Gradient-domain machine learning (GDML) is an accurate and efficient approach to learn a molecular potential and associated force field based on the kernel ridge regression algorithm. Here, we demonstrate its application to learn an effective coarse-grained (CG) model from all-atom simulation data in a sample efficient manner. The CG force field is learned by following the thermodynamic consistency principle, here by minimizing the error between the predicted CG force and the all-atom mean force in the CG coordinates. Solving this problem by GDML directly is impossible because coarse-graining requires averaging over many training data points, resulting in impractical memory requirements for storing the kernel matrices. In this work, we propose a data-efficient and memory-saving alternative. Using ensemble learning and stratified sampling, we propose a 2-layer training scheme that enables GDML to learn an effective CG model. We illustrate our method on a simple biomolecular system, alanine dipeptide, by reconstructing the free energy landscape of a CG variant of this molecule. Our novel GDML training scheme yields a smaller free energy error than neural networks when the training set is small, and a comparably high accuracy when the training set is sufficiently large.
REFERENCES
1.
K.
Lindorff-Larsen
, S.
Piana
, R. O.
Dror
, and D. E.
Shaw
, “How fast-folding proteins fold
,” Science
334
, 517
–520
(2011
).2.
I.
Buch
, M. J.
Harvey
, T.
Giorgino
, D. P.
Anderson
, and G.
De Fabritiis
, “High-throughput all-atom molecular dynamics simulations using distributed computing
,” J. Chem. Inf. Model.
50
, 397
–403
(2010
).3.
M.
Shirts
and V. S.
Pande
, “Screen savers of the world unite!
,” Science
290
, 1903
–1904
(2000
).4.
R. O.
Dror
, A. C.
Pan
, D. H.
Arlow
, D. W.
Borhani
, P.
Maragakis
, Y.
Shan
, H.
Xu
, and D. E.
Shaw
, “Pathway and mechanism of drug binding to g-protein-coupled receptors
,” Proc. Natl. Acad. Sci. U. S. A.
108
, 13118
–13123
(2011
).5.
D.
Shukla
, Y.
Meng
, B.
Roux
, and V. S.
Pande
, “Activation pathway of src kinase reveals intermediate states as targets for drug design
,” Nat. Commun.
5
, 3397
(2014
).6.
N.
Plattner
and F.
Noé
, “Protein conformational plasticity and complex ligand binding kinetics explored by atomistic simulations and markov models
,” Nat. Commun.
6
, 7653
(2015
).7.
N.
Plattner
, S.
Doerr
, G.
De Fabritiis
, and F.
Noé
, “Protein-protein association and binding mechanism resolved in atomic detail
,” Nat. Chem.
9
, 1005
–1011
(2017
).8.
F.
Paul
, C.
Wehmeyer
, E. T.
Abualrous
, H.
Wu
, M. D.
Crabtree
, J.
Schöneberg
, J.
Clarke
, C.
Freund
, T. R.
Weikl
, and F.
Noé
, “Protein-ligand kinetics on the seconds timescale from atomistic simulations
,” Nat. Commun.
8
, 1095
(2017
).9.
F.
Noé
, A.
Tkatchenko
, K.-R.
Müller
, and C.
Clementi
, “Machine learning for molecular simulation
,” Annu. Rev. Phys. Chem.
71
(1
), 361
–390
(2020
).10.
D.
Frenkel
and B.
Smit
, Understanding Molecular Simulation: From Algorithms to Applications
, 2nd ed. (Academic Press
, 2001
).11.
G. M.
Torrie
and J. P.
Valleau
, “Nonphysical sampling distributions in Monte Carlo free-energy estimation: Umbrella sampling
,” J. Comput. Phys.
23
(2
), 187
–199
(1977
).12.
J.
Kästner
, “Umbrella sampling
,” Wiley Interdiscip. Rev.: Comput. Mol. Sci.
1
(6
), 932
–942
(2011
).13.
R. H.
Swendsen
and J. S.
Wang
, “Replica Monte Carlo simulation of spin-glasses
,” Phys. Rev. Lett.
57
, 2607
–2609
(1986
).14.
R. M.
Neal
, “Sampling from multimodal distributions using tempered transitions
,” Stat. Comput.
6
(4
), 353
–366
(1996
).15.
R.
Rajamani
, K. J.
Naidoo
, and J.
