M. Cools-Ceuppens

Modeling Electronic Response Properties with an Explicit-Electron Machine Learning Potential

M. Cools-Ceuppens, J. Dambre, T. Verstraelen

Journal of Chemical Theory and Computation

18, 3, 1672-1691

2023

A1

Abstract

Explicit-electron force fields introduce electrons or electron pairs as semiclassical particles in force fields or empirical potentials, which are suitable for molecular dynamics simulations. Even though semiclassical electrons are a drastic simplification compared to a quantum-mechanical electronic wave function, they still retain a relatively detailed electronic model compared to conventional polarizable and reactive force fields. The ability of explicit-electron models to describe chemical reactions and electronic response properties has already been demonstrated, yet the description of short-range interactions for a broad range of chemical systems remains challenging. In this work, we present the electron machine learning potential (eMLP), a new explicit electron force field in which the short-range interactions are modeled with machine learning. The electron pair particles will be located at well-defined positions, derived from localized molecular orbitals or Wannier centers, naturally imposing the correct dielectric and piezoelectric behavior of the system. The eMLP is benchmarked on two newly constructed data sets: eQM7, an extension of the QM7 data set for small molecules, and a data set for the crystalline beta-glycine. It is shown that the eMLP can predict dipole moments, polarizabilities, and IR-spectra of unseen molecules with high precision. Furthermore, a variety of response properties, for example, stiffness or piezoelectric constants, can be accurately reproduced.

Green Open Access

DOI

http://dx.doi.org/10.1021/acs.jctc.1c00978

Modeling electronic response properties with an explicit-electron machine learning potential

M. Cools-Ceuppens, J. Dambre, T. Verstraelen

Journal of Chemical Theory and Computation

Volume 18, Issue 3, Pages 1672-1691

2023

A1

Abstract

Explicit-electron force fields introduce electrons or electron pairs as semiclassical particles in force fields or empirical potentials, which are suitable for molecular dynamics simulations. Even though semiclassical electrons are a drastic simplification compared to a quantum-mechanical electronic wave function, they still retain a relatively detailed electronic model compared to conventional polarizable and reactive force fields. The ability of explicit-electron models to describe chemical reactions and electronic response properties has already been demonstrated, yet the description of short-range interactions for a broad range of chemical systems remains challenging. In this work, we present the electron machine learning potential (eMLP), a new explicit electron force field in which the short-range interactions are modeled with machine learning. The electron pair particles will be located at well-defined positions, derived from localized molecular orbitals or Wannier centers, naturally imposing the correct dielectric and piezoelectric behavior of the system. The eMLP is benchmarked on two newly constructed data sets: eQM7, an extension of the QM7 data set for small molecules, and a data set for the crystalline beta-glycine. It is shown that the eMLP can predict dipole moments, polarizabilities, and IR-spectra of unseen molecules with high precision. Furthermore, a variety of response properties, for example, stiffness or piezoelectric constants, can be accurately reproduced.

DOI

https://doi.org/10.1021/acs.jctc.1c00978

Quantum free energy profiles for molecular proton transfers

A. Lamaire, M. Cools-Ceuppens, M. Bocus, T. Verstraelen, V. Van Speybroeck

Journal of Chemical Theory and Computation

19, 1, 18–24

2023

A1

Abstract

Although many molecular dynamics simulations treat the atomic nuclei as classical particles, an adequate description of nuclear quantum effects (NQEs) is indispensable when studying proton transfer reactions. Herein, quantum free energy profiles are constructed for three typical proton transfers, which properly take NQEs into account using the path integral formalism. The computational cost of the simulations is kept tractable by deriving machine learning potentials. It is shown that the classical and quasi-classical centroid free energy profiles of the proton transfers deviate substantially from the exact quantum free energy profile.

DOI

http://dx.doi.org/10.1021/acs.jctc.2c00874

Nuclear quantum effects on zeolite proton hopping kinetics explored with machine learning potentials and path integral molecular dynamics

M. Bocus, R. Goeminne, A. Lamaire, M. Cools-Ceuppens, T. Verstraelen, V. Van Speybroeck

Nature Communications

14, 1008

2023

A1

Abstract

Proton hopping is a key reactive process within zeolite catalysis. However, the accurate determination of its kinetics poses major challenges both for theoreticians and experimentalists. Nuclear quantum effects (NQEs) are known to influence the structure and dynamics of protons, but their rigorous inclusion through the path integral molecular dynamics (PIMD) formalism was so far beyond reach for zeolite catalyzed processes due to the excessive computational cost of evaluating all forces and energies at the Density Functional Theory (DFT) level. Herein, we overcome this limitation by training first a reactive machine learning potential (MLP) that can reproduce with high fidelity the DFT potential energy surface of proton hopping around the first Al coordination sphere in the H-CHA zeolite. The MLP offers an immense computational speedup, enabling us to derive accurate reaction kinetics beyond standard transition state theory for the proton hopping reaction. Overall, more than 0.6 μs of simulation time was needed, which is far beyond reach of any standard DFT approach. NQEs are found to significantly impact the proton hopping kinetics up to ~473 K. Moreover, PIMD simulations with deuterium can be performed without any additional training to compute kinetic isotope effects over a broad range of temperatures.

