Towards global reaction feasibility and robustness prediction with high throughput data and bayesian deep learning
Haowen Zhong, Yilan Liu, Haibin Sun, Yuru Liu, Rentao Zhang, Baochen Li, Shuicheng Yan, Yuqing Huang, Fei Yang, Frankie S. Mak, Klement Foo, Sen Lin, Tianshu Yu, Peng Wang, Xiaoxue Wang
Abstract
Predicting organic reaction feasibility and robustness against environmental factors is challenging. We address this issue by integrating high throughput experimentation (HTE) and Bayesian deep learning. Diverging from existing HTE studies focused on niche chemical spaces, in this work, our in-house HTE platform conducted 11,669 distinct acid amine coupling reactions in 156 working hours, yielding the most extensive single HTE dataset at a volumetric scale for industrial delivery. Our Bayesian neural network model achieved a benchmark for prediction accuracy of 89.48% for reaction feasibility. Furthermore, our fine-grained uncertainty disentanglement enables efficient active learning, reducing 80% of data requirements. Additionally, our uncertainty analysis effectively identifies out-of-domain reactions and evaluates reaction robustness or reproducibility against environmental factors for scaling up, offering a practical framework for navigating chemical spaces and designing highly robust industrial processes. Although theoretical advances in the reactivity of organic compounds have progressed rapidly, a complete understanding of the causal relationships between molecular structures and reaction outcomes based solely on first principles remains elusive. Here, the authors use an in-house HTE platform to conduct over 11,000 distinct acid amine couplings, with an accompanying Bayesian neural network model that gives a prediction accuracy of 89.48% for reaction feasibility.