Researchers have developed a machine learning system that can predict chemical reactions, aiming to speed up drug discovery and reduce costs, according to a study published as an accelerated preview in the journal Nature on Feb. 11, 2026.
The new tool is designed to help chemists more efficiently create molecules with specific properties, particularly those with the correct "handedness" or mirror-image forms. This distinction is important because one form of a molecule may be beneficial while its counterpart could be harmful.
Matthew Sigman, chemist at the University of Utah and coauthor of the study, said, "Most AI requires enormous amounts of data to train models on. That's a problem in chemistry by which obtaining high-quality, large datasets from experimental work is very expensive and extremely time consuming. The coolest thing about this tool is that it allows someone to collect smaller bits of data, build reasonably good models and make accurate predictions for known reactions, and also transfer predictions to reactions that the models haven't seen yet."
The workflow focuses on asymmetric cross-coupling reactions—a key process in drug development where two carbon-based fragments are joined using a metal catalyst. These reactions are designed to favor one version of a molecule over its mirror image. The researchers trained their model using data from four academic papers involving nickel-based catalysts with different ligands and then tested its ability to predict outcomes for new combinations not included in the training set.
Erin Bucci, co-lead author and doctoral student at UCLA, said, "As a lab-based chemist, this tool is extremely valuable for saving time spent running experiments. For example, instead of running 50-60 reactions, we are now able to run 5-10, potentially saving weeks or months. Each reaction component we test in the lab needs to either be purchased or made from scratch—this tool greatly cuts the amount of money I would typically spend on materials."
Abigail Doyle, chemist at UCLA and coauthor of the study, added: "One of the nice things about the workflow is—it's not a black box. We can learn something about the chemistry from the predictions, even if they're off. We apply our chemistry expertise to help learn something we wouldn't have learned without the tool." Sigman said that such tools could help pharmaceutical companies optimize reactions quickly when scaling up production for clinical trials: "Optimizing a reaction and the time-cost is the value proposition when you build a drug. This streamlined process could make the difference when they need to take a molecule from phase one to phase two."
