We cast retrosynthesis as a machine translation problem by introducing a special Tensor2Tensor, an entire attention-based and fully data-driven model. Given a data set comprising about 50,000 diverse reactions extracted from USPTO patents, the model significantly outperforms seq2seq model (34.7%) on a top-1 accuracy by achieving 54.1%. For yielding better results, parameters such as batch size and training time are thoroughly investigated to train the model. Additionally, we offer a novel insight into the causes of grammatically invalid SMILES, and conduct a test in which experienced chemists pick out and analyze the "wrong" predictions that may be chemically plausible but differ from the ground truth. Actually, the effectiveness of our model is underestimated and the "true" top-1 accuracy can reach to 64.6%. analysis using novel and emerging computing techniques 4-6 . Computers have been used since the 1960s for storing chemical structures data, and for applying chemical structural information to the applications such as synthesis planning, drug discovery 7

A proof-of-concept methodology for addressing small amounts of chemical data using transfer learning is presented. We demonstrate this by applying transfer learning combining transformer model to small-dataset Heck reaction prediction....