Posted in | News | Consumer Robotics

Robots Outperform Humans in Chemistry Research

Researchers from the University of Liverpool demonstrated in a study published in the journal Nature how mobile robots that make decisions using artificial intelligence (AI) logic could complete exploratory chemistry research tasks just as well as humans but much more quickly.

Mobile robots use AI logic to perform exploratory chemistry research tasks
Mobile robots use AI logic to perform exploratory chemistry research tasks. Image Credit: University of Liverpool

Researchers created mobile robots powered by AI that are incredibly efficient at conducting chemical synthesis research.

The Liverpool team created the 1.75-meter-tall mobile robots to address three main exploratory chemistry challenges: carrying out the reactions, evaluating the products, and making decisions based on the data.

Together, the two robots tackled problems in three distinct areas of chemical synthesis: supramolecular host-guest chemistry, photochemical synthesis, and structural diversification chemistry, which is important for drug discovery.

According to the findings, the mobile robots using the AI function made decisions that were identical to or similar to those made by a human researcher, but they did so much more quickly—hours even—than a human could.

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, Professor, Department of Chemistry and Materials Innovation Factory, University of Liverpool

Cooper added, “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 are not sure of the outcome. It involves subtle, contextual decisions about whether something is interesting or not, based on multiple datasets. It is a time-consuming task for research chemists but a tough problem for AI.”

Decision-making is a critical issue in exploratory chemistry. For example, a researcher could execute several trial reactions before deciding to scale up only those that produce high reaction yields or interesting products. This is difficult for AI to do because whether something is 'interesting' and worth pursuing can take many forms, such as the novelty of the reaction product or the cost and complexity of the synthetic route.

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.

Dr Sriram Vijayakrishnan, Postdoctoral Researcher, Department of Chemistry, University of Liverpool

Dr. Vijayakrishnan added, “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.

Professor Cooper added: “The robots have less contextual breadth than a trained researcher so in its current form, it won’t have a “Eureka!” moment. 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. There is also huge scope to expand the contextual understanding of the AI, for example by using large language models to link it directly to relevant scientific literature.

The Liverpool team hopes to use this technology in the future to find new materials for applications like carbon dioxide capture and chemical reactions related to pharmaceutical drug synthesis.

The study employed two mobile robots, but the number of robot teams that could be employed is unlimited. This method could, therefore, be applied to the largest industrial laboratories.

This new study expands on Professor Cooper's group's 2020 description of the world’s first “mobile robotic chemist". Over eight days, the team worked around the clock to complete nearly 700 catalysis experiments.

The project was funded by the European Research Council, the Engineering and Physical Sciences Research Council, and the Leverhulme Trust.

Journal Reference:

Dai, T. et. al. (2024) Autonomous mobile robots for exploratory synthetic chemistry. Nature. doi.org/10.1038/s41586-024-08173-7

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.