1
|
Kabylda A, Vassilev-Galindo V, Chmiela S, Poltavsky I, Tkatchenko A. Author Correction: Efficient interatomic descriptors for accurate machine learning force fields of extended molecules. Nat Commun 2023; 14:4116. [PMID: 37433787 DOI: 10.1038/s41467-023-39798-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/13/2023] Open
Affiliation(s)
- Adil Kabylda
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg
| | - Valentin Vassilev-Galindo
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg
| | - Stefan Chmiela
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany
- BIFOLD - Berlin Institute for the Foundations of Learning and Data, 10587, Berlin, Germany
| | - Igor Poltavsky
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg
| | - Alexandre Tkatchenko
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg.
| |
Collapse
|
2
|
Kabylda A, Vassilev-Galindo V, Chmiela S, Poltavsky I, Tkatchenko A. Efficient interatomic descriptors for accurate machine learning force fields of extended molecules. Nat Commun 2023; 14:3562. [PMID: 37322039 DOI: 10.1038/s41467-023-39214-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2022] [Accepted: 05/17/2023] [Indexed: 06/17/2023] Open
Abstract
Machine learning force fields (MLFFs) are gradually evolving towards enabling molecular dynamics simulations of molecules and materials with ab initio accuracy but at a small fraction of the computational cost. However, several challenges remain to be addressed to enable predictive MLFF simulations of realistic molecules, including: (1) developing efficient descriptors for non-local interatomic interactions, which are essential to capture long-range molecular fluctuations, and (2) reducing the dimensionality of the descriptors to enhance the applicability and interpretability of MLFFs. Here we propose an automatized approach to substantially reduce the number of interatomic descriptor features while preserving the accuracy and increasing the efficiency of MLFFs. To simultaneously address the two stated challenges, we illustrate our approach on the example of the global GDML MLFF. We found that non-local features (atoms separated by as far as 15 Å in studied systems) are crucial to retain the overall accuracy of the MLFF for peptides, DNA base pairs, fatty acids, and supramolecular complexes. Interestingly, the number of required non-local features in the reduced descriptors becomes comparable to the number of local interatomic features (those below 5 Å). These results pave the way to constructing global molecular MLFFs whose cost increases linearly, instead of quadratically, with system size.
Collapse
Affiliation(s)
- Adil Kabylda
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg
| | - Valentin Vassilev-Galindo
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg
| | - Stefan Chmiela
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany
- BIFOLD - Berlin Institute for the Foundations of Learning and Data, 10587, Berlin, Germany
| | - Igor Poltavsky
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg
| | - Alexandre Tkatchenko
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg.
| |
Collapse
|
3
|
Blücher S, Müller KR, Chmiela S. Reconstructing Kernel-Based Machine Learning Force Fields with Superlinear Convergence. J Chem Theory Comput 2023. [PMID: 37156733 PMCID: PMC10373489 DOI: 10.1021/acs.jctc.2c01304] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/10/2023]
Abstract
Kernel machines have sustained continuous progress in the field of quantum chemistry. In particular, they have proven to be successful in the low-data regime of force field reconstruction. This is because many equivariances and invariances due to physical symmetries can be incorporated into the kernel function to compensate for much larger data sets. So far, the scalability of kernel machines has however been hindered by its quadratic memory and cubical runtime complexity in the number of training points. While it is known that iterative Krylov subspace solvers can overcome these burdens, their convergence crucially relies on effective preconditioners, which are elusive in practice. Effective preconditioners need to partially presolve the learning problem in a computationally cheap and numerically robust manner. Here, we consider the broad class of Nyström-type methods to construct preconditioners based on successively more sophisticated low-rank approximations of the original kernel matrix, each of which provides a different set of computational trade-offs. All considered methods aim to identify a representative subset of inducing (kernel) columns to approximate the dominant kernel spectrum.
