Rxn Hypergraph: a Hypergraph Attention Model for Chemical Reaction Representation

TL;DR

This paper introduces Rxn Hypergraph, a hypergraph attention neural network that improves chemical reaction representation and property prediction, offering a universal, robust, interpretable, and data-driven approach validated across multiple datasets.

Contribution

The paper presents a novel hypergraph attention model for chemical reactions that addresses limitations of existing methods by providing a universal, robust, and interpretable representation.

Findings

Outperforms existing reaction representations in experiments

Provides interpretable multi-level reaction representations

Validated across three independent datasets

Abstract

It is fundamental for science and technology to be able to predict chemical reactions and their properties. To achieve such skills, it is important to develop good representations of chemical reactions, or good deep learning architectures that can learn such representations automatically from the data. There is currently no universal and widely adopted method for robustly representing chemical reactions. Most existing methods suffer from one or more drawbacks, such as: (1) lacking universality; (2) lacking robustness; (3) lacking interpretability; or (4) requiring excessive manual pre-processing. Here we exploit graph-based representations of molecular structures to develop and test a hypergraph attention neural network approach to solve at once the reaction representation and property-prediction problems, alleviating the aforementioned drawbacks. We evaluate this hypergraph representation in three experiments using three independent data sets of chemical reactions. In all experiments, the hypergraph-based approach matches or outperforms other representations and their corresponding models of chemical reactions while yielding interpretable multi-level representations.