David Baker's University of Washington group tested 135 AI-designed zinc proteases, and 36% cut their target peptides. Cysteine designs fared worse, with 13 of 69 cutting theirs, and both rates come from a bacterial screen.
Reality
- Evidence72
- Adoption
- Not scored
- Hype gap+15
- Incentives
- Not scored
- Confidence68
AlphaFold predictions helped ITQB NOVA engineer a bacterial galactose oxidase
ITQB NOVA researchers engineered PsGalOx, which they call the first bacterial galactose oxidase, into a variant 40 to 1,800 times more efficient. The team says much of the gain in directed evolution came from cells making more protein; drug substrates are still ahead.
Reality
- Evidence50
- Adoption
- Not scored
- Hype gap+15
- Incentives
- Not scored
- Confidence55
Plant enzymes evolved to sort mirror-image molecules through a key active-site mutation plus peripheral changes
A Berlin-led team rebuilt ancient plant enzymes and traced their choice between two mirror-image molecules to 19 mutations, just one in the active site. The Nature Communications study points enzyme engineers toward protein dynamics as the lever for building selectivity.
Reality
- Evidence55
- Adoption
- Not scored
- Hype gap+10
- Incentives
- Not scored
- Confidence55
Fluorescence loss lets a microplate reader screen thousands of BsPPS enzyme variants
National Taiwan University researchers built a fluorescence assay that screens thousands of BsPPS enzyme variants on a standard microplate reader. It replaces slow HPLC during screening and flagged one heat-tolerant variant, G145D.
Reality
- Evidence55
- Adoption12
- Hype gap0
- Incentives55
- Confidence45
MutexaGPT translates a chemist's plain-English hunch into a configured physics workflow
Its agents interview the user for what the request leaves out, then build and run the modelling. The paper shows this on two enzymes, which demonstrates the pipeline rather than measuring how often it is right.
Reality
- Evidence48
- Adoption
- Not scored
- Hype gap+30
- Incentives65
- Confidence52