At UCLA, generative AI is drawing proteins that nature has never produced

Jason Zhang, trained in the laboratory of Nobel Prize winner David Baker, is designing new proteins by computer and testing 20,000 of them in a single experiment.

Jason Zhang, an assistant professor of bioengineering at UCLA's Samueli School, is part of the generation of researchers who are using generative AI to write amino acid sequences unknown to living things. Before joining UCLA in 2025, he worked as a postdoc in the lab of David Baker at the University of Washington, who was awarded the 2024 Nobel Prize in Chemistry for his work in computational protein engineering.

The method is based on models trained from experimental data, followed by large-scale laboratory validation: up to 20,000 engineered proteins can be tested in a single experiment, quickly closing the loop between generation and measurement. Zhang's work, supported by an NIH Pathway to Independence grant, includes biosensors, CAR-T therapies for rare liver cancers, and so-called disordered proteins involved in neurodegenerative diseases, diabetes, and several cancers.

In the longer term, the researcher envisions precision medicine where the therapeutic protein would be designed for a given patient, as the molecular understanding of diseases becomes more refined.