Explaining reaction coordinates of alanine dipeptide isomerization obtained from deep neural networks using Explainable Artificial Intelligence (XAI)

B. Peters, Reaction Rate Theory and Rare Events (Elsevier, Amsterdam, 2017).

S. V. Krivov, “On reaction coordinate optimality,” J. Chem. Theory Comput. 9,

135–146 (2013).

W. Li and A. Ma, “Recent developments in methods for identifying reaction

coordinates,” Mol. Simul. 40, 784–793 (2014).

B. Peters, P. G. Bolhuis, R. G. Mullen, and J.-E. Shea, “Reaction coordinates, onedimensional Smoluchowski equations, and a test for dynamical self-consistency,”

J. Chem. Phys. 138, 054106 (2013).

D. J. Wales, “Perspective: Insight into reaction coordinates and dynamics from

the potential energy landscape,” J. Chem. Phys. 142, 130901 (2015).

B. Peters, “Reaction coordinates and mechanistic hypothesis tests,” Annu. Rev.

Phys. Chem. 67, 669–690 (2016).

P. V. Banushkina and S. V. Krivov, “Optimal reaction coordinates,” Wiley

Interdiscip. Rev.: Comput. Mol. Sci. 6, 748–763 (2016).

F. Pietrucci, “Strategies for the exploration of free energy landscapes: Unity in

diversity and challenges ahead,” Rev. Phys. 2, 32–45 (2017).

P. G. Bolhuis and D. W. H. Swenson, “Transition path sampling as Markov chain

Monte Carlo of trajectories: Recent algorithms, software, applications, and future

outlook,” Adv. Theory Simul. 4, 2000237 (2021).

10

P. G. Bolhuis, D. Chandler, C. Dellago, and P. L. Geissler, “Transition path sampling: Throwing ropes over rough mountain passes, in the dark,” Annu. Rev. Phys.

Chem. 53, 291–318 (2002).

11

J. Rogal, “Reaction coordinates in complex systems-a perspective,” Eur. Phys. J.

B 94, 223 (2021).

12

R. Du, V. S. Pande, A. Y. Grosberg, T. Tanaka, and E. S. Shakhnovich, “On the

transition coordinate for protein folding,” J. Chem. Phys. 108, 334–350 (1998).

13

P. L. Geissler, C. Dellago, and D. Chandler, “Kinetic pathways of ion pair

dissociation in water,” J. Phys. Chem. B 103, 3706–3710 (1999).

14

P. G. Bolhuis, C. Dellago, and D. Chandler, “Reaction coordinates of biomolecular isomerization,” Proc. Natl. Acad. Sci. U. S. A. 97, 5877–5882 (2000).

15

M. F. Hagan, A. R. Dinner, D. Chandler, and A. K. Chakraborty, “Atomistic

understanding of kinetic pathways for single base-pair binding and unbinding in

DNA,” Proc. Natl. Acad. Sci. U. S. A. 100, 13922–13927 (2003).

16

G. Hummer, “From transition paths to transition states and rate coefficients,”

J. Chem. Phys. 120, 516–523 (2004).

J. Chem. Phys. 156, 154108 (2022); doi: 10.1063/5.0087310

© Author(s) 2022

ARTICLE

scitation.org/journal/jcp

17

A. C. Pan and D. Chandler, “Dynamics of nucleation in the Ising model,”

J. Phys. Chem. B 108, 19681–19686 (2004).

18

Y. M. Rhee and V. S. Pande, “One-dimensional reaction coordinate and the corresponding potential of mean force from commitment probability distribution,”

J. Phys. Chem. B 109, 6780–6786 (2005).

19

A. Berezhkovskii and A. Szabo, “One-dimensional reaction coordinates for diffusive activated rate processes in many dimensions,” J. Chem. Phys. 122, 014503

(2005).

20

R. B. Best and G. Hummer, “Reaction coordinates and rates from transition

paths,” Proc. Natl. Acad. Sci. U. S. A. 102, 6732–6737 (2005).

