GoMS: Graph of Molecule Substructure Network for Molecule Property Prediction

TL;DR

GoMS introduces a graph-based neural network architecture that models interactions between molecular substructures, significantly improving property prediction accuracy especially for large and complex molecules.

Contribution

The paper proposes GoMS, a novel architecture that explicitly models relationships between molecular substructures, outperforming existing bag-based methods like ESAN.

Findings

GoMS outperforms ESAN and baseline models on public datasets.

Performance improvements are more pronounced for molecules with over 100 atoms.

Theoretical analysis confirms GoMS's ability to distinguish molecules with identical subgraphs but different spatial arrangements.

Abstract

While graph neural networks have shown remarkable success in molecular property prediction, current approaches like the Equivariant Subgraph Aggregation Networks (ESAN) treat molecules as bags of independent substructures, overlooking crucial relationships between these components. We present Graph of Molecule Substructures (GoMS), a novel architecture that explicitly models the interactions and spatial arrangements between molecular substructures. Unlike ESAN's bag-based representation, GoMS constructs a graph where nodes represent subgraphs and edges capture their structural relationships, preserving critical topological information about how substructures are connected and overlap within the molecule. Through extensive experiments on public molecular datasets, we demonstrate that GoMS outperforms ESAN and other baseline methods, with particularly improvements for large molecules containing more than 100 atoms. The performance gap widens as molecular size increases, demonstrating GoMS's effectiveness for modeling industrial-scale molecules. Our theoretical analysis demonstrates that GoMS can distinguish molecules with identical subgraph compositions but different spatial arrangements. Our approach shows particular promise for materials science applications involving complex molecules where properties emerge from the interplay between multiple functional units. By capturing substructure relationships that are lost in bag-based approaches, GoMS represents a significant advance toward scalable and interpretable molecular property prediction for real-world applications.