Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network

TL;DR

This paper introduces a template-free graph neural network approach using Weisfeiler-Lehman Difference Network to predict organic reaction outcomes efficiently, outperforming template-based methods and rivaling expert accuracy.

Contribution

The paper presents a novel, template-free method for reaction prediction that identifies reaction centers and models high-order interactions, improving speed and accuracy over existing approaches.

Findings

Outperforms top template-based methods by 10%

Runs orders of magnitude faster than template-based approaches

Achieves accuracy comparable to domain experts

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.