Molecular force fields with gradient-domain machine learning: Construction and application to dynamics of small molecules with coupled cluster forces

Sauceda, Huziel E.; Chmiela, Stefan; Poltavsky, Igor; Müller, Klaus Robert; Tkatchenko, Alexandre

doi:10.1063/1.5078687

Cited by 129 publications

(181 citation statements)

References 100 publications

(148 reference statements)

Supporting

Mentioning

180

Contrasting

Order By: Relevance

“…Furthermore, since its publication in 2018, 17 separate projects to date have leveraged the Psi4NumPy framework to facilitate their development of novel quantum chemical methods. [101][102][103][104][105][106][107][108][109][110][111][112][113][114][115][116][117] Finally, Psi4NumPy is a thoroughly community-driven project; interested readers are highly encouraged to visit the repository 100 for the latest version of Psi4NumPy and to participate in "pull request" code review, issue tracking, or by contributing code to the project itself.…”

Section: A Psi4numpymentioning

confidence: 99%

PSI4 1.4: Open-source software for high-throughput quantum chemistry

Smith

Burns

Simmonett

et al. 2020

The Journal of Chemical Physics

614

477

View full text Add to dashboard Cite

Psi4 is a free and open-source ab initio electronic structure program providing Hartree-Fock, density functional theory, many-body perturbation theory, configuration interaction, density cumulant theory, symmetry-adapted perturbation theory, and coupled-cluster theory. Most of the methods are quite efficient thanks to density fitting and multi-core parallelism. The program is a hybrid of C++ and Python, and calculations may be run with very simple text files or using the Python API, facilitating post-processing and complex workflows; method developers also have access to most of Psi4's core functionality via Python. Job specification may be passed using The Molecular Sciences Software Institute (MolSSI) QCSchema data format, facilitating interoperability. A rewrite of our top-level computation driver, and concomitant adoption of the MolSSI QCArchive Infrastructure project, make the latest version of Psi4 well suited to distributed computation of large numbers of independent tasks. The project has fostered the development of independent software components that may be reused in other quantum chemistry programs. File list (2) download file view on ChemRxiv psi4.pdf (4.37 MiB) download file view on ChemRxiv supplementary_material.pdf (297.86 KiB)

show abstract

Section: A Psi4numpymentioning

confidence: 99%

PSI4 1.4: Open-source software for high-throughput quantum chemistry

Smith

Burns

Simmonett

et al. 2020

The Journal of Chemical Physics

614

477

View full text Add to dashboard Cite

show abstract

“…Crucial steps towards i-ii) have been recently taken by symmetrized gradient-domain machine learning (sGDML), a kernel-based approach to constructing molecular force fields [57,10,128,129]. Currently, sGDML already enables MD simulations with electrons and nuclei treated at essentially exact quantum-mechanical level for molecules with up to 20-30 atoms.…”

Section: Accuracy and Efficiency In Quantum-chemical Energies And Forcesmentioning

confidence: 99%

Machine Learning for Molecular Simulation

Noé

Tkatchenko

Müller

et al. 2020

Annu. Rev. Phys. Chem.

Self Cite

631

476

View full text Add to dashboard Cite

Machine learning (ML) is transforming all areas of science. The complex and time-consuming calculations in molecular simulations are particularly suitable for a machine learning revolution and have already been profoundly impacted by the application of existing ML methods. Here we review recent ML methods for molecular simulation, with particular focus on (deep) neural networks for the prediction of quantum-mechanical energies and forces, coarse-grained molecular dynamics, the extraction of free energy surfaces and kinetics and generative network approaches to sample molecular equilibrium structures and compute thermodynamics. To explain these methods and illustrate open methodological problems, we review some important principles of molecular physics and describe how they can be incorporated into machine learning structures. Finally, we identify and describe a list of open challenges for the interface between ML and molecular simulation. 1 arXiv:1911.02792v1 [physics.chem-ph] 7 Nov 2019 complex relationship between the input (the pixels) and the output (the labels) that is unknown in its explicit form but can be inferred by a suitable algorithm. Clearly, such an operating principle can be very useful in the description of atomic and molecular systems as well. We know that atomistic configurations dictate the chemical properties, and the machine can learn to associate the latter to the former without solving first principle equations, if presented with enough examples. Although different machine learning tools are available and have been applied to molecular simulation (e.g., kernel methods [2]), here we mostly focus on the use of neural networks, now often synonymously used with the term "deep learning". We assume the reader has basic knowledge of machine learning and we refer to the literature for an introduction to statistical learning theory [3,4] and deep learning [5,6].One of the first applications of machine learning in Chemistry has been to extract classical potential energy surfaces from quantum mechanical (QM) calculations, in order to efficiently perform molecular dynamics (MD) simulations that can incorporate quantum effects. The seminal work of Behler and Parrinello in this direction [7] has opened the way to a now rapidly advancing area of research [8,9,10,11,12,13,14,15]. In addition to atomistic force fields, it has been recently shown that, in the same spirit, effective molecular models at resolution coarser than atomistic can be designed by ML [16,17,18]. Analysis and simulation of MD trajectories has also been affected by ML, for instance for the definition of optimal reaction coordinates [19,20,21,22,23,24], the estimate of free energy surfaces [25,26,27,22], the construction of Markov State Models [21,23,28], and for enhancing MD sampling by learning bias potentials [29,30,31,32,33] or selecting starting configurations by active learning [34,35,36]. Finally, ML can be used to generate samples from the equilibrium distribution of a molecular system without performing MD altogether, as proposed...

show abstract

“…In this work we present an optimized implementation of the recently proposed sGDML model [50][51][52], which is able to achieve high data efficiency through the incorporation of spatial and temporal physical symmetries of molecular systems into a gradient-domain machine learning approach. Unlike traditional FFs, this global model imposes no hypothesized interaction pattern on the nuclei and is thus suited for describing any complex physical interaction.…”

Section: Introductionmentioning

confidence: 99%

sGDML: Constructing accurate and data efficient molecular force fields using machine learning

Chmiela

Sauceda

Poltavsky

et al. 2019

Computer Physics Communications

Self Cite

214

297

View full text Add to dashboard Cite

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.

show abstract

Molecular force fields with gradient-domain machine learning: Construction and application to dynamics of small molecules with coupled cluster forces

Cited by 129 publications

References 100 publications

PSI4 1.4: Open-source software for high-throughput quantum chemistry

PSI4 1.4: Open-source software for high-throughput quantum chemistry

Machine Learning for Molecular Simulation

sGDML: Constructing accurate and data efficient molecular force fields using machine learning

Contact Info

Product

Resources

About