Language selection

Government of Canada / Gouvernement du Canada

Search

Non-autoregressive electron redistribution modeling for reaction prediction

From National Research Council Canada

Download
  1. (PDF, 516 KiB)
  2. (PDF, 846 KiB)
Linkhttp://proceedings.mlr.press/v139/bi21a.html
AuthorSearch for: ; Search for: ; Search for: ; Search for: ; Search for: ; Search for: 1
Affiliation
  1. National Research Council Canada. Digital Technologies
FormatText, Article
Conference38th International Conference on Machine Learning, ICML 2021, July 18-24, 2021, Virtual Event
Abstract
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.
Publication date
PublisherInternational Conference on Machine Learning
In
  • Proceedings of Machine Learning Research 139 (2021): 904–913.
LanguageEnglish
Peer reviewedYes
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifier1f7952ac-fb93-4e2c-b8a7-098ab9419c50
Record created2022-03-29
Record modified2022-03-31
Date modified: