ChemHGNN: A Hierarchical Hypergraph Neural Network for Reaction Virtual Screening and Discovery
This work addresses a fundamental challenge in chemistry and materials science by providing a chemically informed framework for accelerating reaction discovery, though it is incremental as it builds on existing hypergraph neural network methods.
The paper tackled the problem of modeling multi-reactant interactions in reaction virtual screening and discovery, where traditional graph neural networks struggle, by proposing ChemHGNN, a hypergraph neural network framework that significantly outperformed baselines on the USPTO dataset, especially in large-scale settings.
Reaction virtual screening and discovery are fundamental challenges in chemistry and materials science, where traditional graph neural networks (GNNs) struggle to model multi-reactant interactions. In this work, we propose ChemHGNN, a hypergraph neural network (HGNN) framework that effectively captures high-order relationships in reaction networks. Unlike GNNs, which require constructing complete graphs for multi-reactant reactions, ChemHGNN naturally models multi-reactant reactions through hyperedges, enabling more expressive reaction representations. To address key challenges, such as combinatorial explosion, model collapse, and chemically invalid negative samples, we introduce a reaction center-aware negative sampling strategy (RCNS) and a hierarchical embedding approach combining molecule, reaction and hypergraph level features. Experiments on the USPTO dataset demonstrate that ChemHGNN significantly outperforms HGNN and GNN baselines, particularly in large-scale settings, while maintaining interpretability and chemical plausibility. Our work establishes HGNNs as a superior alternative to GNNs for reaction virtual screening and discovery, offering a chemically informed framework for accelerating reaction discovery.