College of Chemical Engineering, Zhejiang University of Technology, Hangzhou 310014, P. R. China.
Artificial Intelligence Aided Drug Discovery Institute, College of Pharmaceutical Sciences, Zhejiang University of Technology, Hangzhou 310014, P. R. China.
Phys Chem Chem Phys. 2022 May 4;24(17):10280-10291. doi: 10.1039/d1cp05878a.
While state-of-art models can predict reactions through the transfer learning of thousands of samples with the same reaction types as those of the reactions to predict, how to prepare such models to predict "unseen" reactions remains an unanswered question. We aimed to study the Transformer model's ability to predict "unseen" reactions through "zero-shot reaction prediction (ZSRP)", a concept derived from zero-shot learning and zero-shot translation. We reproduced the human invention of the Chan-Lam coupling reaction where the inventor was inspired by the Suzuki reaction when improving Barton's bismuth arylation reaction. After being fine-tuned with samples from these two "existing" reactions, the USPTO-trained Transformer could predict "unseen" Chan-Lam coupling reactions with 55.7% top-1 accuracy. Our model could also mimic the later stage of the history of this reaction, where the initial case of this reaction was generalized to more reactants and reagents "one-shot/few-shot reaction prediction (OSRP/FSRP)" approaches.
虽然最先进的模型可以通过对与要预测的反应类型相同的数千个样本进行迁移学习来预测反应，但如何准备这些模型以预测“未见”的反应仍然是一个未解决的问题。我们旨在通过“零镜头反应预测 (ZSRP)”研究 Transformer 模型预测“未见”反应的能力，该概念源自零镜头学习和零镜头翻译。我们重现了 Chan-Lam 偶联反应的人类发明，该反应的发明者在改进 Barton 的铋芳基化反应时受到 Suzuki 反应的启发。在使用这两个“现有”反应的样本进行微调后，USPTO 训练的 Transformer 可以以 55.7%的最高准确率预测“未见”的 Chan-Lam 偶联反应。我们的模型还可以模拟该反应历史的后期阶段，其中该反应的初始情况被推广到更多的反应物和试剂，即“单镜头/少镜头反应预测 (OSRP/FSRP)”方法。
