Mapping the space of chemical reactions using attention-based neural networks

By Philippe Schwaller, Daniel Probst, Alain C. Vaucher, Vishnu H. Nair, D. Kreutter, Teodoro Laino, Jean-Louis Reymond. Nature Machine Intelligence, 2020

318 citations recorded by the source corpus.

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. Organic chemical reactions can be divided into classes that allow chemists to use the knowledge they have about optimal conditions for specific reactions in the context of other reactions of similar type. Schwaller et al. present here an efficient method based on transformer neural networks that learns a chemical space in which reactions of a similar class are grouped together.

Subfields: Artificial Intelligence, Materials Chemistry, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/c2a9c431d77f9a8cdbb84576e123f162afef3833

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Materials Chemistry

Heng Ji

In Molecular Biology

Citations in the corpus

Translation between Molecules and Natural Language (2022, methodology): “(Schwaller et al., 2021b) trains a BERT model to learn representations of chemical reactions.”
Your fairness may vary: Pretrained language model fairness in toxic text classification (2021, background): “More importantly, LMs have been applied to practical problems, leading to improved results for web search (Nayak, 2019) and have become an asset in ﬁelds such as medical evidence inference (Lehman et al., 2019; Subramanian et al., 2020) and chemistry (Schwaller et al., 2021).”
Artificial intelligence in drug development (2025, unknown): “The schematic diagram illustrates the seamless integration of AI-driven software with experimental execution and result analysis within the automated synthesis process.”