Stanford's 'Virtual Lab' of AI agents designs SARS-CoV-2 nanobodies validated in the lab
James Zou's group (Nature, 2025) had an LLM 'principal investigator' agent run a team of AI scientist agents. The team built a pipeline combining ESM, AlphaFold-Multimer and Rosetta and designed 92 nanobodies. Two showed improved binding to recent SARS-CoV-2 variants (JN.1 or KP.3) while keeping binding to the ancestral spike.
Key facts
- Agents: PI agent plus specialist agents (immunology, computational biology, ML) and a critic
- 92 nanobodies designed; 2 with improved binding to JN.1 or KP.3
- Human role: high-level feedback and all wet-lab work; preprint Nov 2024, Nature 2025
Science result
- Field
- biology / antibody engineering
- Problem
- Designing nanobodies against newly emerged SARS-CoV-2 variants
- Result
- An AI-agent-designed computational pipeline produced nanobodies with improved binding to recent variants.
- AI system
- Virtual Lab (GPT-4o agents), ESM, AlphaFold-Multimer, Rosetta
- Human role
- AI-assisted: agents designed the workflow; humans gave feedback and ran experiments
- Verification
- Peer-reviewed in Nature; lab-validated
- Status
- confirmed
What happened
Instead of a single model, a simulated research group of LLM agents held "meetings", chose tools and designed an experiment that humans ran.
Why it matters
It was a peer-reviewed demonstration of multi-agent AI doing interdisciplinary research design with real lab outcomes.
Changelog
- 2026-09-29: created
Related events
- Google's AI co-scientist independently reproduces an unpublished superbug discovery in 48 hours ★★★★
- Agents4Science 2025: first conference where AI must be first author and reviewer ★★★
Sources (2)
- paperThe Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies (Nature)
- codeGitHub: zou-group/virtual-lab
id: 2025-07-29-virtual-lab-ai-agents-nanobodies · updated 2026-09-29 · open in the interactive timeline