Ahneman et al. (Reports, 13 April 2018) applied machine learning models to predict C–N cross-coupling reaction yields. The models use atomic, electronic, and vibrational descriptors as input features. However, the experimental design is insufficient to distinguish models trained on chemical features from those trained solely on random-valued features in retrospective and prospective test scenarios, thus failing classical controls in machine learning. A recent report by Ahneman et al. (1) describes a machine learning approach for modeling chemical reactions with data collected through ultrahigh-throughput experimentation. The Buchwald-Hartwig coupling (2) is used as a model reaction, with a Glorius interference approach (3) to study reaction poisoning by isoxazole additives. Reactions are represented by atomic, electronic, and vibrational descriptors that are automatically calculated through a new computational pipeline.

Machine learning methods are becoming integral to scientific inquiry in numerous disciplines. We demonstrated that machine learning can be used to predict the performance of a synthetic reaction in multidimensional chemical space using data obtained via high-throughput experimentation. We created scripts to compute and extract atomic, molecular, and vibrational descriptors for the components of a palladium-catalyzed Buchwald-Hartwig cross-coupling of aryl halides with 4-methylaniline in the presence of various potentially inhibitory additives. Using these descriptors as inputs and reaction yield as output, we showed that a random forest algorithm provides significantly improved predictive performance over linear regression analysis. The random forest model was also successfully applied to sparse training sets and out-of-sample prediction, suggesting its value in facilitating adoption of synthetic methodology.