Gao
, “Implementation of an adaptive umbrella sampling method for the calculation of multidimensional potential of mean force of chemical reactions in solution
,” Proteins
24
, 1775
–1781
(2003
).16.
J.
Preto
and C.
Clementi
, “Fast recovery of free energy landscapes via diffusion-map-directed molecular dynamics
,” Phys. Chem. Chem. Phys.
16
, 19181
–19191
(2014
).17.
G. R.
Bowman
, D. L.
Ensign
, and V. S.
Pande
, “Enhanced modeling via network theory: Adaptive sampling of Markov state models
,” J. Chem. Theory Comput.
6
(3
), 787
–794
(2010
).18.
C.
Clementi
, “Coarse-grained models of protein folding: Toy-models or predictive tools?
,” Curr. Opin. Struct. Biol.
18
, 10
–15
(2008
).19.
A.
Davtyan
, N. P.
Schafer
, W.
Zheng
, C.
Clementi
, P. G.
Wolynes
, and G. A.
Papoian
, “AWSEM-MD: Protein structure prediction using coarse-grained physical potentials and bioinformatically based local structure biasing
,” J. Phys. Chem. B
116
(29
), 8494
–8503
(2012
).20.
S.
Izvekov
and G. A.
Voth
, “A multiscale coarse-graining method for biomolecular systems
,” J. Phys. Chem. B
109
(7
), 2469
–2473
(2005
).21.
S. J.
Marrink
, A. H.
de Vries
, and A. E.
Mark
, “Coarse grained model for semiquantitative lipid simulations
,” J. Phys. Chem. B
108
(2
), 750
–760
(2004
).22.
F.
Müller-Plathe
, “Coarse-graining in polymer simulation: From the atomistic to the mesoscopic scale and back
,” ChemPhysChem
3
(9
), 754
–769
(2002
).23.
W. G.
Noid
, “Perspective: Coarse-grained models for biomolecular systems
,” J. Chem. Phys.
139
(9
), 090901
(2013
).24.
S. O.
Nielsen
, C. F.
Lopez
, G.
Srinivas
, and M. L.
Klein
, “A coarse grain model for n-alkanes parameterized from surface tension data
,” J. Chem. Phys.
119
(14
), 7043
–7049
(2003
).25.
S.
Matysiak
and C.
Clementi
, “Optimal combination of theory and experiment for the characterization of the protein folding landscape of S6: How far can a minimalist model go?
,” J. Mol. Biol.
343
, 235
–248
(2004
).26.
S.
Matysiak
and C.
Clementi
, “Minimalist protein model as a diagnostic tool for misfolding and aggregation
,” J. Mol. Biol.
363
, 297
–308
(2006
).27.
J.
Chen
, J.
Chen
, G.
Pinamonti
, and C.
Clementi
, “Learning effective molecular models from experimental observables
,” J. Chem. Theory Comput.
14
(7
), 3849
–3858
(2018
).28.
A. P.
Lyubartsev
and A.
Laaksonen
, “Calculation of effective interaction potentials from radial distribution functions: A reverse Monte Carlo approach
,” Phys. Rev. E
52
(4
), 3730
–3737
(1995
).29.
M.
Praprotnik
, L. D.
Site
, and K.
Kremer
, “Multiscale simulation of soft matter: From scale bridging to adaptive resolution
,” Annu. Rev. Phys. Chem.
59
(1
), 545
–571
(2008
).30.
Y.
Wang
, W. G.
Noid
, P.
Liu
, and G. A.
Voth
, “Effective force coarse-graining
,” Phys. Chem. Chem. Phys.
11
(12)
, 2002
(2009
).31.
M. S.
Shell
, “The relative entropy is fundamental to multiscale and inverse thermodynamic problems
,” J. Phys. Chem.
129
(14
), 144108
(2008
).32.
F.
Noé
, S.
Olsson
, J.
Köhler
, and H.
Wu
, “Boltzmann generators: Sampling equilibrium states of many-body systems with deep learning
,” Science
365
(6457
), eaaw1147
(2019
).33.
F.
Noé
, G.
De Fabritiis
, and C.
Clementi
, “Machine learning for protein folding and dynamics
,” Curr. Opin. Struct. Biol.
60
, 77
–84
(2020
).34.
K. T.
Schütt
, M.
Gastegger
, A.
Tkatchenko
, K.-R.
