Self-Parametrizing System-Focused Atomistic Models

Abstract

Computational studies of chemical reactions in complex environments such as proteins, nanostructures, or on surfaces require accurate and efficient atomistic models applicable to the nanometer scale. In general, an accurate parametrization of the atomistic entities will not be available for arbitrary system classes, but demands a fast automated system-focused parametrization procedure to be quickly applicable, reliable, flexible, and reproducible. Here, we develop and combine an automatically parametrizable quantum chemically derived molecular mechanics model with machine-learned corrections under autonomous uncertainty quantification and refinement. Our approach first generates an accurate, physically motivated model from a minimum energy structure and its corresponding Hessian matrix by a partial Hessian fitting procedure of the force constants. This model is then the starting point to generate a large number of configurations for which additional off-minimum reference data can be evaluated on the fly. A $\Delta$-machine learning model is trained on these data to provide a correction to energies and forces including uncertainty estimates. During the procedure, the flexibility of the machine learning model is tailored to the amount of available training data. The parametrization of large systems is enabled by a fragmentation approach. Due to their modular nature, all model construction steps allow for model improvement in a rolling fashion. Our approach may also be employed for the generation of system-focused electrostatic molecular mechanics embedding environments in a quantum-mechanical/molecular-mechanical hybrid model for arbitrary atomistic structures at the nanoscale.

arXiv comment53 pages, 12 figures, 2 tables

References in corpus (29)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Intrinsic atomic orbitals: An unbiased bridge between quantum theory and chemical concepts
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Machine Learning Unifies the Modelling of Materials and Molecules
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine-learning based interatomic potential for amorphous carbon
• Machine learning a general purpose interatomic potential for silicon
• The Density Matrix Renormalization Group in Chemistry and Molecular Physics: Recent Developments and New Challenges
• Exploration of Reaction Pathways and Chemical Transformation Networks
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
• How large should the QM region be in QM/MM calculations? The case of catechol O-methyltransferase
• Bayesian Error Estimation in Density Functional Theory
• A learning scheme to predict atomic forces and accelerate materials simulations
• Context-Driven Exploration of Complex Chemical Reaction Networks
• Training neural nets to learn reactive potential energy surfaces using interactive quantum chemistry in virtual reality
• Error-Controlled Exploration of Chemical Reaction Networks with Gaussian Processes
• Systematic Error Estimation for Chemical Reaction Energies
• Systematic Microsolvation Approach with a Cluster-Continuum Scheme and Conformational Sampling
• Semiempirical Molecular Orbital Models based on the Neglect of Diatomic Differential Overlap Approximation
• Gaussian Process-Based Refinement of Dispersion Corrections
• Reliable estimation of prediction uncertainty for physico-chemical property models
• Error Assessment of Computational Models in Chemistry
• Probabilistic performance estimators for computational chemistry methods: the empirical cumulative distribution function of absolute errors
• Comprehensive Analysis of the Neglect of Diatomic Differential Overlap Approximation
• Statistical Analysis of Semiclassical Dispersion Corrections
• Machine Learning for Atomic Forces in a Crystalline Solid: Transferability to Various Temperatures
• Quantum System Partitioning at the Single-Particle Level

Cited by in corpus (14)

• Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems
• Autonomous Reaction Network Exploration in Homogeneous and Heterogeneous Catalysis
• Universal QM/MM Approaches for General Nanoscale Applications
• Automated construction of quantum-classical hybrid models
• Molecule-specific Uncertainty Quantification in Quantum Chemical Studies
• Solvation Free Energies in Subsystem Density Functional Theory
• Training atomic neural networks using fragment-based data generated in virtual reality
• SCINE -- Software for Chemical Interaction Networks
• Multiscale Embedding for Quantum Computing
• Automated Microsolvation for Minimum Energy Path Construction in Solution
• Hierarchical quantum embedding by machine learning for large molecular assemblies
• Heron: Visualizing and Controlling Chemical Reaction Explorations and Networks
• Ultra-fast Spectroscopy for High-Throughput and Interactive Quantum Chemistry
• Automated Preparation of Nanoscopic Structures: Graph-Based Sequence Analysis, Mismatch Detection, and pH-Consistent Protonation with Uncertainty Estimates