21

D. Moroni, P. R. ten Wolde, and P. G. Bolhuis, “Interplay between structure and

size in a critical crystal nucleus,” Phys. Rev. Lett. 94, 235703 (2005).

22

B. Peters, “Using the histogram test to quantify reaction coordinate error,”

J. Chem. Phys. 125, 241101 (2006).

23

D. Branduardi, F. L. Gervasio, and M. Parrinello, “From A to B in free energy

space,” J. Chem. Phys. 126, 054103 (2007).

24

S. L. Quaytman and S. D. Schwartz, “Reaction coordinate of an enzymatic reaction revealed by transition path sampling,” Proc. Natl. Acad. Sci. U. S. A. 104,

12253–12258 (2007).

25

D. Antoniou and S. D. Schwartz, “The stochastic separatrix and the reaction

coordinate for complex systems,” J. Chem. Phys. 130, 151103 (2009).

26

B. Peters, “p(TP∣q) peak maximization: Necessary but not sufficient for reaction

coordinate accuracy,” Chem. Phys. Lett. 494, 100–103 (2010).

27

M. Ernst, S. Wolf, and G. Stock, “Identification and validation of reaction

coordinates describing protein functional motion: Hierarchical dynamics of T4

lysozyme,” J. Chem. Theory Comput. 13, 5076–5088 (2017).

28

B. Peters and B. L. Trout, “Obtaining reaction coordinates by likelihood

maximization,” J. Chem. Phys. 125, 054108 (2006).

29

B. Peters, G. T. Beckham, and B. L. Trout, “Extensions to the likelihood maximization approach for finding reaction coordinates,” J. Chem. Phys. 127, 034109

(2007).

30

B. Peters, “Recent advances in transition path sampling: Accurate reaction

coordinates, likelihood maximisation and diffusive barrier-crossing dynamics,”

Mol. Simul. 36, 1265–1281 (2010).

31

G. T. Beckham, B. Peters, C. Starbuck, N. Variankaval, and B. L. Trout, “Surfacemediated nucleation in the solid-state polymorph transformation of terephthalic

acid,” J. Am. Chem. Soc. 129, 4714–4723 (2007).

32

G. T. Beckham, B. Peters, and B. L. Trout, “Evidence for a size dependent nucleation mechanism in solid state polymorph transformations,” J. Phys. Chem. B 112,

7460–7466 (2008).

33

B. Peters, “Transition-state theory, dynamics, and narrow time scale separation

in the rate-promoting vibrations model of enzyme catalysis,” J. Chem. Theory

Comput. 6, 1447–1454 (2010).

34

J. Vreede, J. Juraszek, and P. G. Bolhuis, “Predicting the reaction coordinates of

millisecond light-induced conformational changes in photoactive yellow protein,”

Proc. Natl. Acad. Sci. U. S. A. 107, 2397–2402 (2010).

35

W. Lechner, J. Rogal, J. Juraszek, B. Ensing, and P. G. Bolhuis, “Nonlinear reaction coordinate analysis in the reweighted path ensemble,” J. Chem. Phys. 133,

174110 (2010).

36

B. Pan and M. S. Ricci, “Molecular mechanism of acid-catalyzed hydrolysis

of peptide bonds using a model compound,” J. Phys. Chem. B 114, 4389–4399

(2010).

37

G. T. Beckham and B. Peters, “Optimizing nucleus size metrics for liquid–solid

nucleation from transition paths of near-nanosecond duration,” J. Phys. Chem.

Lett. 2, 1133–1138 (2011).

38

B. Peters, “Inertial likelihood maximization for reaction coordinates with high

transmission coefficients,” Chem. Phys. Lett. 554, 248–253 (2012).

39

L. Xi, M. Shah, and B. L. Trout, “Hopping of water in a glassy polymer studied

via transition path sampling and likelihood maximization,” J. Phys. Chem. B 117,

3634–3647 (2013).

