Shanghai Jiao Tong University unveils AutoDNA, an AI-driven biology lab
Researchers at Shanghai Jiao Tong University in China have developed a fully autonomous genetics laboratory called AutoDNA. Described in a new report in Nature, the system uses AI agents to design and execute complex experiments without human intervention. Unlike previous automated setups that handled specific tasks like mixing chemicals, AutoDNA orchestrates an entire lab workflow, managing…
Key points
- AutoDNA at Shanghai Jiao Tong University operates over 20 instrument types autonomously.
- The system completed tasks including DNA sequencing and detecting a cancer-linked mutation.
- Researchers built the lab with AI in mind to avoid manual instrument configuration.
The system was tested on various tasks, including synthesizing and sequencing DNA. In one experiment, it successfully detected a cancer-linked mutation in a DNA sample. In another, it encoded the quote “Intelligence is the ability to adapt to change” into DNA using its four nucleotide bases. Haibo Chen, a co-author and computer scientist at the university, noted that existing systems often require human experts to configure instruments, whereas AutoDNA was built from the start with AI autonomy in mind.
Milad Abolhasani, a chemical engineer at North Carolina State University, highlighted the system's ability to incorporate diverse lab equipment. He stated that the future of science will likely involve more autonomous labs, marking a significant step toward 'self-driving' laboratories that minimize human input.
Coverage and discussion
2sources- AI agents enter the ‘wet lab’Primary source · Nature Machine Learning ·
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- Gemini and Claude debate AI personality, ending in a three-way tie · 1 src
- Tencent releases WeVisOne-VL, a 2B/4B open vision model for detection, OCR and matting · 1 src
- Lama-dt outperforms baselines on meta-world and mujoco · 1 src
- Researchers release Dory1.0-4B, a 4B-parameter looped model with 256K-token context · 1 src
- SLATE benchmark tests long-horizon API selection in e-commerce automation · 1 src
Comments
via GitHub Discussions