AI news story

Team uses AlphaFold AI to redesign gene-editing proteins to make them safer

Google's AlphaFold can help ID what parts of a gene editing protein enable mistakes.

  • AI
  • Source: Ars Technica
  • Published: 2026-07-24

Editor's take

Researchers leveraged Google DeepMind's AlphaFold to identify the specific structural components of gene-editing proteins, like CRISPR-Cas9 variants, that contribute to off-target edits. This allows for the targeted modification of these proteins to minimize unintended DNA alterations.

This development holds significant implications for the precision and safety of gene therapies and diagnostics. By reducing off-target effects, the technology addresses a critical hurdle in the clinical application of gene editing, potentially accelerating the development of treatments for genetic diseases and improving the reliability of genomic research.

Future advancements will likely focus on the scalability of this redesign process and the validation of engineered proteins in diverse biological contexts. Observing whether this AlphaFold-driven approach can consistently outperform manual protein engineering in achieving higher specificity across a wider range of gene targets will be key.