Gold Open Access

DOI

https://doi.org/10.1038/s41467-023-36666-y

Machine Learning Potentials for Metal-Organic Frameworks using an Incremental Learning Approach

S. Vandenhaute, M. Cools-Ceuppens, S. DeKeyser, T. Verstraelen, V. Van Speybroeck

npj Computational Materials

9, 1, 19

2023

A1

Abstract

Computational modeling of physical processes in metal-organic frameworks (MOFs) is highly challenging due to the presence of spatial heterogeneities and complex operating conditions which affect their behavior. Density functional theory (DFT) may describe interatomic interactions at the quantum mechanical level, but is computationally too expensive for systems beyond the nanometer and picosecond range. Herein, we propose an incremental learning scheme to construct accurate and data-efficient machine learning potentials for MOFs. The scheme builds on the power of equivariant neural network potentials in combination with parallelized enhanced sampling and on-the-fly training to simultaneously explore and learn the phase space in an iterative manner. With only a few hundred single-point DFT evaluations per material, accurate and transferable potentials are obtained, even for flexible frameworks with multiple structurally different phases. The incremental learning scheme is universally applicable and may pave the way to model framework materials in larger spatiotemporal windows with higher accuracy.

A flexible and scalable implementation of the methodology is available in Psiflow.

Gold Open Access

DOI

http://dx.doi.org/10.1038/s41524-023-00969-x

Modeling Electronic Response Properties with an Explicit-Electron Machine Learning Potential

M. Cools-Ceuppens, J. Dambre, T. Verstraelen

Journal of Chemical Theory and Computation (JCTC)

18 (3), 1672–1691

2022

A1

Abstract

Explicit-electron force fields introduce electrons or electron pairs as semiclassical particles in force fields or empirical potentials, which are suitable for molecular dynamics simulations. Even though semiclassical electrons are a drastic simplification compared to a quantum-mechanical electronic wave function, they still retain a relatively detailed electronic model compared to conventional polarizable and reactive force fields. The ability of explicit-electron models to describe chemical reactions and electronic response properties has already been demonstrated, yet the description of short-range interactions for a broad range of chemical systems remains challenging. In this work, we present the electron machine learning potential (eMLP), a new explicit electron force field in which the short-range interactions are modeled with machine learning. The electron pair particles will be located at well-defined positions, derived from localized molecular orbitals or Wannier centers, naturally imposing the correct dielectric and piezoelectric behavior of the system. The eMLP is benchmarked on two newly constructed data sets: eQM7, an extension of the QM7 data set for small molecules, and a data set for the crystalline β-glycine. It is shown that the eMLP can predict dipole moments, polarizabilities, and IR-spectra of unseen molecules with high precision. Furthermore, a variety of response properties, for example, stiffness or piezoelectric constants, can be accurately reproduced.

DOI

https://doi.org/10.1021/acs.jctc.1c00978

IOData: A python library for reading, writing, and converting computational chemistry file formats and generating input files

T. Verstraelen, W. Adams, L. Pujal, A. Tehrani, B. D. Kelly, L. Macaya, F. Meng, M. Richer, R. Hernández-Esparza, X. D. Yang, M. Chan, T. D. Kim, M. Cools-Ceuppens, V. Chuiko, E. Vohringer-Martinez, P.W. Ayers, F. Heidar-Zadeh

Journal of Computational Chemistry

45, 6, 458--464

2021

A1

Abstract

IOData is a free and open‐source Python library for parsing, storing, and converting various file formats commonly used by quantum chemistry, molecular dynamics, and plane‐wave density‐functional‐theory software programs. In addition, IOData supports a flexible framework for generating input files for various software packages. While designed and released for stand‐alone use, its original purpose was to facilitate the interoperability of various modules in the HORTON and ChemTools software packages with external (third‐party) molecular quantum chemistry and solid‐state density‐functional‐theory packages. IOData is designed to be easy to use, maintain, and extend; this is why we wrote IOData in Python and adopted many principles of modern software development, including comprehensive documentation, extensive testing, continuous integration/delivery protocols, and package management. This article is the official release note of the IOData library.