# AI-driven design of functional viral genomes

> Live situation record from CLSTR: https://clstr.news/situations/ai-driven-design-of-functional-viral-genomes
> Updated: 2026-08-09T19:16:24.000Z. Sources: 42. Developments: 2.

Researchers from Stanford University, the Arc Institute, and the Broad Institute have utilized generative AI models—specifically the ‘Evo 1’ and ‘Evo 2’ genomic language models—to design and synthesize functional viral genomes. By training on millions of existing DNA patterns, these models produced hundreds of thousands of genome designs.

In laboratory testing, a subset of approximately 300 chemically synthesized designs, using the Phi X-174 bacteriophage as a template, resulted in 16 viable, replicating bacteriophages. These artificial viruses specifically target bacteria such as E. coli and do not pose a direct threat to humans, animals, or plants. Some of these AI-designed phages demonstrated higher efficacy or faster replication rates than naturally occurring viruses and successfully overcame existing bacterial resistance.

While the technology holds significant promise for medical advancements, such as developing new phage therapies to combat antibiotic-resistant ‘superbugs’ or targeted gene therapies, it has raised urgent biosecurity concerns. Experts warn that the capability to compose functional viral genomes could be misused to engineer harmful pathogens or biological weapons, emphasizing a critical gap in current regulatory and governance frameworks for managing rapidly advancing generative biology tools.

## Claims

- Researchers at Stanford University, the Arc Institute, and the Broad Institute used generative AI to design complete, functional viral genomes from scratch. (corroborated by 27 sources)
- Out of nearly 300 chemically synthesized AI-designed genomes, 16 resulted in viable bacteriophages. (corroborated by 26 sources)
- The 16 functional viruses were designed to infect and destroy E. coli bacteria. (corroborated by 25 sources)
- Experts warn that the ability to compose viral genomes via generative AI raises urgent biosecurity and bioprotection concerns. (corroborated by 24 sources)
- The research utilized AI models known as Evo1 and Evo2. (corroborated by 23 sources)
- Current governance and regulatory frameworks may be insufficient to manage rapidly developing generative biology tools. (corroborated by 22 sources)
- The bacteriophages created do not pose a threat to humans or animals. (corroborated by 17 sources)
- The research was published in the journal Science. (corroborated by 16 sources)

## Timeline

### 2026-08-09: Stanford researchers use AI to design functional synthetic viral genomes

Stanford researchers used AI models to design functional, synthetic bacteriophage genomes, successfully creating 16 viable viruses capable of killing E. coli, while raising significant biosecurity concerns.

6 sources. https://clstr.news/cluster/ai-models-successfully-design-functional-viruses-in-laboratory-study

### 2026-08-07: Stanford researchers use generative AI to design functional viruses

Stanford and Arc Institute researchers used generative AI models Evo 1 and Evo 2 to design functional bacteriophages that successfully destroy E. coli, offering new hope for antibiotic resistance treatments.

37 sources. https://clstr.news/cluster/stanford-researchers-use-generative-ai-to-design-functional-virus-genomes

---
Cite as: AI-driven design of functional viral genomes. CLSTR, https://clstr.news/situations/ai-driven-design-of-functional-viral-genomes