OpenAI and Ginkgo Bioworks show how AI can accelerate scientific discovery

AI-designed, robot-led experiments suggest new approach to biology

By Deni Ellis Béchard edited by Eric Sullivan

OpenAI’s GPT can summarize research papers and make predictions, but can it do science? Can it generate hypotheses, design experiments, interpret results and iterate? Last summer, researchers from OpenAI and Ginkgo Bioworks, a company that designs and installs autonomous laboratories run by robots, decided to find out.

Although artificial intelligence systems have scored high in math, physics and computer science, biology is harder to measure, says Joy Jiao, who leads life sciences research at OpenAI. “For something like ‘design the optimal experiment,’ there is no right answer. This is what we call a hard problem: it is difficult to generate a solution, and it is also very difficult to verify it. This led the team to conduct AI design experiments using superfolder green fluorescent protein (sfGFP), an artificial jellyfish protein that is a common reference because it provides a quick and unambiguous signal: it glows green.

While OpenAI’s GPT-5 provided the experimental designs, Ginkgo Bioworks provided what its co-founder and CEO Jason Kelly calls the “Waymo” of biology: an automated laboratory system where researchers set goals and AI does the driving. The autonomous robotic laboratory can quickly process experiments and operate without constant human supervision.

On supporting science journalism

If you enjoy this article, please consider supporting our award-winning journalism by subscription. By purchasing a subscription, you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.

The team focused their experiment on cell-free protein synthesis (CFPS), a technique for producing proteins without living cells. Traditional biomanufacturing relies on genetically modifying living cells to produce drugs like insulin. CFPS makes proteins outside of cells by operating the cell’s own protein production machinery in a controlled mixture.

“It’s one of the fastest ways to make protein,” says Reshma Shetty, COO and co-founder of Ginkgo Bioworks. “You don’t need to clone your DNA, put it into the cell and wait for the cell to grow.” Improving CFPS could have significant implications for medicine, food and agricultural products.

From OpenAI’s headquarters in San Francisco, California, GPT-5 designed experiments and sent them across the country to robotic systems at Ginkgo Bioworks in Boston. As it iterated, GPT-5 analyzed incoming data and proposed new experiments, which took about an hour per cycle. “In the time it would take a human to get their coffee, sit down at their computer, log in and get ready to work, the model could collect the data, analyze it and come up with new experiences,” Shetty says.

“At the beginning of this project, I didn’t know if we could design a single experiment,” says Jiao. “I remember when the experimental results came back, the reaction on both sides was like, oh, we made a non-zero amount of protein, and that was somewhat surprising.”

After two months and more than 36,000 tests of unique reaction compositions, the AI-driven system reduced the cost of producing the protein by about 40% compared to a previously reported benchmark from the lab of bioengineer Michael Jewett at Stanford University. “Honestly, it’s a big deal,” says Jewett, whose lab published its own seminal paper last week in Natural communications. “How can we develop drugs faster to deliver life-saving therapies to patients more quickly? I think the integration of artificial intelligence and autonomous laboratories is one way to do this.”

The OpenAI-Ginkgo Bioworks collaboration also produced a moment of unexpected novelty. When the team gave GPT-5 access to new reagents, “they tried to fit in as many as possible,” Jiao says. “So the model set the amount of water to something negative.” Starting an experiment with a negative volume of water is not possible. In the laboratory, when Ginkgo Bioworks’ robot technicians noticed the problem, they still carried out the experiments with an overall volume slightly higher than that specified.

The AI-enhanced reaction composition is now commercially available. Most importantly, on March 2, Ginkgo Bioworks launched its Ginkgo Cloud Lab, which allows researchers anywhere to submit experiments to autonomous laboratory systems starting at just $39 per analysis. Meanwhile, the U.S. Department of Energy is funding a 97-robot autonomous laboratory at the Pacific Northwest National Laboratory in Washington state. The laboratory will be built by Ginkgo Bioworks and is expected to become operational by 2030.”[AI] models alone will not be enough,” says Shetty. “You need models coupled with labs that can do experimental validation.”

It’s time to defend science

If you enjoyed this article, I would like to ask for your support. Scientific American has been defending science and industry for 180 years, and we are currently experiencing perhaps the most critical moment in these two centuries of history.

I was a Scientific American subscriber since the age of 12, and it helped shape the way I see the world. SciAm always educates and delights me, and inspires a sense of respect for our vast and magnificent universe. I hope this is the case for you too.

If you subscribe to Scientific Americanyou help ensure our coverage centers on meaningful research and discoveries; that we have the resources to account for decisions that threaten laboratories across the United States; and that we support budding and working scientists at a time when the value of science itself too often goes unrecognized.

In exchange, you receive essential information, captivating podcasts, brilliant infographics, newsletters not to be missed, unmissable videos, stimulating games and the best writings and reports from the scientific world. You can even offer a subscription to someone.

There has never been a more important time for us to stand up and show why science matters. I hope you will support us in this mission.