{
  "abstract": "In-context learning (ICL), the ability to perform new tasks from a few examples supplied in a prompt, is a defining emergent capability of large language models. Here, we show that ICL emerges in the genome language model Evo 2 and enables 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 {Phi}X174-like bacteriophage design, ICL surpasses previously fine-tuned models on computational measures of design quality and diversity. Beyond {Phi}X174, conditioning the model with different phage prompts enables us to efficiently design MS2 and M13 genomes in silico without fine-tuning. Iteratively updating the prompt with newly generated phage genomes, which we refer to as genomic chain-of-thought, further improves the diversity of designs while maintaining quality metrics. Paired with an inference engine that accelerates generation up to 35-fold and extends practicable context to a megabase, these results establish ICL as a versatile and efficient paradigm for biological sequence design.",
  "abstract_shown": true,
  "affiliations": [
    "Stanford University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "name": "G. Brixi"
    },
    {
      "name": "Y. A. Hao"
    },
    {
      "name": "D. Nori"
    },
    {
      "name": "A. Merchant"
    },
    {
      "name": "T. Widatalla"
    },
    {
      "name": "S. King"
    },
    {
      "name": "K. Shalvarjian"
    },
    {
      "name": "D. Park"
    },
    {
      "affs": [
        0
      ],
      "name": "B. Hie"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/b2dydsp4qceat.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.28.762643",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762643v1.full",
  "id": "b2dydsp4qceat",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762643v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762643v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/b2dydsp4qceat.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:30:26Z",
      "native_id": "10.64898/2026.10.28.762643",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762643v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Efficient biological design via genomic in-context learning",
  "title_text": "Efficient biological design via genomic in-context learning",
  "type": "preprint",
  "updated_at": "2026-10-31T00:20:46Z",
  "url": "https://research.draconitic.com/paper/b2dydsp4qceat",
  "venue": "bioRxiv",
  "versions": []
}