Organic reactions are usually assigned to classes containing reactions with similar reagents and mechanisms. Reaction classes facilitate the communication of complex concepts and efficient navigation through chemical reaction space. However, the classification process is a tedious task. It requires identification of the corresponding reaction class template via annotation of the number of molecules in the reactions, the reaction centre and the distinction between reactants and reagents. Here, we show that transformer-based models can infer reaction classes from non-annotated, simple text-based representations of chemical reactions. Our best model reaches a classification accuracy of 98.2%. We also show that the learned representations can be used as reaction fingerprints that capture fine-grained differences between reaction classes better than traditional reaction fingerprints. The insights into chemical reaction space enabled by our learned fingerprints are illustrated by an interactive reaction atlas providing visual clustering and similarity searching.

有机反应通常被分配到包含具有类似试剂和机制的反应的类别。反应类促进了复杂概念的交流和化学反应空间的有效导航。但是，分类过程是一项繁琐的任务。它需要通过注释反应中的分子数量、反应中心以及反应物和试剂的区别来识别相应的反应类模板。在这里，我们展示了基于转换器的模型可以从化学反应的无注释、简单的基于文本的表示中推断反应类别。我们最好的模型达到了 98.2% 的分类准确率。我们还表明，学习的表示可以用作反应指纹，比传统的反应指纹更好地捕捉反应类别之间的细粒度差异。由我们学习的指纹实现的对化学反应空间的洞察通过提供视觉聚类和相似性搜索的交互式反应图谱来说明。