Democratising The Science Of Protein Design With Adaptyv Bio

Artificial intelligence-powered protein design promises to transform fields ranging from drug discovery to industrial materials development. But design only gets you so far – every invention also has to be tested in the real world. Enter the Swiss start-up Adaptyv Bio, which hopes its technology will resolve this potential blockage in the innovation pipeline.

“Proteins are at the core of the bio-revolution, whether in the form of new medicines, better enzymes for research and industrial applications or as materials with novel properties,” explains Adaptyv Bio’s CEO and co-founder Julian Englert. And the advance of AI solutions such as DeepMind’s AlphaFold is game-changing in this regard, enabling researchers to automate the design of new proteins.

The problem, explains Englert, is that each new design then has to be tried out. “We’re getting very used to AI tools that generate content such as text, but with that kind of output, you can see instantly whether it works, or whether it’s gibberish,” he explains. “With an AI-designed protein, you can’t tell just from looking at it whether it will work in the way you want it to; it needs to be tested in a lab.”

That’s where Adaptyv Bio comes in. Its lab – Englert describes the facility as a “full-stack protein engineering foundry” – enables designers to test new proteins quickly and at scale. They can send hundreds or even thousands of designs to Adaptyv Bio, which uses technologies such as robotics, microfluidics and synthetic biology to test them in the lab in order to identify which works best. The process can be repeated over and again to iterate the design until it is exactly what is needed. Each new test generates data that can be used to fine-tune designs – and to improve the subsequent performance of AI-powered protein design.

Englert believes the foundry can provide a breakthrough moment for scientists, democratising the protein engineering industry. Currently, scientists without access to their own labs – largely the preserve of the largest pharmaceutical companies and industrial conglomerates – are waiting months to get test results on each new design and racking up significant costs.

Englert compares his company’s value proposition to the software development sector. “Imagine that every time you used Github Copilot to generate some code, you had to wait 10 weeks for it to execute or to tell you that it had a bug,” he says. “And imagine that each execution costs $1,000. That’s pretty much the situation for protein designers today.”

Adaptyv Bio was launched around two years ago, since when the company has been fine-tuning the technology in its Lausanne-based foundry by working with a number of clients in the biotechnology sector. “We’re now at a point where the technology is working very well on an automated basis and we’re really ready to start talking about it,” Englert adds.

The company sees the drug discovery sector as its prime target market, at least initially. In particular, small biotechnology companies, including “virtual biotechs” that have raised funding for research but have no facilities of their own, will be able to use Adaptyv Bio’s foundry to test the real-world efficacy of their protein designs.

However, protein design has applications in multiple fields, with scientists constantly working to develop new materials with specific properties. Industrial applications in the environmental sector are just one potential area of interest.

“Take a look at the proteins that make up the incredibly powerful molecular machinery inside every single one of the cells in our body,” says Englert. “Now imagine the kind of technological progress humanity could make if we could start designing novel proteins for personalised medicines, industrial applications like new enzymes, or better, more sustainable materials.”

Englert and his co-founders met at Lausanne’s Swiss Federal Institute for Technology, setting up Adaptyv Bio and developing the business as it progressed through the Y Combinator accelerator programme. It subsequently raised $2.5 million of funding from Wingman Ventures.