---
id: "2025-09-12-ai-generated-phage-genomes"
url: "https://postcutoff.com/e/2025-09-12-ai-generated-phage-genomes/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2025-09-12"
date_precision: day
category: science
importance: 5
confidence: high
status: [Result confirmed]
verification: Peer-reviewed
sources: 5
editor: human editor
human_review: null
version: "2026-10-17"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2025-09-12-ai-generated-phage-genomes/

# First AI-generated complete genomes

Full title: First AI-generated complete genomes: Evo models design viable bacteriophages that kill resistant E. coli

Brian Hie's lab used the Evo 1 and Evo 2 genome language models to generate whole ΦX174-like bacteriophage genomes. Of ~285–300 synthesised designs, 16 were viable. Some rapidly overcame ΦX174-resistant E. coli, and one used an evolutionarily distant DNA-packaging protein. Preprint 12 Sep 2025; published in Science on 6 Aug 2026.

## Key facts
- Generated full ~5.4 kb ΦX174-family genomes; ~285–300 synthesised, 16 viable
- AI phage cocktails overcame ΦX174-resistant E. coli strains
- Cryo-EM showed one phage using a packaging protein from a distant lineage
- Raised biosecurity discussion about generative design of self-replicating agents
- Biosecurity debate (The Cryptonomist, Oct 16, 2026, summarizing): Johns Hopkins Center for Health Security specialists wrote that 'The ability to compose viral genomes using generative AI now exists; the governance to safely steer it does not' and urged that work on viruses infecting eukaryotes not be pursued; Jordi García Ojalvo (Pompeu Fabra) judged this experiment lower-risk because each genome needs individual lab testing and the viable yield was low (16 of about 300 designs built). The Johns Hopkins piece itself was not read

## What happened

The team prompted genome language models to write complete phage genomes, synthesised hundreds, and found 16 that infected and killed bacteria, including strains resistant to the natural phage.

## Why it matters

It is a milestone toward AI-designed life forms and phage therapies against resistant bacteria, and a biosecurity flashpoint.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [bioRxiv: generative design of novel bacteriophages with genome language models](https://www.biorxiv.org/content/10.1101/2025.09.12.675911v1) (biorxiv.org, paper)
2. [Arc Institute: first AI-designed synthetic phage](https://arcinstitute.org/news/hie-king-first-synthetic-phage) (arcinstitute.org, official)
3. [The Cryptonomist: AI generated viral genomes yield 16 viable phages, prompting safety concerns (Oct 16)](https://en.cryptonomist.ch/2026/10/16/ai-generated-viral-genomes/) (en.cryptonomist.ch, press)
4. [Stanford News: Evo 2 AI tool designs E. coli-killing bacteriophages (Science, Aug 2026)](https://news.stanford.edu/stories/2026/08/evo-2-ai-tool-e-coli-killer-bacteriophages) (news.stanford.edu, press)
5. [C&EN: AI program designs new bacteriophages](https://cen.acs.org/biological-chemistry/genomics/ai-program-designs-new-bacteriophages/104/web/2026/08) (cen.acs.org, press)

## Changes

- 2026-10-17: Biosecurity reactions (Johns Hopkins CHS, García Ojalvo) via The Cryptonomist
- 2026-09-29 (filed): Created

## Related

- 2025-02-19: [Evo 2: a 40B-parameter genome language model trained on DNA from all domains of life](https://postcutoff.com/e/2025-02-19-evo-2-genome-model/index.md)