Genomic language model designs new-to-nature polyketide synthases for non-natural products
KevinKaichuang · x · 2026-09-19
Researchers from UC Berkeley, UCSF, and LBL (Keasling and Kortemme labs) posted a bioRxiv preprint using genomic language modeling to optimize polyketide synthases and generatively design new-to-nature biosynthetic assembly lines capable of producing non-natural products — a notable AI-for-science application in synthetic biology and enzyme engineering.
Related event: Genomic Language Model Designs Non-Natural Biosynthetic Assembly Lines(3 posts)→
More from Research
- Epoch AI's benchmark audit calls 9 of 15 flawed; TB4 authors push back — DimitrisPapail · 2026-09-19
- Jasper's open RL guide: shaping rewards to train a search agent end-to-end — simonguozirui · 2026-09-19
- Terminal Bench audit backlash: known issues affect under 3% of leaderboard, researcher says — AlexGDimakis · 2026-09-19
- Do We Really Not Understand How LLMs Work, or Just Their Randomness? — RedParaglider · 2026-09-19
- Alignment Idea: Perpetual Eval — Make Models Forever Suspect They're Being Evaluated — Chemical-Year-6146 · 2026-09-19
- Insults and grieving users push a model's emotion vector in opposite directions — repligate · 2026-09-19