Collapse
Affiliation(s)
- Stefan Blücher
- BIFOLD-Berlin Institue for the Foundations of Learning and Data, 10587 Berlin, Germany
- Technische Universität Berlin, Machine Learning Group, 10587 Berlin, Germany
| | - Klaus-Robert Müller
- BIFOLD-Berlin Institue for the Foundations of Learning and Data, 10587 Berlin, Germany
- Technische Universität Berlin, Machine Learning Group, 10587 Berlin, Germany
- Department of Artificial Intelligence, Korea University, Seoul 136-713, Korea
- Max Planck Institute for Informatics, 66123 Saarbrücken, Germany
- Google Research, Brain Team, 10117 Berlin, Germany
| | - Stefan Chmiela
- BIFOLD-Berlin Institue for the Foundations of Learning and Data, 10587 Berlin, Germany
- Technische Universität Berlin, Machine Learning Group, 10587 Berlin, Germany
| |
Collapse
|
4
|
Chmiela S, Vassilev-Galindo V, Unke OT, Kabylda A, Sauceda HE, Tkatchenko A, Müller KR. Accurate global machine learning force fields for molecules with hundreds of atoms. Sci Adv 2023; 9:eadf0873. [PMID: 36630510 PMCID: PMC9833674 DOI: 10.1126/sciadv.adf0873] [Citation(s) in RCA: 16] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/29/2022] [Accepted: 11/28/2022] [Indexed: 05/25/2023]
Abstract
Global machine learning force fields, with the capacity to capture collective interactions in molecular systems, now scale up to a few dozen atoms due to considerable growth of model complexity with system size. For larger molecules, locality assumptions are introduced, with the consequence that nonlocal interactions are not described. Here, we develop an exact iterative approach to train global symmetric gradient domain machine learning (sGDML) force fields (FFs) for several hundred atoms, without resorting to any potentially uncontrolled approximations. All atomic degrees of freedom remain correlated in the global sGDML FF, allowing the accurate description of complex molecules and materials that present phenomena with far-reaching characteristic correlation lengths. We assess the accuracy and efficiency of sGDML on a newly developed MD22 benchmark dataset containing molecules from 42 to 370 atoms. The robustness of our approach is demonstrated in nanosecond path-integral molecular dynamics simulations for supramolecular complexes in the MD22 dataset.
Collapse
Affiliation(s)
- Stefan Chmiela
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Berlin Institute for the Foundations of Learning and Data – BIFOLD, Germany
| | - Valentin Vassilev-Galindo
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Oliver T. Unke
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Google Research, Brain Team, Berlin, Germany
| | - Adil Kabylda
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Huziel E. Sauceda
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Berlin Institute for the Foundations of Learning and Data – BIFOLD, Germany
- Departamento de Materia Condensada, Instituto de Física, Universidad Nacional Autónoma de México, Cd. de México C.P. 04510, Mexico
- BASLEARN - TU Berlin/BASF Joint Lab for Machine Learning, Technische Universität Berlin, 10587 Berlin, Germany
| | - Alexandre Tkatchenko
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Klaus-Robert Müller
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Berlin Institute for the Foundations of Learning and Data – BIFOLD, Germany
- Google Research, Brain Team, Berlin, Germany
- Max Planck Institute for Informatics, Stuhlsatzenhausweg, 66123 Saarbrücken, Germany
- Department of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, Korea
| |
Collapse
|
5
|
Schmitz N, Müller KR, Chmiela S. Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields. J Phys Chem Lett 2022; 13:10183-10189. [PMID: 36279418 PMCID: PMC9639201 DOI: 10.1021/acs.jpclett.2c02632] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/09/2023]
Abstract
Reconstructing force fields (FFs) from atomistic simulation data is a challenge since accurate data can be highly expensive. Here, machine learning (ML) models can help to be data economic as they can be successfully constrained using the underlying symmetry and conservation laws of physics. However, so far, every descriptor newly proposed for an ML model has required a cumbersome and mathematically tedious remodeling. We therefore propose using modern techniques from algorithmic differentiation within the ML modeling process, effectively enabling the usage of novel descriptors or models fully automatically at an order of magnitude higher computational efficiency. This paradigmatic approach enables not only a versatile usage of novel representations and the efficient computation of larger systems─all of high value to the FF community─but also the simple inclusion of further physical knowledge, such as higher-order information (e.g., Hessians, more complex partial differential equations constraints etc.), even beyond the presented FF domain.
