2021/06/08 by Hangrui Bi, Bi, Hangrui, Hengyi Wang +10 · 1 citation
Chemistry · Computer Science · Materials Science · Physics and Astronomy · #Chemical Physics (physics.chem-ph) #Computational Drug Discovery Methods #Computational Engineering #FOS: Computer and information sciences #FOS: Physical sciences #Finance #Machine Learning (cs.LG) #Machine Learning in Materials Science #Mass Spectrometry Techniques and Applications #and Science (cs.CE) #cs.CE #cs.LG #physics.chem-ph
paper · pdf · doi:10.48550/arxiv.2106.07801
arxiv created 2021/06/08 · openalex publication_date 2021/06/08 · arxiv updated 2021/06/16 · openalex created_date 2021/06/22 · openalex updated_date 2026/07/28
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.