Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network
arXiv:1709.04555
Abstract
The prediction of organic reaction outcomes is a fundamental problem in computational chemistry. Since a reaction may involve hundreds of atoms, fully exploring the space of possible transformations is intractable. The current solution utilizes reaction templates to limit the space, but it suffers from coverage and efficiency issues. In this paper, we propose a template-free approach to efficiently explore the space of product molecules by first pinpointing the reaction center -- the set of nodes and edges where graph edits occur. Since only a small number of atoms contribute to reaction center, we can directly enumerate candidate products. The generated candidates are scored by a Weisfeiler-Lehman Difference Network that models high-order interactions between changes occurring at nodes across the molecule. Our framework outperforms the top-performing template-based approach with a 10\% margin, while running orders of magnitude faster. Finally, we demonstrate that the model accuracy rivals the performance of domain experts.
arXiv commentaccepted by NIPS 2017
References in corpus (1)
Cited by in corpus (26)
- Hierarchical Graph Representation Learning with Differentiable Pooling
- Junction Tree Variational Autoencoder for Molecular Graph Generation
- GNNExplainer: Generating Explanations for Graph Neural Networks
- SELFIES and the future of molecular string representations
- A Survey of Machine Learning for Computer Architecture and Systems
- Exploring Chemical Space using Natural Language Processing Methodologies for Drug Discovery
- Quantum chemistry-augmented neural networks for reactivity prediction: Performance, generalizability and interpretability
- Root-aligned SMILES: A Tight Representation for Chemical Reaction Prediction
- Error-Controlled Exploration of Chemical Reaction Networks with Gaussian Processes
- Learning Graph Models for Retrosynthesis Prediction
- ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations
- Constrained Bayesian Optimization for Automatic Chemical Design
- A Bayesian algorithm for retrosynthesis
- RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction
- A Model to Search for Synthesizable Molecules
- Reinforcement Learning for Molecular Design Guided by Quantum Mechanics
- Symmetry-Aware Actor-Critic for 3D Molecular Design
- Graph-Aware Transformer: Is Attention All Graphs Need?
- NIPS - Not Even Wrong? A Systematic Review of Empirically Complete Demonstrations of Algorithmic Effectiveness in the Machine Learning and Artificial Intelligence Literature
- "Found in Translation": Predicting Outcomes of Complex Organic Chemistry Reactions using Neural Sequence-to-Sequence Models
- Wasserstein Embedding for Graph Learning
- Controlled Molecule Generator for Optimizing Multiple Chemical Properties
- Self-Improved Retrosynthetic Planning
- Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
- Efficient interpolation of molecular properties across chemical compound space with low-dimensional descriptors
- Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization