Genomic Language Model Designs New-to-Nature Biosynthetic Assembly Lines
KevinKaichuang · x · 2026-09-19
A UC Berkeley/UCSF team posted a bioRxiv preprint using a genomic language model to generatively design new-to-nature biosynthetic assembly lines — polyketide synthases that produce non-natural products. The poster notes they used the genomic LM to optimize a polyketide synthase for a non-natural product. Authors include Tanja Kortemme and Jay Keasling.
Related event: Genomic Language Model Designs Non-Natural Biosynthetic Assembly Lines(3 posts)→
More from Research
- New paper: looping with model growth improves scaling exponent, matches GPT-3 with 20x less compute — burny_tech · 2026-09-19
- Dream-RSI: Google and DeepMind propose replay-simulator framework for recursive self-improvement in AI agents — burny_tech · 2026-09-19
- Tsinghua paper: RL fine-tuning prunes exploration, letting base LLMs beat RL models at high pass@k — burny_tech · 2026-09-19
- Async RL is just horizontal scaling with sticky routing, one dev argues — dosco · 2026-09-19
- Neuron: The recipe for intelligence in natural and artificial systems — AnnaCiaunica · 2026-09-19
- CoT may not be faithful: filler tokens add 13 points, models keep reasoning after committing — ziv_ravid · 2026-09-19