In a recent Science review article, UC Berkeley researchers Jennifer Listgarten and Hanlun Jiang discussed opportunities and challenges in using generative protein models and other AI methods to advance protein engineering.
“By engineering proteins, we can create new therapeutics and vaccines; design plants with enhanced resilience to environmental stressors and more efficient carbon fixation; and enable cost-effective biomanufacturing of antibiotics and materials,” the authors wrote in the Apr. 9 review article. “Few scientific fields have the potential for a broader societal impact than protein engineering.”
In recent years, Listgarten and Jiang noted, “AI has further propelled protein engineering by enabling more efficient search through high-dimensional sequence space for proteins with desired properties. Notable AI-based advances encompass generative modeling of sequences, backbone structure, and atoms; tailoring general versions of such models to design proteins with specific properties; modeling for extraction of protein representations and scoring candidate protein sequences; and developing techniques for library design, including synthesis-aware approaches.”
Upon reviewing the current use of AI in their field to improve searching and scoring of proteins, Listgarten and Jiang emphasized that laboratory testing is still needed to confirm that engineered proteins are stable, foldable and functional. They aim to encourage more baselines for publication of new AI-based methods and suggested the protein engineering community could ideally create “more robust in silico benchmark problems, using more useful metrics,” but acknowledged that “doing so for many design-related problems is itself a difficult challenge.”
Listgarten is the Jeffrey Huber and Angel Vossough Chancellor’s Chair in Computational Biomedicine and professor in UC Berkeley’s Department of Electrical Engineering and Computer Science and Center for Computational Biology, and is also affiliated with the UCSF-UC Berkeley Joint PhD Program in Bioengineering. Jiang is a postdoctoral researcher in Listgarten’s lab.
Read more
- Jennifer Listgarten and Hanlun Jiang. How artificial intelligence is reengineering protein engineering. Science 392,159-166 (2026).