Müller
, and R. J.
Maurer
, “Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions
,” Nat. Commun.
10
(1
), 5024
(2019
).35.
J.
Behler
and M.
Parrinello
, “Generalized neural-network representation of high-dimensional potential-energy surfaces
,” Phys. Rev. Lett.
98
, 146401
(2007
).36.
A. P.
Bartók
, M. C.
Payne
, R.
Kondor
, and G.
Csányi
, “Gaussian approximation potentials: The accuracy of quantum mechanics, without the electrons
,” Phys. Rev. Lett.
104
(13
), 136403
(2010
).37.
M.
Rupp
, A.
Tkatchenko
, K.-R.
Müller
, and O. A.
von Lilienfeld
, “Fast and accurate modeling of molecular atomization energies with machine learning
,” Phys. Rev. Lett.
108
(5
), 058301
(2012
).38.
A. P.
Bartók
, M. J.
Gillan
, F. R.
Manby
, and G.
Csányi
, “Machine-learning approach for one- and two-body corrections to density functional theory: Applications to molecular and condensed water
,” Phys. Rev. B
88
(5
), 054104
(2013
).39.
J. S.
Smith
, O.
Isayev
, and A. E.
Roitberg
, “ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
,” Chem. Sci.
8
(4
), 3192
–3203
(2017
).40.
A. P.
Bartók
, S.
De
, C.
Poelking
, N.
Bernstein
, J. R.
Kermode
, G.
Csányi
, and M.
Ceriotti
, “Machine learning unifies the modeling of materials and molecules
,” Sci. Adv.
3
(12
), e1701816
(2017
).41.
K. T.
Schütt
, F.
Arbabzadah
, S.
Chmiela
, K. R.
Müller
, and A.
Tkatchenko
, “Quantum-chemical insights from deep tensor neural networks
,” Nat. Commun.
8
, 13890
(2017
).42.
J. S.
Smith
, B.
Nebgen
, N.
Lubbers
, O.
Isayev
, and A. E.
Roitberg
, “Less is more: Sampling chemical space with active learning
,” J. Chem. Phys.
148
(24
), 241733
(2018
).43.
K. T.
Schütt
, H. E.
Sauceda
, P.-J.
Kindermans
, A.
Tkatchenko
, and K.-R.
Müller
, “SchNet—A deep learning architecture for molecules and materials
,” J. Chem. Phys.
148
(24
), 241722
(2018
).44.
A.
Grisafi
, D. M.
Wilkins
, G.
Csányi
, and M.
Ceriotti
, “Symmetry-adapted machine learning for tensorial properties of atomistic systems
,” Phys. Rev. Lett.
120
(3
), 036002
(2018
).45.
G.
Imbalzano
, A.
Anelli
, D.
Giofré
, S.
Klees
, J.
Behler
, and M.
Ceriotti
, “Automatic selection of atomic fingerprints and reference configurations for machine-learning potentials
,” J. Chem. Phys.
148
(24
), 241730
(2018
).46.
T. T.
Nguyen
, E.
Székely
, G.
Imbalzano
, J.
Behler
, G.
Csányi
, M.
Ceriotti
, A. W.
Götz
, and F.
Paesani
, “Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions
,” J. Chem. Phys.
148
(24
), 241725
(2018
).47.
L.
Zhang
, J.
Han
, H.
Wang
, W. A.
Saidi
, R.
Car
, and W. E.
, “End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems
,” Proceedings of the 32nd International Conference on Neural Information Processing Systems (NuerIPS 2018)
(NIPS
, 2018
), pp. 4436
–4446
.48.
L.
Zhang
, J.
Han
, H.
Wang
, R.
Car
, and W.
E
, “Deep potential molecular dynamics: A scalable model with the accuracy of quantum mechanics
,” Phys. Rev. Lett.
120
, 143001
(2018
).49.
T.
Bereau
, R. A.
DiStasio
, A.
Tkatchenko
, and O. A.
von Lilienfeld
, “Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
,” J. Chem. Phys.
148
, 241706
(2018
).50.
S.
Chmiela
, A.
Tkatchenko
, H. E.
Sauceda
, I.
Poltavsky
, K. T.
Schütt
, and K.-R.
Müller
, “Machine learning of accurate energy-conserving molecular force fields
,” Sci. Adv.
3
, e1603015
(2017
).51.
