Adaptive Substructure-Aware Expert Model for Molecular Property Prediction
This work solves the challenge of improving generalization and interpretability in molecular property prediction for applications like drug discovery, though it is incremental as it builds on existing GNN and MoE methods.
The paper tackled the problem of molecular property prediction by addressing the limitations of Graph Neural Networks in handling data imbalance and diverse substructures, proposing ASE-Mol, which achieved state-of-the-art performance on eight benchmark datasets with improvements in accuracy and interpretability.
Molecular property prediction is essential for applications such as drug discovery and toxicity assessment. While Graph Neural Networks (GNNs) have shown promising results by modeling molecules as molecular graphs, their reliance on data-driven learning limits their ability to generalize, particularly in the presence of data imbalance and diverse molecular substructures. Existing methods often overlook the varying contributions of different substructures to molecular properties, treating them uniformly. To address these challenges, we propose ASE-Mol, a novel GNN-based framework that leverages a Mixture-of-Experts (MoE) approach for molecular property prediction. ASE-Mol incorporates BRICS decomposition and significant substructure awareness to dynamically identify positive and negative substructures. By integrating a MoE architecture, it reduces the adverse impact of negative motifs while improving adaptability to positive motifs. Experimental results on eight benchmark datasets demonstrate that ASE-Mol achieves state-of-the-art performance, with significant improvements in both accuracy and interpretability.