Hybrid localized graph kernel for machine learning energy-related properties of molecules and solids

Abstract

Nowadays, the coupling of electronic structure and machine learning techniques serves as a powerful tool to predict chemical and physical properties of a broad range of systems. With the aim of improving the accuracy of predictions, a large number of representations for molecules and solids for machine learning applications has been developed. In this work we propose a novel descriptor based on the notion of molecular graph. While graphs are largely employed in classification problems in cheminformatics or bioinformatics, they are not often used in regression problem, especially of energy-related properties. Our method is based on a local decomposition of atomic environments and on the hybridization of two kernel functions: a graph kernel contribution that describes the chemical pattern and a Coulomb label contribution that 1encodes finer details of the local geometry. The accuracy of this new kernel method in energy predictions of molecular and condensed phase systems is demonstrated by considering the popular QM7 and BA10 datasets. These examples show that the hybrid localized graph kernel outperforms traditional approaches such as, for example, the smooth overlap of atomic positions (SOAP) and the Coulomb matrices.

References in corpus (21)

• Scikit-learn: Machine Learning in Python
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Quantum computational chemistry
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Machine learning for molecular simulation
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Comparing molecules and solids across structural and alchemical space
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• A Survey on Graph Kernels
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Machine-learned multi-system surrogate models for materials prediction
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• Machine-Learning X-ray Absorption Spectra to Quantitative Accuracy
• Learning molecular energies using localized graph kernels
• Prediction of Atomization Energy Using Graph Kernel and Active Learning