Collapse
Affiliation(s)
| | - Klaus-Robert Müller
- Machine
Learning Group, Technische Universität
Berlin, 10587Berlin, Germany
- BIFOLD
- Berlin Institute for the Foundations of Learning and Data, 10587Berlin, Germany
- Department
of Artificial Intelligence, Korea University, Seongbuk-gu, Seoul02841, Korea
- Max
Planck Institute for Informatics, Stuhlsatzenhausweg, 66123Saarbrücken, Germany
- Google
Research, Brain Team, 10117Berlin, Germany
| | - Stefan Chmiela
- Machine
Learning Group, Technische Universität
Berlin, 10587Berlin, Germany
- BIFOLD
- Berlin Institute for the Foundations of Learning and Data, 10587Berlin, Germany
| |
Collapse
|
6
|
Unke OT, Chmiela S, Gastegger M, Schütt KT, Sauceda HE, Müller KR. SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects. Nat Commun 2021; 12:7273. [PMID: 34907176 PMCID: PMC8671403 DOI: 10.1038/s41467-021-27504-0] [Citation(s) in RCA: 74] [Impact Index Per Article: 24.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2021] [Accepted: 11/16/2021] [Indexed: 01/12/2023] Open
Abstract
Machine-learned force fields combine the accuracy of ab initio methods with the efficiency of conventional force fields. However, current machine-learned force fields typically ignore electronic degrees of freedom, such as the total charge or spin state, and assume chemical locality, which is problematic when molecules have inconsistent electronic states, or when nonlocal effects play a significant role. This work introduces SpookyNet, a deep neural network for constructing machine-learned force fields with explicit treatment of electronic degrees of freedom and nonlocality, modeled via self-attention in a transformer architecture. Chemically meaningful inductive biases and analytical corrections built into the network architecture allow it to properly model physical limits. SpookyNet improves upon the current state-of-the-art (or achieves similar performance) on popular quantum chemistry data sets. Notably, it is able to generalize across chemical and conformational space and can leverage the learned chemical insights, e.g. by predicting unknown spin states, thus helping to close a further important remaining gap for today's machine learning models in quantum chemistry.
Collapse
Affiliation(s)
- Oliver T Unke
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany.
- DFG Cluster of Excellence "Unifying Systems in Catalysis" (UniSysCat), Technische Universität Berlin, 10623, Berlin, Germany.
| | - Stefan Chmiela
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany
| | - Michael Gastegger
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany
- DFG Cluster of Excellence "Unifying Systems in Catalysis" (UniSysCat), Technische Universität Berlin, 10623, Berlin, Germany
| | - Kristof T Schütt
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany
| | - Huziel E Sauceda
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany
- BASLEARN, BASF-TU joint Lab, Technische Universität Berlin, 10587, Berlin, Germany
| | - Klaus-Robert Müller
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany.
- Department of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul, 02841, Korea.
- Max Planck Institute for Informatics, Stuhlsatzenhausweg, 66123, Saarbrücken, Germany.
- BIFOLD-Berlin Institute for the Foundations of Learning and Data, Berlin, Germany.
- Google Research, Brain team, Berlin, Germany.
| |
Collapse
|
7
|
Keith JA, Vassilev-Galindo V, Cheng B, Chmiela S, Gastegger M, Müller KR, Tkatchenko A. Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems. Chem Rev 2021; 121:9816-9872. [PMID: 34232033 PMCID: PMC8391798 DOI: 10.1021/acs.chemrev.1c00107] [Citation(s) in RCA: 170] [Impact Index Per Article: 56.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2021] [Indexed: 12/23/2022]
Abstract
Machine learning models are poised to make a transformative impact on chemical sciences by dramatically accelerating computational algorithms and amplifying insights available from computational chemistry methods. However, achieving this requires a confluence and coaction of expertise in computer science and physical sciences. This Review is written for new and experienced researchers working at the intersection of both fields. We first provide concise tutorials of computational chemistry and machine learning methods, showing how insights involving both can be achieved. We follow with a critical review of noteworthy applications that demonstrate how computational chemistry and machine learning can be used together to provide insightful (and useful) predictions in molecular and materials modeling, retrosyntheses, catalysis, and drug design.
