sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning

Abstract

We present an optimized implementation of the recently proposed symmetric gradient domain machine learning (sGDML) model. The sGDML model is able to faithfully reproduce global potential energy surfaces (PES) for molecules with a few dozen atoms from a limited number of user-provided reference molecular conformations and the associated atomic forces. Here, we introduce a Python software package to reconstruct and evaluate custom sGDML force fields (FFs), without requiring in-depth knowledge about the details of the model. A user-friendly command-line interface offers assistance through the complete process of model creation, in an effort to make this novel machine learning approach accessible to broad practitioners. Our paper serves as a documentation, but also includes a practical application example of how to reconstruct and use a PBE0+MBD FF for paracetamol. Finally, we show how to interface sGDML with the FF simulation engines ASE (Larsen et al., J. Phys. Condens. Matter 29, 273002 (2017)) and i-PI (Kapil et al., Comput. Phys. Commun. 236, 214-223 (2019)) to run numerical experiments, including structure optimization, classical and path integral molecular dynamics and nudged elastic band calculations.

References in corpus (34)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• By-passing the Kohn-Sham equations with machine learning
• Active learning of linearly parametrized interatomic potentials
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine learning prediction errors better than DFT accuracy
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• VAMPnets: Deep learning of molecular kinetics
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Hierarchical modeling of molecular energies using a deep neural network
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
• A learning scheme to predict atomic forces and accelerate materials simulations
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Efficient nonparametric $n$-body force fields from machine learning
• Transferable atomic multipole machine learning models for small organic molecules
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• The Many-Body Expansion Combined with Neural Networks
• Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
• Boltzmann Generators -- Sampling Equilibrium States of Many-Body Systems with Deep Learning
• Convolutional neural networks for atomistic systems
• Exploring a potential energy surface by machine learning for characterizing atomic transport
• An Atomistic Fingerprint Algorithm for Learning Ab Initio Molecular Force Fields

Cited by in corpus (74)

• Machine Learning Force Fields
• Machine learning for molecular simulation
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• DeePMD-kit v2: A software package for Deep Potential models
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Machine learning for electronically excited states of molecules
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Deep Potentials for Materials Science
• Perspective on integrating machine learning into computational chemistry and materials science
• Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid Hafnium dioxide
• Quantum Machine Learning for Chemistry and Physics
• Active learning of reactive Bayesian force fields: Application to heterogeneous hydrogen-platinum catalysis dynamics
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• End-to-End Differentiable Molecular Mechanics Force Field Construction
• DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows
• Physically inspired deep learning of molecular excitations and photoemission spectra
• i-PI 3.0: a flexible and efficient framework for advanced atomistic simulations
• Machine learning and excited-state molecular dynamics
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
• PANNA: Properties from Artificial Neural Network Architectures
• JARVIS-Leaderboard: A Large Scale Benchmark of Materials Design Methods
• High-Dimensional Potential Energy Surfaces for Molecular Simulations
• Permutationally Invariant, Reproducing Kernel-Based Potential Energy Surfaces for Polyatomic Molecules: From Formaldehyde to Acetone
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Permutationally invariant polynomial regression for energies and gradients, using reverse differentiation, achieves orders of magnitude speed-up with high precision compared to other machine learning methods
• Atomic Permutationally Invariant Polynomials for Fitting Molecular Force Fields
• Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
• Dynamical Strengthening of Covalent and Non-Covalent Molecular Interactions by Nuclear Quantum Effects at Finite Temperature
• Predicting tensorial molecular properties with equivariant machine-learning models
• SOS-SDP: an Exact Solver for Minimum Sum-of-Squares Clustering
• Learning Gradient Fields for Molecular Conformation Generation
• Overcoming the Barrier of Orbital-Free Density Functional Theory for Molecular Systems Using Deep Learning
• Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer
• Exploring the robust extrapolation of high-dimensional machine learning potentials
• The MD17 Datasets from the Perspective of Datasets for Gas-Phase "Small" Molecule Potentials
• Learning from the Density to Correct Total Energy and Forces in First Principle Simulations
• Progress and Challenges in Ab Initio Simulations of Quantum Nuclei in Weakly Bonded Systems
• Symmetrical Graph Neural Network for Quantum Chemistry, with Dual R/K Space
• Tensorial properties via the neuroevolution potential framework: Fast simulation of infrared and Raman spectra
• MGNN: Moment Graph Neural Network for Universal Molecular Potentials
• Energy-conserving molecular dynamics is not energy conserving
• Accurate quantum Monte Carlo forces for machine-learned force fields: Ethanol as a benchmark
• Stress and heat flux via automatic differentiation
• GPU-Accelerated Approximate Kernel Method for Quantum Machine Learning
• Wasserstein metric for improved QML with adjacency matrix representations
• Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields
• Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks
• Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights
• A Hessian-Based Assessment of Atomic Forces for Training Machine Learning Interatomic Potentials
• Accurate Molecular Dynamics Enabled by Efficient Physically-Constrained Machine Learning Approaches
• Size and Quality of Quantum Mechanical Data Sets for Training Neural Network Force Fields for Liquid Water
• Efficient force field and energy emulation through partition of permutationally equivalent atoms
• Tell machine learning potentials what they are needed for: Simulation-oriented training exemplified for glycine
• Gradient domain machine learning with composite kernels: improving the accuracy of PES and force fields for large molecules
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• Molecular relaxation by reverse diffusion with time step prediction
• Symmetry- and Gradient-enhanced Gaussian Process Regression for the Active Learning of Potential Energy Surfaces in Porous Materials
• Ab initio machine learning in chemical compound space
• Recurrent Neural Network-based Model for Accelerated Trajectory Analysis in AIMD Simulations
• MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
• Learning to Make Chemical Predictions: the Interplay of Feature Representation, Data, and Machine Learning Algorithms
• Reconstructing Kernel-based Machine Learning Force Fields with Super-linear Convergence
• Considerations in the use of ML interaction potentials for free energy calculations
• Machine-Learned Potentials for Solvation Modeling
• GeoT: A Geometry-aware Transformer for Reliable Molecular Property Prediction and Chemically Interpretable Representation Learning
• Efficient interpolation of molecular properties across chemical compound space with low-dimensional descriptors
• Enhancing ab initio diffusion calculations in materials through Gaussian process regression
• Simplifying inverse material design problems for fixed lattices with alchemical chirality
• Neural Polarization: Toward Electron Density for Molecules by Extending Equivariant Networks
• Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations