AI-designed proteins can produce evolution paths that outperform natural ones
EricTopol · x · 2026-07-22
A new study argues that AI can design protein starting points that are better than natural ones for subsequent evolution.
The paper says the authors used AI-based protein sequence design to redesign three botulinum proteases, then ran side-by-side evolution campaigns against wild-type proteins. The redesigned proteins produced more active and more stable evolved variants, and one route achieved 79× greater selected specificity for ataxin‑2 than the best wild-type-derived variant.
The takeaway is a practical workflow: use AI-redesigned proteins as starting points to unlock evolutionary paths that are otherwise hard to reach.
More from Research
- FlexGlue: sparse-to-dense matching that beats dense accuracy at a fraction of the cost — zhenjun_zhao · 2026-10-27
- Mundo turns a few room photos into an explorable, simulatable 3D world — at 1.5 FPS — mark_k · 2026-10-27
- Mathematics as an experimental science: Marc Lelarge to talk LLM-driven math experiments at ENS — marc_lelarge · 2026-10-27
- DOE Genesis Mission Phase II: AI for particle accelerators and rare isotope separation — prescott · 2026-10-27
- Tenstorrent runs Proteina protein model at high throughput, claims no HBM shortage — gajesh · 2026-10-27
- Deepity: hand-tuned C++/CUDA predictive coding library beats jpc and ngc-learn on MNIST — Important-Home4431 · 2026-10-27