Collapse
Affiliation(s)
- John A. Keith
- Department
of Chemical and Petroleum Engineering Swanson School of Engineering, University of Pittsburgh, Pittsburgh, Pennsylvania 15261, United States
| | - Valentin Vassilev-Galindo
- Department
of Physics and Materials Science, University
of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Bingqing Cheng
- Accelerate
Programme for Scientific Discovery, Department
of Computer Science and Technology, 15 J. J. Thomson Avenue, Cambridge CB3 0FD, United Kingdom
| | - Stefan Chmiela
- Department
of Software Engineering and Theoretical Computer Science, Technische Universität Berlin, 10587, Berlin, Germany
| | - Michael Gastegger
- Department
of Software Engineering and Theoretical Computer Science, Technische Universität Berlin, 10587, Berlin, Germany
| | - Klaus-Robert Müller
- Machine
Learning Group, Technische Universität
Berlin, 10587, Berlin, Germany
- Department
of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul, 02841, Korea
- Max-Planck-Institut für Informatik, 66123 Saarbrücken, Germany
- Google Research, Brain Team, 10117 Berlin, Germany
| | - Alexandre Tkatchenko
- Department
of Physics and Materials Science, University
of Luxembourg, L-1511 Luxembourg City, Luxembourg
| |
Collapse
|
8
|
Abstract
In recent years, the use of machine learning (ML) in computational chemistry has enabled numerous advances previously out of reach due to the computational complexity of traditional electronic-structure methods. One of the most promising applications is the construction of ML-based force fields (FFs), with the aim to narrow the gap between the accuracy of ab initio methods and the efficiency of classical FFs. The key idea is to learn the statistical relation between chemical structure and potential energy without relying on a preconceived notion of fixed chemical bonds or knowledge about the relevant interactions. Such universal ML approximations are in principle only limited by the quality and quantity of the reference data used to train them. This review gives an overview of applications of ML-FFs and the chemical insights that can be obtained from them. The core concepts underlying ML-FFs are described in detail, and a step-by-step guide for constructing and testing them from scratch is given. The text concludes with a discussion of the challenges that remain to be overcome by the next generation of ML-FFs.
Collapse
Affiliation(s)
- Oliver
T. Unke
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
- DFG
Cluster of Excellence “Unifying Systems in Catalysis”
(UniSysCat), Technische Universität Berlin, 10623 Berlin, Germany
| | - Stefan Chmiela
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
| | - Huziel E. Sauceda
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
- BASLEARN,
BASF-TU Joint Lab, Technische Universität
Berlin, 10587 Berlin, Germany
| | - Michael Gastegger
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
- DFG
Cluster of Excellence “Unifying Systems in Catalysis”
(UniSysCat), Technische Universität Berlin, 10623 Berlin, Germany
- BASLEARN,
BASF-TU Joint Lab, Technische Universität
Berlin, 10587 Berlin, Germany
| | - Igor Poltavsky
- Department
of Physics and Materials Science, University
of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Kristof T. Schütt
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
| | - Alexandre Tkatchenko
- Department
of Physics and Materials Science, University
of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Klaus-Robert Müller
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
- BIFOLD−Berlin
Institute for the Foundations of Learning and Data, Berlin, Germany
- Department
of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, Korea
- Max Planck
Institute for Informatics, Stuhlsatzenhausweg, 66123 Saarbrücken, Germany
- Google
Research, Brain Team, Berlin, Germany
| |
Collapse
|
9
|
Sauceda HE, Vassilev-Galindo V, Chmiela S, Müller KR, Tkatchenko A. Dynamical strengthening of covalent and non-covalent molecular interactions by nuclear quantum effects at finite temperature. Nat Commun 2021; 12:442. [PMID: 33469007 PMCID: PMC7815839 DOI: 10.1038/s41467-020-20212-1] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2020] [Accepted: 11/12/2020] [Indexed: 11/08/2022] Open
Abstract
Nuclear quantum effects (NQE) tend to generate delocalized molecular dynamics due to the inclusion of the zero point energy and its coupling with the anharmonicities in interatomic interactions. Here, we present evidence that NQE often enhance electronic interactions and, in turn, can result in dynamical molecular stabilization at finite temperature. The underlying physical mechanism promoted by NQE depends on the particular interaction under consideration. First, the effective reduction of interatomic distances between functional groups within a molecule can enhance the n → π* interaction by increasing the overlap between molecular orbitals or by strengthening electrostatic interactions between neighboring charge densities. Second, NQE can localize methyl rotors by temporarily changing molecular bond orders and leading to the emergence of localized transient rotor states. Third, for noncovalent van der Waals interactions the strengthening comes from the increase of the polarizability given the expanded average interatomic distances induced by NQE. The implications of these boosted interactions include counterintuitive hydroxyl-hydroxyl bonding, hindered methyl rotor dynamics, and molecular stiffening which generates smoother free-energy surfaces. Our findings yield new insights into the versatile role of nuclear quantum fluctuations in molecules and materials.
