Abstract
Transition metal-catalyzed asymmetric reactions are of high contemporary importance in organic synthesis. Recently, machine learning (ML) has shown promise in accelerating the development of newer catalytic protocols. However, the need for large amount of experimental data can present a bottleneck for implementing ML models. Here, we propose a meta-learning workflow that can harness the literature-derived data to extract shared reaction features and requires only a few examples to predict the outcome of new reactions. Prototypical networks are used as a meta-learning method to predict the enantioselectivity of asymmetric hydrogenation of olefins. This meta-learning model consistently provides significant performance improvement over other popular ML methods such as random forests and graph neural networks. The performance of our meta-model is analyzed with varying sizes of training examples to demonstrate its utility even with limited data. A good model performance on an out-of-sample test set further indicates the general applicability of our approach. We believe this work will provide a leap forward in identifying promising reactions in the early phases of reaction development when minimal data is available.