Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective

TL;DR

This paper introduces a multilevel graph neural network model that captures complex quantum interactions within molecules to improve the accuracy and transferability of molecular property predictions, addressing limitations of traditional and existing machine learning methods.

Contribution

The paper proposes a novel multilevel graph convolutional neural network that models hierarchical quantum interactions for more accurate molecular property prediction.

Findings

Effective on equilibrium and off-equilibrium molecules

Demonstrates high transferability and generalizability

Outperforms traditional methods in prediction accuracy

Abstract

Predicting molecular properties (e.g., atomization energy) is an essential issue in quantum chemistry, which could speed up much research progress, such as drug designing and substance discovery. Traditional studies based on density functional theory (DFT) in physics are proved to be time-consuming for predicting large number of molecules. Recently, the machine learning methods, which consider much rule-based information, have also shown potentials for this issue. However, the complex inherent quantum interactions of molecules are still largely underexplored by existing solutions. In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction. Specifically, we represent each molecule as a graph to preserve its internal structure. Moreover, the well-designed hierarchical graph neural network directly extracts features from the conformation and spatial information followed by the multilevel interactions. As a consequence, the multilevel overall representations can be utilized to make the prediction. Extensive experiments on both datasets of equilibrium and off-equilibrium molecules demonstrate the effectiveness of our model. Furthermore, the detailed results also prove that MGCN is generalizable and transferable for the prediction.