AI Innovations Enhance CRISPR With Advanced Gene-editing Tools

WHO:

Phys.org - Scientists involved in the study include Jennifer Doudna, a biochemist at the University of California, Berkeley, who is the lead author of the paper.

Nature - Soeren Lienkamp, a molecular biologist at the University of Zurich in Switzerland, commented on the research.

WHAT:

Phys.org - A new study describes an AI-designed synthetic TnpB enzyme, called SynTnpBs, which has outperformed the natural reference enzyme.

Nature - The study published in Science details how scientists created synthetic CRISPR proteins that edit the genome more efficiently than naturally occurring counterparts.

Nature - The research focuses on creating synthetic versions of tiny nucleases called TnpBs, which are evolutionary precursors to the commonly used Cas12.

WHERE:

Nature - The research was conducted at the University of California, Berkeley, and the University of Zurich in Switzerland.

WHEN:

Nature - The results of the study were published on 16 July in Science.

WHY:

Nature - The motivation behind the research is to create genuinely new gene-editing enzymes with properties that have not evolved naturally, enhancing the capabilities of CRISPR technology.

HOW:

Nature - The team provided an AI model with the final conformation of a type of TnpB and asked it to reverse-engineer changes to the underlying DNA templates while maintaining the protein’s final shape.

Nature - The AI tools allow researchers to identify promising candidates for new, functional nucleases without performing hundreds or thousands of exploratory experiments.

(UPDATED July 17, 2026 18:27 UTC)

A new study led by Jennifer Doudna at the University of California, Berkeley, has introduced an AI-designed synthetic enzyme called SynTnpBs, which outperforms its natural counterpart. This groundbreaking research, conducted in collaboration with the University of Zurich, focuses on creating synthetic CRISPR proteins that edit genomes more efficiently than those found in nature, with results published on July 16 in the journal Science. By utilizing AI to reverse-engineer DNA templates while preserving the protein's structure, the team aims to develop innovative gene-editing enzymes that enhance CRISPR technology's capabilities.