40

S. Jungblut, A. Singraber, and C. Dellago, “Optimising reaction coordinates for

crystallisation by tuning the crystallinity definition,” Mol. Phys. 111, 3527–3533

(2013).

41

R. G. Mullen, J.-E. Shea, and B. Peters, “Transmission coefficients, committors,

and solvent coordinates in ion-pair dissociation,” J. Chem. Theory Comput. 10,

659–667 (2014).

156, 154108-7

The Journal

of Chemical Physics

42

R. G. Mullen, J.-E. Shea, and B. Peters, “Easy transition path sampling methods: Flexible-length aimless shooting and permutation shooting,” J. Chem. Theory

Comput. 11, 2421–2428 (2015).

43

L. Lupi, B. Peters, and V. Molinero, “Pre-ordering of interfacial water in the

pathway of heterogeneous ice nucleation does not lead to a two-step crystallization

mechanism,” J. Chem. Phys. 145, 211910 (2016).

44

H. Jung, K.-i. Okazaki, and G. Hummer, “Transition path sampling of rare

events by shooting from the top,” J. Chem. Phys. 147, 152716 (2017).

45

M. N. Joswiak, M. F. Doherty, and B. Peters, “Ion dissolution mechanism and

kinetics at kink sites on NaCl surfaces,” Proc. Natl. Acad. Sci. U. S. A. 115, 656–661

(2018).

46

G. Díaz Leines and J. Rogal, “Maximum likelihood analysis of reaction

coordinates during solidification in Ni,” J. Phys. Chem. B 122, 10934–10942

(2018).

47

K.-i. Okazaki, D. Wöhlert, J. Warnau, H. Jung, Ö. Yildiz, W. Kühlbrandt, and

G. Hummer, “Mechanism of the electroneutral sodium/proton antiporter PaNhaP

from transition-path shooting,” Nat. Commun. 10, 1742 (2019).

48

T. A. B. Arjun and P. G. Bolhuis, “Unbiased atomistic insight in the competing

nucleation mechanisms of methane hydrates,” Proc. Natl. Acad. Sci. U. S. A. 116,

19305–19310 (2019).

49

Y. Liang, G. Díaz Leines, R. Drautz, and J. Rogal, “Identification of a multidimensional reaction coordinate for crystal nucleation in Ni3 Al,” J. Chem. Phys.

152, 224504 (2020).

50

J. R. Rogers and P. L. Geissler, “Breakage of hydrophobic contacts limits the rate

of passive lipid exchange between membranes,” J. Phys. Chem. B 124, 5884–5898

(2020).

51

N. Schwierz, “Kinetic pathways of water exchange in the first hydration shell of

magnesium,” J. Chem. Phys. 152, 224106 (2020).

52

L. Levintov, S. Paul, and H. Vashisth, “Reaction coordinate and thermodynamics of base flipping in RNA,” J. Chem. Theory Comput. 17, 1914–1921

(2021).

53

R. L. Silveira, B. C. Knott, C. S. Pereira, M. F. Crowley, M. S. Skaf, and G. T.

Beckham, “Transition path sampling study of the feruloyl esterase mechanism,”

J. Phys. Chem. B 125, 2018–2030 (2021).

54

T. Mori and S. Saito, “Dissecting the dynamics during enzyme catalysis: A case

study of Pin1 peptidyl-prolyl isomerase,” J. Chem. Theory Comput. 16, 3396–3407

(2020).

55

Y. Mori, K.-i. Okazaki, T. Mori, K. Kim, and N. Matubayasi, “Learning reaction

coordinates via cross-entropy minimization: Application to alanine dipeptide,”

J. Chem. Phys. 153, 054115 (2020).

56

A. Ma and A. R. Dinner, “Automatic method for identifying reaction

coordinates in complex systems,” J. Phys. Chem. B 109, 6769–6779 (2005).

57

M. M. Sultan and V. S. Pande, “Automated design of collective variables using

supervised machine learning,” J. Chem. Phys. 149, 094106 (2018).

