Neural Information Processing Systems http://nips.cc/

Summary: This work provides a novel approach to predict the outcome of organic chemical reactions. A reaction can be computationally regarded as graph-prediction problem: given the input of several connected graphs (molecules), the model aims to predict a fully-connected graph (reaction product) that can be obtained by performing several graph edits (reaction) on some edges and nodes (reaction center) in the input graphs. Past reaction predictions involving exhaustively enumeration of reaction centers and fitting them to a large number of existing reaction templates, which is very inefficient and hard to scale. In this work, the author proposed a template-free method to predict the outcome. It is a 3 step pipeline: 1) identify the reaction center given the input graphs using a Weisfeiler-Lehman Network.

Neural Information Processing Systems http://nips.cc/

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.

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.