The self-driving laboratory, called AutoDNA, can analyze the “letters” that make up DNA fragments.
Credit: Turtle Rock Science/Science Source/Science Photo Library
Researchers at Shanghai Jiao Tong University in China have developed an artificial-intelligence-driven laboratory that can design and conduct molecular-biology experiments with minimal human involvement. Called AutoDNA, the system uses robotic arms to operate more than 20 types of equipment, perform thousands of operations in a project, and carry out tasks including DNA synthesis and sequencing.
Unlike conventional automated laboratories, which typically automate only selected steps, AutoDNA is designed to manage experiments from start to finish. Human operators provide simple prompts, after which a team of AI agents designs and executes the work. People are needed mainly to replenish reagents and maintain the hardware.
Inside the ‘self-driving’ lab revolution
The work, described in Nature1, is among the latest efforts to build “self-driving” laboratories guided by AI. Milad Abolhassani, a chemical engineer at North Carolina State University in Raleigh, says AutoDNA stands out for its autonomy and its ability to integrate a range of laboratory equipment. “The future of science will involve many autonomous laboratories,” he says.
Designed for autonomy
Laboratories have used automation for years to handle individual parts of experimental procedures, including mixing and heating chemicals. More recently, researchers have begun using increasingly sophisticated AI systems to create self-driving laboratories that can design and run complex experiments, troubleshoot problems, refine protocols and coordinate equipment across an entire facility.
Developing such a system for molecular biology is particularly difficult because the field involves complex workflows, many kinds of equipment and a high level of precision. Haibo Chen, a computer scientist at Shanghai Jiao Tong University and a co-author of the report, says that many existing automated systems still require a human expert to configure the equipment. In those systems, he says, “AI is almost always added to handle only part of the process.”
Chen and his colleagues therefore built AutoDNA with AI capabilities at its core, rather than adding AI to an existing laboratory system.
Encoding a message in DNA
The researchers tested AutoDNA on several projects, including the detection of cancer-related mutations in DNA samples. In another experiment, they instructed the system to encode a message in DNA using the four nucleotide bases: A, C, G and T.
The message was a quotation from cosmologist Stephen Hawking: “Intelligence is the ability to adapt to change.” The researchers selected the quotation because it is often misunderstood.
Source: www.nature.com
