Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction
This addresses the challenge of efficient and interpretable reaction prediction in synthetic chemistry, offering a novel paradigm that improves speed and accuracy over existing methods.
The paper tackles the problem of predicting chemical reaction products by introducing a non-autoregressive method that models reactions as electron redistribution, achieving a new state-of-the-art top-1 accuracy on the USPTO-MIT dataset and at least 27 times faster inference speed.
Reliably predicting the products of chemical reactions presents a fundamental challenge in synthetic chemistry. Existing machine learning approaches typically produce a reaction product by sequentially forming its subparts or intermediate molecules. Such autoregressive methods, however, not only require a pre-defined order for the incremental construction but preclude the use of parallel decoding for efficient computation. To address these issues, we devise a non-autoregressive learning paradigm that predicts reaction in one shot. Leveraging the fact that chemical reactions can be described as a redistribution of electrons in molecules, we formulate a reaction as an arbitrary electron flow and predict it with a novel multi-pointer decoding network. Experiments on the USPTO-MIT dataset show that our approach has established a new state-of-the-art top-1 accuracy and achieves at least 27 times inference speedup over the state-of-the-art methods. Also, our predictions are easier for chemists to interpret owing to predicting the electron flows.