AlphaFold-guided protein engineering screens 45,000 oxidases and 500 million variants

pushmeet · x · 2026-07-21

Research teams are using AlphaFold beyond structure prediction to tackle protein engineering problems.

• The cited work used AlphaFold to search 45,000 oxidases and then screened more than 500 million engineered variants via directed evolution.
• The goal is to reverse sugar-induced protein damage, which is linked to aging effects on skin, arteries, eyes, and other tissues.
• The result is still ex vivo in a lab setting; safely delivering a large bacterial enzyme into living tissue remains a major challenge.
• The post frames AlphaFold Database as a five-year-old open resource that is helping experimental biologists uncover structural blind spots.

Original post →

More from Research

• Style-similarity analysis puts Kimi K3 closer to Claude Fable 5 than to K2.6 — soumitrashukla9 · 2026-07-21
• A GLP1R variant may explain stronger Ozempic weight loss, and the team built an agent workflow — julia_kiseleva · 2026-07-21
• Proceedings for the second geometry-grounded representation learning workshop are now online — erikjbekkers · 2026-07-21
• New survey maps how agentic systems are learning to improve themselves — SchmidhuberAI · 2026-07-21
• A curated TTS list for voice agents tracks latency, cancellation, and evals — mahimairaja · 2026-07-21
• Jacob Tsimerman interview frames LLMs as a turning point for mathematical discovery — stevenstrogatz · 2026-07-21

Research channel →