Quantum chemical roots of machine-learning molecular similarity descriptors

Abstract

In this work, we explore the quantum chemical foundations of descriptors for molecular similarity. Such descriptors are key for traversing chemical compound space with machine learning. Our focus is on the Coulomb matrix and on the smooth overlap of atomic positions (SOAP). We adopt a basic framework that allows us to connect both descriptors to electronic structure theory. This framework enables us then to define two new descriptors that are more closely related to electronic structure theory, which we call Coulomb lists and smooth overlap of electron densities (SOED). By investigating their usefulness as molecular similarity descriptors, we gain new insights in how and why Coulomb matrix and SOAP work. Moreover, Coulomb lists avoid the somewhat mysterious diagonalization step of the Coulomb matrix and might provide a direct means to extract subsystem information that can be compared across Born-Oppenheimer surfaces of varying dimension. For the electron density we derive the necessary formalism to create the SOED measure in close analogy to SOAP. Since this formalism is more involved than that of SOAP, we review the essential theory, but also introduce a set of approximations that eventually allow us to work with SOED in terms of the same implementation available for the evaluation of SOAP. We focus our analysis on elementary reaction steps, where transition state structures are more similar to either reactant or product structures than the latter two are with respect to one another. The prediction of electronic energies of transition state structures can, however, be more difficult than that of stable intermediates due to multi-configurational effects. The question arises to what extent molecular similarity descriptors rooted in electronic structure theory can resolve these intricate effects.

arXiv comment41 pages, 10 figures

References in corpus (32)

• Array Programming with NumPy
• 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
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• 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
• Physics-inspired structural representations for molecules and materials
• FCHL revisited: faster and more accurate quantum machine learning
• Resolving transition metal chemical space: feature selection for machine learning and structure-property relationships
• Hierarchical modeling of molecular energies using a deep neural network
• Electronic Spectra from TDDFT and Machine Learning in Chemical Space
• A Transferable Machine-Learning Model of the Electron Density
• Exploration of Reaction Pathways and Chemical Transformation Networks
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Data-driven learning of total and local energies in elemental boron
• On the Completeness of Atomic Structure Representations
• Predicting Electronic Structure Properties of Transition Metal Complexes with Neural Networks
• Atom-Density Representations for Machine Learning
• Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials
• Machine learning based energy-free structure predictions of molecules (closed and open-shell), transition states, and solids
• Using Gaussian Process Regression to Simulate the Vibrational Raman Spectra of Molecular Crystals
• Towards the design of chemical reactions: Machine learning barriers of competing mechanisms in reactant space
• Learning molecular energies using localized graph kernels
• A Bayesian approach to NMR crystal structure determination
• Efficient implementation of atom-density representations
• Comment on "Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning"
• Deep Reinforcement Learning of Transition States
• An Atomistic Fingerprint Algorithm for Learning Ab Initio Molecular Force Fields
• Machine learning at the atomic-scale

Cited by in corpus (5)

• Lifelong Machine Learning Potentials
• SCINE -- Software for Chemical Interaction Networks
• Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
• SPA${}^{\mathrm{H}}$M(a,b): encoding the density information from guess Hamiltonian in quantum machine learning representations
• Automated Preparation of Nanoscopic Structures: Graph-Based Sequence Analysis, Mismatch Detection, and pH-Consistent Protonation with Uncertainty Estimates