Chemical diversity in molecular orbital energy predictions with kernel ridge regression

Abstract

Instant machine learning predictions of molecular properties are desirable for materials design, but the predictive power of the methodology is mainly tested on well-known benchmark datasets. Here, we investigate the performance of machine learning with kernel ridge regression (KRR) for the prediction of molecular orbital energies on three large datasets: the standard QM9 small organic molecules set, amino acid and dipeptide conformers, and organic crystal-forming molecules extracted from the Cambridge Structural Database. We focus on prediction of highest occupied molecular orbital (HOMO) energies, computed at density-functional level of theory. Two different representations that encode molecular structure are compared: the Coulomb matrix (CM) and the many-body tensor representation (MBTR). We find that KRR performance depends significantly on the chemistry of the underlying dataset and that the MBTR is superior to the CM, predicting HOMO energies with a mean absolute error as low as 0.09 eV. To demonstrate the power of our machine learning method, we apply our model to structures of 10k previously unseen molecules. We gain instant energy predictions that allow us to identify interesting molecules for future applications.

arXiv comment16 pages, 13 figures

References in corpus (24)

• Automatic chemical design using a data-driven continuous representation of molecules
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• 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 Unifies the Modelling of Materials and Molecules
• Resolution-of-identity approach to Hartree-Fock, hybrid density functionals, RPA, MP2, and \textit{GW} with numeric atom-centered orbital basis functions
• Machine learning prediction errors better than DFT accuracy
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Alchemical and structural distribution based representation for improved QML
• Hierarchical modeling of molecular energies using a deep neural network
• Combining GW calculations with exact-exchange density-functional theory: An analysis of valence-band photoemission for compound semiconductors
• Electronic Spectra from TDDFT and Machine Learning in Chemical Space
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Efficient Bayesian Inference of Atomistic Structure in Complex Functional Materials
• Transferable atomic multipole machine learning models for small organic molecules
• Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
• Finding the Right Bricks for Molecular Lego: A Data Mining Approach to Organic Semiconductor Design

Cited by in corpus (15)

• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Data-driven materials science: status, challenges and perspectives
• Physics-inspired structural representations for molecules and materials
• Machine learning for electronically excited states of molecules
• Quantum Machine Learning for Chemistry and Physics
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Updates to the DScribe Library: New Descriptors and Derivatives
• Accurate computational prediction of core-electron binding energies in carbon-based materials: A machine-learning model combining density-functional theory and $\mathbf{GW}$
• Physically inspired deep learning of molecular excitations and photoemission spectra
• Machine learning and excited-state molecular dynamics
• Predicting Gas-Particle Partitioning Coefficients of Atmospheric Molecules with Machine Learning
• Scalable neural networks for the efficient learning of disordered quantum systems
• Efficient dataset generation for machine learning perovskite alloys
• $\chi$iplot: web-first visualisation platform for multidimensional data
• Using Slisemap to interpret physical data