in the lab, runs tests on them with the help of robots, and then feeds the data from those experiments back to his computers for the next round of design, construction and testing.
Protein therapies, commonly prescribed for cancer, immune diseases and rare genetic conditions, are part of a huge global market that approached $284 billion in 2020 and is 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 turn them into better drugs. But some scientists say that designing a de novo protein will lead to drugs that cannot be made from improving existing proteins.
“We don’t start from something good and make it better. We create perfection, ideally,” said David Long, CEO of New York biotech startup Ordaōs, which raised $5 million in seed funding in August to design new proteins using machine learning. From the beginning”.
Bahl chopped his teeth to make proteins when he joined David Baker’s lab at the Institute of Protein Design in Seattle in 2012. Bahl has led the development of techniques for making a class of small synthetic proteins called small proteins that are able to bind to targets implicated in cancer or other diseases.
Powered by High-Level Micro-Protein Research Published in 2016, Bahl headed east the following year to start his own lab in Timothy SpringerIt is the newly created Institute for Protein Innovations in Boston that has combined software, robotics, and synthetic biology to develop more small proteins.
Unlike most proteins that have to be infused or injected, Bahl believes that the compact, robust structures of small proteins can protect them from digestive juices and allow people to take them as a grain. Small proteins can also be easier to manufacture and store than conventional proteins, and reach deeper into the body.
“They are small and travel everywhere in the body very quickly, so we can start treating diseases that have historically been very difficult for antibodies,” Bahl said.
As the approach began to attract more interest from drug companies, Bahl began talking to investors in July 2021 about forming his own small protein company. Just a few months later, Bahl closed his academic lab and launched AI Proteins in Andover—he couldn’t find lab space on short notice in Boston.
Ten people from Bahl Academic Lab joined his company, and the number of people working at AI Proteins has doubled since then. Later this month, the startup will be returning to Boston.
In theory, the company could make small proteins for almost any disease. “One of the big challenges we’ve had over the past year is trying to narrow it down,” Bahl said. Initially, the company makes treatments for inflammatory diseases that more accurately hit their targets to reduce side effects common in commercial drugs.
AI Proteins already has a few competitors that make small proteins, including Ordaōs. Somerville biotech startup Generate Biomedicines, which uses machine learning to engineer protein, has ambitions to design de novo protein, including small proteins.
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 start-up’s main programs are COVID-19 antibody and asthma drugs, which CEO Michael Nally hopes will be more effective and more convenient to take than existing drugs.
Improving existing medicines allows the company to reduce the risks associated with new medicines. “This is probably the bottom hanging fruit compared to designing something completely from scratch,” said Nicholas Polizzi, a protein designer at the Dana-Farber Cancer Institute. “But Generate is the company that any new startup in this field should differentiate itself from.”
Developing new proteins is not without risks. If the proteins look very different from anything in nature, there is a strong chance that we will develop immune reactions to them – which could frustrate the effectiveness of the drug and potentially cause dangerous side effects. “This is a very important downside to overcome,” Springer said.
Bahl did not disclose the diseases or the specific goals of its proprietary drug programs, but he said the company is preparing to test its three main candidates on animals. Clinical trials could come after a year or two.
“Once there is proof of concept that these drugs are safe and effective that can do things that haven’t been done before, I think a lot of people will be tempted to catch up and move into the field,” Bahl said. .