Nvidia’s AI technology designs proteins never seen in nature, pointing the way to new therapies

Engineering techniques are already being used to design new proteins with the potential to become novel therapies. Nvidia and partner Evozyne have new research showing that their technologies have created new proteins never before seen in nature, doing it faster and with better results. They did so by studying the language of life.

Language learning patterns are now a hot topic of discussion thanks to technologies like ChatGPT, an AI software that analyzes language to answer questions and even engage in conversation with a user. Kimberly Powell, vice president of healthcare at Nvidia, says language learning techniques can also be applied to genomics, specifically the proteins encoded by our genes.

“We learned that these large language models can only understand relationships through studying the sequence of amino acids,” Powell said. “There is information about protein function when you can encode, represent and explore that data in these big language models.”

The research findings were announced at the recent JP Morgan Healthcare Conference in San Francisco. Powell discussed this during a separate briefing with reporters. The new proteins come from a collaboration between Nvidia and Evozyne, a Chicago-based protein design startup. Neither company develops new drugs, but their technologies are used by biotech and pharmaceutical companies working in drug discovery.

Nvidia and Evozyne began working together in 2022, collaborating to develop a new deep learning model that can learn the rules of protein function. Using these rules, they aimed to design new proteins with improved functions. The model was built on Nvidia’s technology for training and implementing large language models for biology.

Nvidia and Evozyne’s research focused on the phenylalanine hydroxylase (PAH) family of proteins. PAH is an enzyme needed to break down phenylalanine, an amino acid found in some foods. PAH deficiency leads to a rare disease called phenylketonuria (PKU), in which levels of phenylalanine build up in the body and cause neurological damage. Patients who have this hereditary disorder manage it by maintaining a strict diet that avoids foods containing phenylalanine.

When designing therapeutic proteins, scientists aim to make changes that improve the protein’s function without compromising its safety. In research described by Nvidia, Evozyne managed to create a PAH protein with 51 mutations. Despite all these changes, that protein was still capable of a two-and-a-half-fold improvement in function over native human PAH, Powell said. Going further, the technology was able to engineer a PAH protein with 167 mutations. Despite the modification of more than half of the protein, that version of PAH still retained its function.

PKU has few FDA-approved therapies. BioMarin Pharmaceutical markets two: the small-molecule drug Kuvan and Palynziq, an engineered enzyme designed to replace deficient PAH. But the use of these drugs does not eliminate the need for patients to continue dietary restrictions. BioMarin is also developing a gene therapy that offers the potential for a one-time treatment of enzyme deficiency.

Other companies are in various stages of development with potential PKU therapies that could help patients who are unresponsive to currently available BioMarin products. Homology Medicines is in early-stage clinical trials of a gene-editing therapy that replaces the disease-causing gene with a functional one. PTC Therapeutics has advanced into clinical trials with a small molecule drug for PKU. Earlier this month, Jnana Therapeutics received permission from the FDA to begin a Phase 1 trial of a small molecule drug candidate for the metabolic disorder.

Powell said the results from Nvidia and Evozyne hold promise for designing new protein therapies. Protein engineering methods used today include directed evolution, an approach that makes iterative modifications until the protein with the desired characteristics and functions is obtained. He said directed evolution would take months, maybe even years to achieve what Evozyne has done to design its new PAH proteins. The startup is calling its approach machine learning-driven protein engineering.

“With this ability for us to explore an essentially infinite space of proteins, to now be able to find proteins with the function you want while retaining other properties you also want, such as protein safety, here’s what I’m absolutely these unlocking methods,” Powell said.

Image by Nvidia

Add a Comment

Your email address will not be published. Required fields are marked *