Guidelines for Machine Learning Yield Prediction from Small-Size Literature Dataset

Synthetic yield prediction using machine learning is intensively studied. Previous work focused on two categories of datasets: High-Throughput Experimentation data, as an ideal case study and datasets extracted from proprietary databases, which are known to have a strong reporting bias towards high yields. However, predicting yields using published reaction data remains elusive. To fill the gap, we built a dataset on nickel-catalyzed cross-couplings extracted from organic reaction publications, including scope and optimization information. We demonstrate the importance of including optimization data as a source of failed experiments and emphasize how publication constraints shape the exploration of the chemical space by the synthetic community. While machine learning models still fail to perform out-of-sample predictions, this work shows that adding chemical knowledge enables fair predictions in a low-data regime. Eventually, we hope that this unique public database will foster further improvements of machine learning methods for reaction yield prediction in a more realistic context.