Researchers at the University of Liverpool have unveiled AI-driven mobile robots capable of performing complex chemical synthesis tasks with extraordinary efficiency and speed, potentially revolutionizing the field of exploratory chemistry.
Scientists at the University of Liverpool have made a significant breakthrough in chemical research by developing mobile robots equipped with artificial intelligence. These robots can execute intricate chemical synthesis tasks at a speed and efficiency previously unattainable by human researchers.
Published in the journal Nature, the study demonstrates how these advanced robots can autonomously handle exploratory chemistry tasks, including performing reactions, analyzing products and making data-driven decisions on what steps to take next.
Designed to tackle some of the most challenging aspects of chemical synthesis, the 1.75-meter-tall mobile robots collaborated to solve three critical areas of research: structural diversification chemistry (which is crucial for drug discovery), supramolecular host-guest chemistry and photochemical synthesis.
The AI function allowed the robots to make decisions comparable to those of human researchers but within a much shorter time frame.
“Chemical synthesis research is time-consuming and expensive, both in the physical experiments and the decisions about what experiments to do next, so using intelligent robots provides a way to accelerate this process,” Andrew Cooper, a professor, academic director of the Materials Innovation Factory and director of Leverhulme Research Centre for Functional Materials Design at the University of Liverpool, who led the project, said in a news release.
“When people think about robots and chemistry automation, they tend to think about mixing solutions, heating reactions, and so forth. That’s part of it, but the decision-making can be at least as time-consuming. This is particularly true for exploratory chemistry, where you’re not sure of the outcome. It involves subtle, contextual decisions about whether something is interesting or not, based on multiple datasets. It’s a time-consuming task for research chemists but a tough problem for AI,” he added.
Exploratory chemistry, where researchers often have to decide which trial reactions to scale up based on multiple contexts, such as reaction yield, product novelty or synthetic route complexity, is especially challenging for AI.
“When I did my PhD, I did many of the chemical reactions by hand. Often, collecting and figuring out the analytical data took just as long as setting up the experiments. This data analysis problem becomes even more severe when you start to automate the chemistry. You can end up drowning in data,” Sriram Vijayakrishnan, a former University of Liverpool doctoral student and the postdoctoral researcher with the Department of Chemistry who spearheaded the synthesis work, said in the news release.
“We tackled this here by building an AI logic for the robots. This processes analytical datasets to make an autonomous decision — for example, whether to proceed to the next step in the reaction. This decision is basically instantaneous, so if the robot does the analysis at 3:00 am, then it will have decided by 3:01 am which reactions to progress. By contrast, it might take a chemist hours to go through the same datasets.”
While the robots currently lack the full contextual understanding of a trained researcher, they performed comparably across various chemistry problems, making instantaneous decisions.
“The robots have less contextual breadth than a trained researcher so in its current form, it won’t have a ‘Eureka!’ moment,” Cooper added. “But for the tasks that we gave it here, the AI logic made more or less the same decisions as a synthetic chemist across these three different chemistry problems, and it makes these decisions in the blink of an eye.”
Looking forward, Cooper and his team aim to employ this technology in discovering chemical reactions relevant to pharmaceutical drug synthesis and novel materials for applications like carbon dioxide capture. The scalability potential is immense, suggesting that large industrial labs could eventually employ numerous AI-driven robots working in tandem.