Nature paper describes AutoDNA, an AI-run lab that carried out DNA synthesis, sequencing and other experiments with little human help
Nature · Research paper
Read the source (opens in a new tab)- What happened
- Researchers led by Shanghai Jiao Tong University published a paper in Nature on November 4, 2026, describing AutoDNA, an AI-native laboratory that autonomously runs nucleic acid experiments across lab instruments.
- Key points
- The system "autonomously orchestrates over 20 types of instruments across more than 11,000 steps" to run nucleic acid operations including synthesis, transcription, amplification and sequencing.
- The authors say "human intervention is limited to hardware maintenance tasks, such as reagent and labware replenishment."
- In four applications it matched expert-optimized enzymatic DNA synthesis yields, ran concurrent protocols 3.2-fold faster, completed a DNA data storage cycle and identified a clinically detected KRAS G13D mutation.
- The authors call it "a blueprint towards science-as-a-service" and have released the code on GitHub.
- Evidence
- Peer-reviewed paper in Nature. The full text is paywalled; this entry rests on the public abstract and the article page's availability and author sections.