De novo enzyme design has been used, primarily, in efforts to introduce active sites and substrate-binding pockets. Now, for the first time, scientists have used machine learning to create brand-new enzymes. A team from the lab of David Baker, PhD, a professor at the University of Washington School of Medicine, devised machine-learning algorithms that can create luciferases. Laboratory testing confirmed that the new enzymes catalyze the chemicals and emit light very efficiently. The luciferase technology (LuxSit) was licensed by Monod Bio—a Seattle-based biotech company.
This work is published in Nature, in the paper, “De novo design of luciferases using deep learning.”
“Living organisms are remarkable chemists. Rather than relying on toxic compounds or extreme heat, they use gentle enzymes to break down or build up whatever they need. If we could create new enzymes, that would put renewable chemicals and biofuels within reach,” said Baker, an HHMI investigator, co-founder of Monod Bio, the founder and director of IPD, and recipient of the 2021 Breakthrough Prize in Life Sciences.
To create the novel luciferases, the team first selected luciferins that they wanted the enzymes to act upon. They then used software to generate thousands of possible protein structures that might react with those chemicals.
More specifically, the authors described “a deep-learning-based ‘family-wide hallucination’ approach that generates large numbers of idealized protein structures containing diverse pocket shapes and designed sequences that encode them.” They added that they used these scaffolds “to design artificial luciferases that selectively catalyze the oxidative chemiluminescence of the synthetic luciferin substrates diphenylterazine3 and 2-deoxycoelenterazine.”
The luciferase technology developed by the Baker lab was licensed by Monod Bio, which uses computational protein design to develop a new class of modular biosensors that emit a bioluminescent signal when the sensor recognizes its target.
“We were able to design very efficient enzymes from scratch on the computer, as opposed to relying on enzymes found in nature. This breakthrough means that custom enzymes for almost any chemical reaction could, in principle, be designed,” said Andy Yeh, PhD, scientific co-founder at Monod Bio.
The company is founded on technology developed in Baker’s group, including the LucCage biosensor platform and the LuxSit de novo luciferase technology. Combining Monod’s biosensors with the de novo luciferases will create new commercial opportunities for Monod Bio.
“I am thrilled that Monod Bio will be advancing LuxSit for its use in life sciences. This is just the first example of what we can now achieve using de novo proteins for biosensors and diagnostics,” said Baker.