Automatic Retrosynthetic Pathway Planning Using Template-free Models

Abstract

We present an attention-based Transformer model for automatic retrosynthesis route planning. Our approach starts from reactants prediction of single-step organic reactions for given products, followed by Monte Carlo tree search-based automatic retrosynthetic pathway prediction.Trained on two datasets from the United States patent literature, our models achieved a top-1 prediction accuracy of over 54.6% and 63.0% with more than 95% and 99.6% validity rate of SMILES, respectively, which is the best up to now to our knowledge. We also demonstrate the application potential of our model by successfully performing multi-step retrosynthetic route planning for four case products, i.e., antiseizure drug Rufinamide, a novel allosteric activator, an inhibitor of human acute-myeloid-leukemia cells and a complex intermediate of drug candidate. Further, by using heuristics Monte Carlo tree search, we achieved automatic retrosynthetic pathway searching and successfully reproduced published synthesis pathways. In summary, our model has achieved the stateof-the-art performance on single-step retrosynthetic prediction and provides a novel strategy for automatic retrosynthetic pathway planning.

Predicting Retrosynthetic Pathways Using a Combined Linguistic Model and Hyper-Graph Exploration Strategy

“…Duan et al [37] increased the batch size and the training time for their Transformer model and were able to achieve a top-1 accuracy of 54.1% on the 50k USPTO data set [44]. Later on, the same architecture was reported to have a top-1 accuracy of 43.8% [36], in line with the three previous transformer-based approaches [32,33,35] but significantly lower than the accuracy previously reported by Duan et al [37]. Interestingly, the transformer model was also trained on a proprietary data set [36], including only reactions with two reactants with a Tanimoto similarity distribution peaked at 0.75, characteristic of an excessive degree of similarity (roughly 2 times higher than the USPTO).…”

“…While this extensive production of AI models for Organic chemistry was made possible by the availability of public data [28,29], the noise contained in this data and generated by the text-mining extraction process is heavily reducing their potential. In fact, while rule-based systems [30] demonstrated, through wet-lab experiments, the capability to design target molecules with less purification steps and hence, leading to savings in time and cost [31], the AI approaches [6,9,12,16,[32][33][34][35][36][37][38] still have a long way to go.…”

“…Transformer-based retrosynthesis: current status. Inspired by the success of the Molecular Transformer [22,42,43] for forward reaction prediction, a few retrosynthetic models based on the same architecture were reported shortly after [32,33,[35][36][37]. Zheng et al [32] proposed a template-free self-corrected retrosynthesis predictor built on the Transformer architecture.…”

“…They were able to successfully predict the reactants with a top-1 accuracy of 42.7%. Lin et al [35] combined a Monte-Carlo tree search, previously introduced for retrosynthesis in the ground-breaking work by Segler et al [12], with a single retrosynthetic step Transformer architecture for predicting multi-step reactions. In a single-step setting, the model described by Lin et al [35] achieved a top-1 prediction accuracy of over 43.1% and 54.1% when trained on the same small data set [44] and a ten times larger collection, respectively.…”

“…Lin et al [35] combined a Monte-Carlo tree search, previously introduced for retrosynthesis in the ground-breaking work by Segler et al [12], with a single retrosynthetic step Transformer architecture for predicting multi-step reactions. In a single-step setting, the model described by Lin et al [35] achieved a top-1 prediction accuracy of over 43.1% and 54.1% when trained on the same small data set [44] and a ten times larger collection, respectively. Duan et al [37] increased the batch size and the training time for their Transformer model and were able to achieve a top-1 accuracy of 54.1% on the 50k USPTO data set [44].…”