S.
Chmiela
, H. E.
Sauceda
, K.-R.
Müller
, and A.
Tkatchenko
, “Towards exact molecular dynamics simulations with machine-learned force fields
,” Nat. Commun.
9
, 3887
(2018
).52.
A.
Mardt
, L.
Pasquali
, H.
Wu
, and F. N.
Vampnets
, “Deep learning of molecular kinetics
,” Nat. Commun.
9
, 5
(2018
).53.
H.
Wu
, A.
Mardt
, L.
Pasquali
, and F.
Noé
, “Deep generative Markov state models
,” in Advances in Neural Information Processing Systems
, edited by S.
Bengio
, H.
Wallach
, H.
Larochelle
, K.
Grauman
, N.
Cesa-Bianchi
, and R.
Garnett
(Curran Associates, Inc.
, 2018
), Vol. 31, pp. 3975
–3984
.54.
C.
Wehmeyer
and F.
Noé
, “Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
,” J. Chem. Phys.
148
, 241703
(2018
).55.
C. X.
Hernández
, H. K.
Wayment-Steele
, M. M.
Sultan
, B. E.
Husic
, and V. S.
Pande
, “Variational encoding of complex dynamics
,” Phys. Rev. E
97
(6
), 062412
(2018
).56.
J. M. L.
Ribeiro
, P.
Bravo
, Y.
Wang
, and P.
Tiwary
, “Reweighted autoencoded variational Bayes for enhanced sampling (RAVE)
,” J. Chem. Phys.
149
, 072301
(2018
).57.
S. T.
John
and G.
Csányi
, “Many-body coarse-grained interactions using Gaussian approximation potentials
,” J. Phys. Chem. B
121
(48
), 10934
–10949
(2017
).58.
L.
Zhang
, J.
Han
, H.
Wang
, R.
Car
, and W.
E
, “DeePCG: Constructing coarse-grained models via deep neural networks
,” J. Chem. Phys.
149
(3
), 034101
(2018
).59.
J.
Wang
, S.
Olsson
, C.
Wehmeyer
, A.
Pérez
, N. E.
Charron
, G.
de Fabritiis
, F.
Noé
, and C.
Clementi
, “Machine learning of coarse-grained molecular dynamics force fields
,” ACS Cent. Sci.
5
, 755
–767
(2019
).60.
W. G.
Noid
, J.-W.
Chu
, G. S.
Ayton
, V.
Krishna
, S.
Izvekov
, G. A.
Voth
, A.
Das
, and H. C.
Andersen
, “The multiscale coarse-graining method. I. A rigorous bridge between atomistic and coarse-grained models
,” J. Chem. Phys.
128
(24
), 244114
(2008
).61.
S.
Chmiela
, H. E.
Sauceda
, I.
Poltavsky
, K.-R.
Müller
, and A.
Tkatchenko
, “Constructing accurate and data efficient molecular force fields using machine learning
,” Comput. Phys. Commun.
240
, 38
–45
(2019
).62.
L.
Boninsegna
, R.
Banisch
, and C.
Clementi
, “A data-driven perspective on the hierarchical assembly of molecular structures
,” J. Chem. Theory Comput.
14
(1
), 453
–460
(2018
).63.
A. V.
Sinitskiy
, M. G.
Saunders
, and G. A.
Voth
, “Optimal number of coarse-grained sites in different components of large biomolecular complexes
,” J. Phys. Chem. B
116
(29
), 8363
–8374
(2012
).64.
W.
Wang
and R.
Gómez-Bombarelli
, “Coarse-graining auto-encoders for molecular dynamics
,” npj Comput. Mater.
5
(1
), 125
(2019
).65.
V. N.
Vapnik
, “An overview of statistical learning theory
,” IEEE Trans. Neural Network
10
, 988
–999
(1999
).66.
C. E.
Rasmussen
, “Gaussian processes in machine learning
,” in Advanced Lectures on Machine Learning
(Springer
, 2004
), pp. 63
–71
.67.
M. L.
Stein
, Interpolation of Spatial Data: Some Theory for Kriging
(Springer-Verlag
, New York
, 1999
).68.
D.
Opitz
and R.
Maclin
, “Popular ensemble methods: An empirical study
,” J. Artif. Intell. Res.
11
, 169
–198
(1999
).69.
R.
