Biotechnology and artificial intelligence startup Cradle of civilization It has achieved success with its generative approach to protein design, attracting major clients and a massive $24 million in new investment.
The company came out of stealth a little over a year ago, at a time when the hype around large language models was heating up. Many biotech AI companies train models to understand molecular structure natively; Cradle’s vision was that the long sequences of amino acids that make up the proteins in our bodies are like a “strange programming language.”
It may not be possible for anyone to learn that language, but an AI model can, and anyone can work with it instead. While they still can’t say “make a protein that does that,” they can ask which of the 100 interesting proteins seems most likely to survive at room temperature or in an acidic environment.
This approach appears to have caught the attention of major drug developers such as Johnson & Johnson and Novozymes. Creating a useful and functional protein from scratch is generally a very complex process, perhaps taking years and hundreds or thousands of laboratory experiments.
Cradle says its technology can reduce this time and dramatically reduce the number of experiments required. Although it didn’t really prove the claims of cutting development time in half, it did provide an illustrative example from its internal development.
They used their software to produce alternative versions of T7 RNA polymerase, an RNA-producing enzyme, that would be more resistant to high temperatures. Normally, a team might expect less than 5% of intentionally modified molecules to have the desired appearance, but 70% of the variants produced by Cradle showed increased stability, they said. This is equivalent to running four or five experimental trials in one experiment.
In addition to T7, Cradle works internally on “a dehalogenase enzyme that can be used to disinfect soil, a growth factor that promotes growth through cell division that is commonly used in cultured meat products, a transaminase enzyme that regulates metabolic pathways and helps understand some diseases as well.” . “As a therapeutic antibody,” Cradle CEO and co-founder Stef van Grieken said in an email to TechCrunch. “We benchmarked our models with an internal protein engineer using existing tools and see significant improvement in designs based on generative AI.”
(It’s this one, in case you were wondering 🙂
Image credits: Cradle of civilization
Such large improvements are possible, and small and even partial improvements would be welcomed by companies that invest millions in these processes. But of course there is more to the drug development process than simply generating potential candidate molecules.
“We have already been able to showcase the potential of our platform to accelerate the R&D phase and help our partners bring critical products to market faster and more cost-effectively,” Van Greken said. “In fact, since we and several partners have now completed several rounds of trials on our platform, we are seeing the models generalize very well across different types of proteins and tasks, which is incredibly exciting.”
The technology is by no means limited to drug development, and can be used in food and industrial applications as well. As with other tools of this type, part of the appeal for customers is that Cradle does not require a machine learning engineer to work, but can be put directly into the hands of scientists and labs.
I asked Van Greeken about his thoughts on building an EU-based biotech company, as many of the team members previously worked at big tech companies in Silicon Valley.
We have found that building in the EU has pros and cons. Deep tech venture fundraising in Europe is more complex in Europe than in the United States, where there are many contemporary “biotech” investors interested in companies like Cradle. “There is also a much larger community of like-minded founders in the Bay Area,” he said.
“However, from a talent perspective, I think Europe is underappreciated,” Van Grecken continued. “For example, here in Zurich, you have all the big big tech companies (Apple, Google, Facebook) represented by thousands of engineers. You have an amazing talent pool coming from ETH and EPFL, which are two of the best universities for computer science and molecular biology in the world. “The competition for talent is less intense than in the Gulf region. Finally, many of the world’s largest pharmaceutical and biotech companies are based in Europe, so we are close to our customers. I definitely think the European ecosystem is developing rapidly.”
Cradle’s $24 million round comes on the heels of a $5.5 million seed last year. Previous investors Index Ventures led the round, with participation from Kindred Capital (also a cornerstone investor), along with individual investors Chris Gibson, Tom Gloser and others. The company says it will use the capital to grow its team and sales, as you would.