Intermediate Knowledge Enhanced the Performance of N-Acylation Yield Prediction Model

Acylation is an important reaction widely applied in medicinal chemistry. However, yield optimization remains a challenging issue due to the broad conditions space. Recently, accurate condition recommendations via machine learning have emerged as a novel and efficient method to achieve the desired transformations without a trial-and-error process. Nonetheless, accurately predicting yields is challenging due to the complex relationships involved. Herein, we present our strategy to address this problem. Two steps were taken to ensure the quality of the dataset. First, we skillfully selected substrates to ensure diversity and representativeness. Second, experiments were conducted using our in-house high-throughput experimentation (HTE) platform to minimize the influence of human factors. Additionally, we proposed an intermediate knowledge-embedded strategy to enhance the model’s robustness. The performance of the model was first evaluated at three different levels—random split, partial substrate novelty, and full substrate novelty. All model metrics in these cases improved dramatically, achieving an R2 of 0.89, MAE of 6.1%, and RMSE of 8.0%. Moreover, the generalization of our strategy was assessed using external datasets from reported literature. The prediction error for nine reactions among 30 was less than 5%, and the model was able to identify which reaction in a reaction pair with a reactivity cliff had a higher yield. In summary, our research demonstrated the feasibility of achieving accurate yield predictions through the combination of HTE and embedding intermediate knowledge into the model. This approach also has the potential to facilitate other related machine learning tasks.