Polikar
, “Ensemble based systems in decision making
,” IEEE Circuits Syst. Mag.
6
(3
), 21
–45
(2006
).70.
L.
Rokach
, “Ensemble-based classifiers
,” Artif. Intell. Rev.
33
(1
), 1
–39
(2010
).71.
L.
Breiman
, “Bagging predictors
,” Mach. Learn.
24
(2
), 123
–140
(1996
).72.
S.
Geman
, E.
Bienenstock
, and R.
Doursat
, “Neural networks and the bias/variance dilemma
,” Neural Comput.
4
(1
), 1
–58
(1992
).73.
L. K.
Hansen
and P.
Salamon
, “Neural network ensembles
,” IEEE Trans. Pattern Anal. Mach. Intell.
12
(10
), 993
–1001
(1990
).74.
R. E.
Schapire
, “The strength of weak learnability
,” Mach. Learn.
5
(2
), 197
–227
(1990
).75.
L. I.
Kuncheva
and C. J.
Whitaker
, “Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy
,” Mach. Learn.
51
(2
), 181
–207
(2003
).76.
E.
Bauer
and R.
Kohavi
, “An empirical comparison of voting classification algorithms: Bagging, boosting, and variants
,” Mach. Learn.
36
(1
), 105
–139
(1999
).77.
M. A.
Rohrdanz
, W.
Zheng
, and C.
Clementi
, “Discovering mountain passes via torchlight: Methods for the definition of reaction coordinates and pathways in complex macromolecular reactions
,” Annu. Rev. Phys. Chem.
64
, 295
–316
(2013
).78.
F.
Noé
and C.
Clementi
, “Collective variables for the study of long-time kinetics from molecular trajectories: Theory and methods
,” Curr. Opin. Struct. Biol.
43
, 141
–147
(2017
).79.
G.
Pérez-Hernández
, F.
Paul
, T.
Giorgino
, G.
De Fabritiis
, and F.
Noé
, “Identification of slow molecular order parameters for Markov model construction
,” J. Chem. Phys.
139
(1
), 015102
(2013
).80.
C. R.
Schwantes
and V. S.
Pande
, “Improvements in Markov state model construction reveal many non-native interactions in the folding of NTL9
,” J. Chem. Theory Comput.
9
, 2000
–2009
(2013
).81.
A.
Ziehe
and K.-R.
Müller
, “TDSEP—An efficient algorithm for blind separation using time structure
,” in ICANN 98
(Springer Science and Business Media
, 1998
), pp. 675
–680
.82.
A.
Belouchrani
, K.
Abed-Meraim
, J.-F.
Cardoso
, and E.
Moulines
, “A blind source separation technique using second-order statistics
,” IEEE Trans. Signal Process.
45
(2
), 434
–444
(1997
).83.
L.
Molgedey
and H. G.
Schuster
, “Separation of a mixture of independent signals using time delayed correlations
,” Phys. Rev. Lett.
72
, 3634
–3637
(1994
).84.
B.
Schölkopf
, A.
Smola
, and K.-R.
Müller
, “Kernel principal component analysis
,” in Artificial Neural Networks—ICANN’97
, edited by W.
Gerstner
, A.
Germond
, M.
Hasler
, and J.-D.
Nicoud
(Springer Berlin Heidelberg
, Berlin, Heidelberg
, 1997
), pp. 583
–588
.85.
B.
Schölkopf
, A.
Smola
, and K.-R.
Müller
, “Nonlinear component analysis as a kernel eigenvalue problem
,” Neural Comput.
10
(5
), 1299
–1319
(1998
).86.
K.-R.
Muller
, S.
Mika
, G.
Ratsch
, K.
Tsuda
, and B.
Scholkopf
, “An introduction to kernel-based learning algorithms
,” IEEE Trans. Neural Networks
12
(2
), 181
–201
(2001
).87.
M. A.
Rohrdanz
, W.
Zheng
, M.
Maggioni
, and C.
Clementi
, “Determination of reaction coordinates via locally scaled diffusion map
,” J. Chem. Phys.
134
, 124116
(2011
).88.
F.
Nüske
, L.
Boninsegna
, and C.
Clementi
, “Coarse-graining molecular systems by spectral matching
,” J. Chem. Phys.
151
(4
), 044116
(2019
).© 2020 Author(s).
2020
Author(s)
You do not currently have access to this content.
