Non-autoregressive electron flow generation for reaction prediction
This work provides a faster and more accurate method for reaction prediction, which is crucial for computational chemists and drug discovery.
This paper addresses the problem of reaction prediction in computational chemistry by proposing a non-autoregressive decoder that represents edge edits as electron flows, enabling parallel prediction. The model achieves state-of-the-art top-1 accuracy and an order of magnitude lower inference latency on the USPTO MIT dataset.
Reaction prediction is a fundamental problem in computational chemistry. Existing approaches typically generate a chemical reaction by sampling tokens or graph edits sequentially, conditioning on previously generated outputs. These autoregressive generating methods impose an arbitrary ordering of outputs and prevent parallel decoding during inference. We devise a novel decoder that avoids such sequential generating and predicts the reaction in a Non-Autoregressive manner. Inspired by physical-chemistry insights, we represent edge edits in a molecule graph as electron flows, which can then be predicted in parallel. To capture the uncertainty of reactions, we introduce latent variables to generate multi-modal outputs. Following previous works, we evaluate our model on USPTO MIT dataset. Our model achieves both an order of magnitude lower inference latency, with state-of-the-art top-1 accuracy and comparable performance on Top-K sampling.