Collapse
Affiliation(s)
- Huziel E Sauceda
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg.
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany.
- BASLEARN, BASF-TU joint Lab, Technische Universität Berlin, 10587, Berlin, Germany.
| | - Valentin Vassilev-Galindo
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg
| | - Stefan Chmiela
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany
| | - Klaus-Robert Müller
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany.
- Department of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul, 02841, Korea.
- Max Planck Institute for Informatics, Stuhlsatzenhausweg, 66123, Saarbrücken, Germany.
- Google Research, Brain team, Berlin, Germany.
| | - Alexandre Tkatchenko
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg.
| |
Collapse
|
10
|
Sauceda HE, Gastegger M, Chmiela S, Müller KR, Tkatchenko A. Molecular force fields with gradient-domain machine learning (GDML): Comparison and synergies with classical force fields. J Chem Phys 2020; 153:124109. [DOI: 10.1063/5.0023005] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022] Open
Affiliation(s)
- Huziel E. Sauceda
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg, Luxembourg
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- BASLEARN, BASF-TU Joint Lab, Technische Universität Berlin, 10587 Berlin, Germany
| | - Michael Gastegger
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- BASLEARN, BASF-TU Joint Lab, Technische Universität Berlin, 10587 Berlin, Germany
- DFG Cluster of Excellence “Unifying Systems in Catalysis” (UniSysCat), Technische Universität Berlin, 10623 Berlin, Germany
| | - Stefan Chmiela
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
| | - Klaus-Robert Müller
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Department of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul 136-713, South Korea
- Max Planck Institute for Informatics, Stuhlsatzenhausweg, 66123 Saarbrücken, Germany
- Google Research, Brain Team, Berlin, Germany
| | - Alexandre Tkatchenko
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg, Luxembourg
| |
Collapse
|
11
|
Wang J, Chmiela S, Müller KR, Noé F, Clementi C. Ensemble learning of coarse-grained molecular dynamics force fields with a kernel approach. J Chem Phys 2020; 152:194106. [DOI: 10.1063/5.0007276] [Citation(s) in RCA: 27] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/05/2023] Open
Affiliation(s)
- Jiang Wang
- Center for Theoretical Biological Physics, Rice University, Houston, Texas 77005, USA
- Department of Chemistry, Rice University, Houston, Texas 77005, USA
| | - Stefan Chmiela
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
| | - Klaus-Robert Müller
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Department of Brain and Cognitive Engineering, Korea University, Seoul 02841, South Korea
- Max Planck Institute for Informatics, Saarbrücken 66123, Germany
| | - Frank Noé
- Center for Theoretical Biological Physics, Rice University, Houston, Texas 77005, USA
- Department of Chemistry, Rice University, Houston, Texas 77005, USA
- Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 6, 14195 Berlin, Germany
- Department of Physics, Freie Universität Berlin, Arnimallee 14, 14195 Berlin, Germany
| | - Cecilia Clementi
- Center for Theoretical Biological Physics, Rice University, Houston, Texas 77005, USA
- Department of Chemistry, Rice University, Houston, Texas 77005, USA
- Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 6, 14195 Berlin, Germany
- Department of Physics, Freie Universität Berlin, Arnimallee 14, 14195 Berlin, Germany
- Department of Physics, Rice University, Houston, Texas 77005, USA
| |
Collapse
|
12
|
