Universal neural network potentials as descriptors: Towards scalable chemical property prediction using quantum and classical computers

2024/02/28 by Tomoya Shiota, Shiota, Tomoya, Kenji Ishihara +3 · 3 citations
Computer Science · Materials Science · #Chemical Physics (physics.chem-ph) #FOS: Physical sciences #Machine Learning in Materials Science #Quantum Computing Algorithms and Architecture #Quantum Physics (quant-ph)

paper · pdf · doi:10.48550/arxiv.2402.18433

openalex publication_date 2024/02/28 · openalex created_date 2024/03/05 · openalex updated_date 2026/07/28

Abstract

Accurate prediction of diverse chemical properties is crucial for advancing molecular design and materials discovery. Here we present a versatile approach that uses the intermediate information of a universal neural network potential as a general-purpose descriptor for chemical property prediction. Our method is based on the insight that by training a sophisticated neural network architecture for universal force fields, it learns transferable representations of atomic environments. We show that transfer learning with graph neural network potentials such as M3GNet and MACE achieves accuracy comparable to state-of-the-art methods for predicting the NMR chemical shifts of using quantum machine learning as well as a standard classical regression model, despite the compactness of its descriptors. In particular, the MACE descriptor demonstrates the highest accuracy to date on the ¹³C NMR chemical shift benchmarks for drug molecules. This work provides an efficient way to accurately predict properties, potentially accelerating the discovery of new molecules and materials.

Cited by

• Enhancing NMR Shielding Predictions of Atoms-in-Molecules Machine Learning Models with Neighborhood-Informed Representations
• Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability
• Hybrid Quantum--Classical Machine Learning Potential with Variational Quantum Circuits

Related

• Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective
• Automatic Identification of Chemical Moieties
• Broadening the Scope of Neural Network Potentials through Direct Inclusion of Additional Molecular Attributes
• Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation
• Graph Neural Network Architecture Search for Molecular Property Prediction