July 24, 2026 · Ars Technica
Researchers use AlphaFold to make gene-editing proteins safer
A research team used Google's AlphaFold AI model to identify which parts of gene-editing proteins are responsible for unintended edits. The approach could help redesign CRISPR-related proteins to reduce off-target effects.
Why it matters: This is a concrete example of AI accelerating structural biology beyond protein-folding prediction into active protein redesign, building on AlphaFold's earlier breakthroughs. Safer gene-editing tools could speed clinical use of CRISPR therapies, an area where off-target effects have been a major safety barrier.
Related updates
- Trump administration directs $5 billion to AI-driven science projectsJul 24
- Kimi K3 lags US models on cyber exploit tests, fueling distillation claimsJul 24
- NASA runs Google's Gemma AI model in orbit to analyze satellite imagesJul 23
- Black Forest Labs' Flux 3 adds native audio to video generationJul 23