Sauceda HE, Chmiela S, Poltavsky I, Müller KR, Tkatchenko A. Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights. Machine Learning Meets Quantum Physics 2020. [DOI: 10.1007/978-3-030-40245-7_14] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/02/2023]
|
13
|
Sauceda HE, Chmiela S, Poltavsky I, Müller KR, Tkatchenko A. Molecular force fields with gradient-domain machine learning: Construction and application to dynamics of small molecules with coupled cluster forces. J Chem Phys 2019; 150:114102. [DOI: 10.1063/1.5078687] [Citation(s) in RCA: 56] [Impact Index Per Article: 11.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Affiliation(s)
- Huziel E. Sauceda
- Fritz-Haber-Institut der Max-Planck-Gesellschaft, 14195 Berlin, Germany
| | - Stefan Chmiela
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
| | - Igor Poltavsky
- Physics and Materials Science Research Unit, University of Luxembourg, L-1511 Luxembourg, Luxembourg
| | - Klaus-Robert Müller
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Department of Brain and Cognitive Engineering, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, South Korea
- Max Planck Institute for Informatics, Stuhlsatzenhausweg, 66123 Saarbrücken, Germany
| | - Alexandre Tkatchenko
- Physics and Materials Science Research Unit, University of Luxembourg, L-1511 Luxembourg, Luxembourg
| |
Collapse
|
14
|
Chmiela S, Tkatchenko A, Sauceda HE, Poltavsky I, Schütt KT, Müller KR. Machine learning of accurate energy-conserving molecular force fields. Sci Adv 2017; 3:e1603015. [PMID: 28508076 PMCID: PMC5419702 DOI: 10.1126/sciadv.1603015] [Citation(s) in RCA: 441] [Impact Index Per Article: 63.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/01/2016] [Accepted: 03/07/2017] [Indexed: 05/20/2023]
Abstract
Using conservation of energy-a fundamental property of closed classical and quantum mechanical systems-we develop an efficient gradient-domain machine learning (GDML) approach to construct accurate molecular force fields using a restricted number of samples from ab initio molecular dynamics (AIMD) trajectories. The GDML implementation is able to reproduce global potential energy surfaces of intermediate-sized molecules with an accuracy of 0.3 kcal mol-1 for energies and 1 kcal mol-1 Å̊-1 for atomic forces using only 1000 conformational geometries for training. We demonstrate this accuracy for AIMD trajectories of molecules, including benzene, toluene, naphthalene, ethanol, uracil, and aspirin. The challenge of constructing conservative force fields is accomplished in our work by learning in a Hilbert space of vector-valued functions that obey the law of energy conservation. The GDML approach enables quantitative molecular dynamics simulations for molecules at a fraction of cost of explicit AIMD calculations, thereby allowing the construction of efficient force fields with the accuracy and transferability of high-level ab initio methods.
Collapse
Affiliation(s)
- Stefan Chmiela
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
| | - Alexandre Tkatchenko
- Physics and Materials Science Research Unit, University of Luxembourg, L-1511 Luxembourg, Luxembourg
- Fritz-Haber-Institut der Max-Planck-Gesellschaft, 14195 Berlin, Germany
| | - Huziel E. Sauceda
- Fritz-Haber-Institut der Max-Planck-Gesellschaft, 14195 Berlin, Germany
| | - Igor Poltavsky
- Physics and Materials Science Research Unit, University of Luxembourg, L-1511 Luxembourg, Luxembourg
| | - Kristof T. Schütt
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
| | - Klaus-Robert Müller
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Department of Brain and Cognitive Engineering, Korea University, Anam-dong, Seongbuk-gu, Seoul 136-713, Korea
- Max Planck Institute for Informatics, Stuhlsatzenhausweg, 66123 Saarbrücken, Germany
| |
Collapse
|