Molecular geometric deep learning

TL;DR

This paper introduces Mol-GDL, a novel geometric deep learning approach that uses multi-scale molecular graphs including non-covalent bonds, achieving superior property prediction results over traditional covalent-bond-based models.

Contribution

The paper proposes a new molecular representation incorporating non-covalent bonds and demonstrates its effectiveness in molecular property prediction tasks.

Findings

Mol-GDL outperforms state-of-the-art methods on benchmark datasets.

Non-covalent bonds can be as informative as covalent bonds in molecular graphs.

Multi-scale molecular graphs improve the accuracy of molecular property predictions.

Abstract

Geometric deep learning (GDL) has demonstrated huge power and enormous potential in molecular data analysis. However, a great challenge still remains for highly efficient molecular representations. Currently, covalent-bond-based molecular graphs are the de facto standard for representing molecular topology at the atomic level. Here we demonstrate, for the first time, that molecular graphs constructed only from non-covalent bonds can achieve similar or even better results than covalent-bond-based models in molecular property prediction. This demonstrates the great potential of novel molecular representations beyond the de facto standard of covalent-bond-based molecular graphs. Based on the finding, we propose molecular geometric deep learning (Mol-GDL). The essential idea is to incorporate a more general molecular representation into GDL models. In our Mol-GDL, molecular topology is modeled as a series of molecular graphs, each focusing on a different scale of atomic interactions. In this way, both covalent interactions and non-covalent interactions are incorporated into the molecular representation on an equal footing. We systematically test Mol-GDL on fourteen commonly-used benchmark datasets. The results show that our Mol-GDL can achieve a better performance than state-of-the-art (SOTA) methods. Source code and data are available at https://github.com/CS-BIO/Mol-GDL.