"Accelerating Organic Synthesis using Chemical Language Models"

In organic chemistry, we are currently witnessing a rise in artificial intelligence (AI) approaches, which show great potential for improving molecular designs, facilitating synthesis, and accelerating the discovery of novel molecules.
Based on an analogy between written language and organic chemistry, we built linguistics-inspired transformer neural network models for chemical reaction prediction, synthesis planning, and the prediction of experimental actions. We extended the models to chemical reaction classification and fingerprints.
By finding a mapping from discrete reactions to continuous vectors, we enabled efficient chemical reaction space exploration. Moreover, we specialised similar models for reaction yield predictions. Intrigued by the remarkable performance of chemical language models, we discovered that the models could capture how atoms rearrange during a reaction without supervision or human labelling, leading to the development of the open-source atom-mapping tool RXNMapper (https://urldefense.com/v3/__http://rxnmapper.ai/__;!!Dc8iu7o!m0DZpqA3YX0nH6sGgfDFrwYabigp4XvcKDd7YplPVN5TS890spcR4aUy4YSSVSqOaww$ ).

During my talk, I will provide an overview of the different contributions at the base of this digital synthetic chemistry revolution.