Evo 2 designs phage genomes via in-context learning, beating fine-tuned models
garykbrixi · x · 2026-10-29
A study published on Zenodo, "Efficient biological design via genomic in-context learning," shows that the genome language model Evo 2 exhibits in-context learning (ICL) usable for biological design. With as few as four examples in the prompt and no additional training, Evo 2 generates realistic metal-binding proteins, de novo antibodies, protein-RNA systems, and entire bacteriophage genomes.
For ΦX174-like phage design, ICL surpasses previously fine-tuned models on computational measures of design quality and diversity; different phage prompts enable in-silico design of MS2 and M13 genomes without fine-tuning. The authors introduce "genomic chain-of-thought" — iteratively updating the prompt with newly generated phage genomes — which further improves diversity while maintaining quality. Paired with an inference engine accelerating generation up to 35-fold and extending context to a megabase, the work establishes ICL as a versatile paradigm for biological sequence design. Code and a web app are available.
More from Research
- CVPR 2027 caps submissions at 25 per author and mandates LLM usage statements — CSProfKGD · 2026-10-30
- NUS's Xavier Bresson releases Lecture 10: GNNs Meet Large Language Models — xbresson · 2026-10-30
- One-neuron owl in Qwen3-8B fires on the chat template, not the persona — maxsloef · 2026-10-30
- WSDM 2027 to host LongSeek, first workshop on long-horizon information seeking — mrdrozdov · 2026-10-30
- Lean 4 formalization of an asymmetric metric-tensor physics paper hits GitHub — SubtleGradient · 2026-10-30
- Is sycophantic AI inflating research publications? Two mechanisms worth questioning — KLdivergence · 2026-10-30