AI agents run this autonomous biology lab: AutoDNA in Nature needs only a prompt
EricTopol · x · 2026-11-05
Nature reports AutoDNA, a 'self-driving' biology lab at Shanghai Jiao Tong University where multi-agent AI designs and executes wet-lab experiments end to end, with humans limited to hardware maintenance.
- A single user prompt (e.g. 'run a nucleic acid test') is decomposed by a planner agent coordinating protocol, reagent, code, and hardware agents, with self-correction built in.
- Robotic arms operate 20+ instrument types and execute thousands of operations per project, covering reagent assembly, mixing, tube capping, incubation, fluorescence recording, and read-out.
- Demonstrated tasks include synthesizing and sequencing DNA, such as encoding and reading out messages in DNA.
- Framed as a major step toward autonomous labs where human effort is limited to maintaining hardware.
Related event: AutoDNA: AI-native autonomous lab lands in Nature(3 posts)→
More from Embodied
- Robotics sim frontier names from World Labs, NVIDIA, PI to meet in SF on sim2real gap — jia_seed · 2026-11-05
- Robotics RL still on Isaac Lab PhysX despite mjwarp's 2x+ training speedup — carlosdponx · 2026-11-05
- Widespread broken code and training data in academic robotics projects — carlosdponx · 2026-11-05
- General Intuition: game clips (1.5T action tokens/month) train one model to control 10+ robots — AI Engineer · 2026-11-05
- CoRL paper GUILD: actively guiding robot data collection toward useful auxiliary tasks — RobobertoMM · 2026-11-05
- TAMPAgent at CoRL: coding agents + TAMP planning for zero-shot long-horizon mobile manipulation — dhadfieldmenell · 2026-11-05