Geometry-enhanced molecular representation learning for property prediction

TLDR

Molecular representation learning, especially via graph neural networks, is crucial for property prediction, yet existing self‑supervised methods largely ignore 3‑D geometry, which is essential for determining molecular properties. This study introduces GEM, a geometry‑enhanced representation learning framework designed to incorporate 3‑D molecular geometry into graph neural networks. GEM employs a geometry‑based GNN architecture coupled with dedicated geometry‑level self‑supervised learning strategies to capture spatial structure. Across multiple benchmarks, GEM consistently outperforms state‑of‑the‑art baselines, demonstrating its superior predictive performance.

Abstract

Abstract Effective molecular representation learning is of great importance to facilitate molecular property prediction. Recent advances for molecular representation learning have shown great promise in applying graph neural networks to model molecules. Moreover, a few recent studies design self-supervised learning methods for molecular representation to address insufficient labelled molecules; however, these self-supervised frameworks treat the molecules as topological graphs without fully utilizing the molecular geometry information. The molecular geometry, also known as the three-dimensional spatial structure of a molecule, is critical for determining molecular properties. To this end, we propose a novel geometry-enhanced molecular representation learning method (GEM). The proposed GEM has a specially designed geometry-based graph neural network architecture as well as several dedicated geometry-level self-supervised learning strategies to learn the molecular geometry knowledge. We compare GEM with various state-of-the-art baselines on different benchmarks and show that it can considerably outperform them all, demonstrating the superiority of the proposed method.