Data Augmentation and Transfer Learning Strategies for Reaction Prediction in Low Chemical Data Regimes

Effective and rapid deep learning method to predict chemical reactions contributes to the research and development of organic chemistry and drug discovery. Despite the outstanding capability of deep learning in retrosynthesis and forward synthesis, predictions based on small chemical datasets generally result in a low accuracy due to an insufficiency of reaction examples. Here, we introduce a new state-of-the-art method, which integrates transfer learning with the transformer model to predict the outcomes of the Baeyer–Villiger reaction which is a representative small dataset reaction. The results demonstrate that introducing a transfer learning strategy markedly improves the top-1 accuracy of the transformer-transfer learning model (81.8%) over that of the transformer-baseline model (58.4%). Moreover, we further introduce data augmentation to the input reaction SMILES, which allows for a better performance and improves the accuracy of the transformer-transfer learning model (86.7%). In summary, both transfer learning and data augmentation methods significantly improve the predictive performance of transformer models, which are powerful methods used in the field of chemistry to eliminate the restriction of limited training data.