Chemists harness artificial intelligence to predict the future (of chemical reactions)

To manufacture medicines, chemists must find the right combinations of chemicals to make the necessary chemical structures. This is more complicated than it sounds, as typical chemical reactions employ several different components, and each chemical involved in a reaction adds another dimension to the calculations. In an ideal world, chemists would like to predict which combination of chemicals would deliver the highest yield of product and avoid unintended by-products or other losses, but predicting the outcome of these multi-dimensional reactions has proven challenging. A group of researchers led by Abigail Doyle, the A. Barton Hepburn Professor of Chemistry at Princeton University, and Dr. Spencer Dreher of Merck Research Laboratories, has found a way to accurately predict reaction yields while varying up to four reaction components, using an application of artificial intelligence known as machine learning. They have turned their method into software that they have made available to other chemists.