Reproducing the invention of a named reaction: zero-shot prediction of unseen chemical reactions

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 remain an unanswered question. We aim to study the Transformer model's ability to predict "unseen" reactions following "zero-shot reaction prediction (ZSRP)", a concept derived from zero-shot learning and zero-shot translation. We reproduce 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 the samples from these two "existing" reactions, the USPTO-trained Transformer can predict "unseen" Chan-Lam coupling reactions with 55.7% top-1 accuracy. Our model also mimics the later stage of the history of this reaction, where the initial case of this reaction was generalized to more reactants and reagents via the "one-shot/few-shot reaction prediction(OSRP/FSRP)" approaches.