Predicting retrosynthetic pathways using a combined linguistic model and hyper-graph exploration strategy
This work addresses retrosynthesis planning for chemists, offering an incremental improvement by combining existing methods with new strategies.
The authors tackled the problem of automatic retrosynthesis route planning by extending a Molecular Transformer architecture with a hyper-graph exploration strategy, achieving a new state of the art for predicting reactants, reagents, solvents, and catalysts in single-step retrosynthesis. They introduced new evaluation metrics and demonstrated very good performance in end-to-end frameworks, though with some weaknesses due to training bias.
We present an extension of our Molecular Transformer architecture combined with a hyper-graph exploration strategy for automatic retrosynthesis route planning without human intervention. The single-step retrosynthetic model sets a new state of the art for predicting reactants as well as reagents, solvents and catalysts for each retrosynthetic step. We introduce new metrics (coverage, class diversity, round-trip accuracy and Jensen-Shannon divergence) to evaluate the single-step retrosynthetic models, using the forward prediction and a reaction classification model always based on the transformer architecture. The hypergraph is constructed on the fly, and the nodes are filtered and further expanded based on a Bayesian-like probability. We critically assessed the end-to-end framework with several retrosynthesis examples from literature and academic exams. Overall, the frameworks has a very good performance with few weaknesses due to the bias induced during the training process. The use of the newly introduced metrics opens up the possibility to optimize entire retrosynthetic frameworks through focusing on the performance of the single-step model only.