Slower enzyme, more product: DLCatalysis lifts NeuAc yield from 8.54 to 9.27 g/L
bravo_abad · x · 2026-09-06
A thread unpacks Wang et al.'s enzyme-engineering study with the thesis "don't optimize the proxy — optimize the whole scientific system": making the terminal enzyme NeuB faster doesn't necessarily raise cell output, since its substrate phosphoenolpyruvate is also needed for growth and central metabolism.
- DLCatalysis ranked 6,612 NeuB variants, combining ProtT5 protein-sequence embeddings, molecular fingerprints, and graph-based substrate representations via bidirectional cross-attention.
- Crucially, the team sampled across the predicted activity range rather than testing only top-ranked mutants.
- A less active NeuB variant raised NeuAc production from 8.54 to 9.27 g/L by better balancing product formation with cell metabolism.
Takeaway: sampling beyond the top of model rankings reveals that fastest ≠ best, and proxy metrics must serve system-level goals.
More from Research
- OpenAI and Anthropic models share a favorite name, writing benchmark finds — almmaasoglu · 2026-09-07
- Five-model writing style comparison shows average sentence length misses the mark — almmaasoglu · 2026-09-07
- Felda AI builds writing benchmark analyzing names, punctuation and sentence rhythm — almmaasoglu · 2026-09-07
- Claude Works Autonomously for 11 Days to Produce First Computer-Checked Proof of Fermat's Last Theorem — satnam6502 · 2026-09-07
- AI startup Felda dissects writing quality down to sentence rhythm and punctuation in its new benchmark — almmaasoglu · 2026-09-07
- TailRL optimizes reward tails instead of mean, cutting samples 256x on GUI grounding — burny_tech · 2026-09-07