Zhong Haowen, Liu Yilan, Sun Haibin, Liu Yuru, Zhang Rentao, Li Baochen, Yang Yi, Huang Yuqing, Yang Fei, Mak Frankie S, Foo Klement, Lin Sen, Yu Tianshu, Wang Peng, Wang Xiaoxue
ChemLex, Shanghai, Shanghai, China.
MegaRobo Technologies Co., Ltd., Shanghai, Shanghai, China.
Nat Commun. 2025 May 15;16(1):4522. doi: 10.1038/s41467-025-59812-0.
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.
预测有机反应的可行性以及其对环境因素的稳健性具有挑战性。我们通过整合高通量实验（HTE）和贝叶斯深度学习来解决这一问题。与现有的专注于特定化学空间的HTE研究不同，在这项工作中，我们的内部HTE平台在156个工作小时内进行了11,669个不同的酸胺偶联反应，产生了体积规模上最广泛的单一HTE数据集，用于工业应用。我们的贝叶斯神经网络模型在反应可行性预测准确性方面达到了89.48%的基准。此外，我们的细粒度不确定性解缠实现了高效的主动学习，减少了80%的数据需求。此外，我们的不确定性分析有效地识别出域外反应，并评估反应对环境因素的稳健性或可重复性，以实现扩大规模，为探索化学空间和设计高度稳健的工业过程提供了一个实用框架。
