Energy-based View of Retrosynthesis
arXiv:2007.13437
Abstract
Retrosynthesis -- the process of identifying a set of reactants to synthesize a target molecule -- is of vital importance to material design and drug discovery. Existing machine learning approaches based on language models and graph neural networks have achieved encouraging results. In this paper, we propose a framework that unifies sequence- and graph-based methods as energy-based models (EBMs) with different energy functions. This unified perspective provides critical insights about EBM variants through a comprehensive assessment of performance. Additionally, we present a novel dual variant within the framework that performs consistent training over Bayesian forward- and backward-prediction by constraining the agreement between the two directions. This model improves state-of-the-art performance by 9.6% for template-free approaches where the reaction type is unknown.
References in corpus (6)
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Molecular Graph Convolutions: Moving Beyond Fingerprints
- Question Answering and Question Generation as Dual Tasks
- BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model
- A Graph to Graphs Framework for Retrosynthesis Prediction
Cited by in corpus (5)
- Re-evaluating Retrosynthesis Algorithms with Syntheseus
- Node-Aligned Graph-to-Graph (NAG2G): Elevating Template-Free Deep Learning Approaches in Single-Step Retrosynthesis
- MIST-CF: Chemical formula inference from tandem mass spectra
- Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction
- Modern Hopfield Networks for Few- and Zero-Shot Reaction Template Prediction