58

C. Wehmeyer and F. Noé, “Time-lagged autoencoders: Deep learning of slow

collective variables for molecular kinetics,” J. Chem. Phys. 148, 241703 (2018).

59

A. Mardt, L. Pasquali, H. Wu, and F. Noé, “VAMPnets for deep learning of

molecular kinetics,” Nat. Commun. 9, 5 (2018).

60

A. Bittracher, R. Banisch, and C. Schütte, “Data-driven computation of

molecular reaction coordinates,” J. Chem. Phys. 149, 154103 (2018).

61

W. Chen and A. L. Ferguson, “Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy

landscape exploration,” J. Comput. Chem. 39, 2079–2102 (2018).

62

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).

63

J. Rogal, E. Schneider, and M. E. Tuckerman, “Neural-network-based path collective variables for enhanced sampling of phase transformations,” Phys. Rev. Lett.

123, 245701 (2019).

64

L. Bonati, V. Rizzi, and M. Parrinello, “Data-driven collective variables for

enhanced sampling,” J. Phys. Chem. Lett. 11, 2998–3004 (2020).

65

Y. Wang, J. M. Lamim Ribeiro, and P. Tiwary, “Machine learning approaches

for analyzing and enhancing molecular dynamics simulations,” Curr. Opin. Struct.

Biol. 61, 139–145 (2020).

J. Chem. Phys. 156, 154108 (2022); doi: 10.1063/5.0087310

© Author(s) 2022

ARTICLE

scitation.org/journal/jcp

66

D. Wang and P. Tiwary, “State predictive information bottleneck,” J. Chem.

Phys. 154, 134111 (2021).

67

H. Sidky, W. Chen, and A. L. Ferguson, “Machine learning for collective variable

discovery and enhanced sampling in biomolecular simulation,” Mol. Phys. 118,

e1737742 (2020).

68

J. Zhang, Y.-K. Lei, Z. Zhang, X. Han, M. Li, L. Yang, Y. I. Yang, and Y. Q. Gao,

“Deep reinforcement learning of transition states,” Phys. Chem. Chem. Phys. 23,

6888–6895 (2021).

69

M. Frassek, A. Arjun, and P. G. Bolhuis, “An extended autoencoder model

for reaction coordinate discovery in rare event molecular dynamics datasets,” J.

Chem. Phys. 155, 064103 (2021).

70

F. Hooft, A. Pérez de Alba Ortíz, and B. Ensing, “Discovering collective variables

of molecular transitions via genetic algorithms and neural networks,” J. Chem.

Theory Comput. 17, 2294–2306 (2021).

71

L. Bonati, G. Piccini, and M. Parrinello, “Deep learning the slow modes for rare

events sampling,” Proc. Natl. Acad. Sci. U. S. A. 118, e2113533118 (2021).

72

M. Chen, “Collective variable-based enhanced sampling and machine learning,”

Eur. Phys. J. B 94, 211 (2021).

73

Z. Belkacemi, P. Gkeka, T. Lelièvre, and G. Stoltz, “Chasing collective variables

using autoencoders and biased trajectories,” J. Chem. Theory Comput. 18, 59–78

(2022).

74

H. Jung, R. Covino, and G. Hummer, “Artificial intelligence assists discovery

of reaction coordinates and mechanisms from molecular dynamics simulations,”

arXiv:1901.04595 (2019).

75

H. Jung, R. Covino, A. Arjun, P. G. Bolhuis, and G. Hummer, “Autonomous

artificial intelligence discovers mechanisms of molecular self-organization in

virtual experiments,” arXiv:2105.06673 (2021).

76

J. Neumann and N. Schwierz, “Artificial intelligence resolves kinetic pathways

of magnesium binding to RNA,” J. Chem. Theory Comput. 18, 1202–1212 (2022).

77

W. Ren, E. Vanden-Eijnden, P. Maragakis, and W. E, “Transition pathways

in complex systems: Application of the finite-temperature string method to the

alanine dipeptide,” J. Chem. Phys. 123, 134109 (2005).

78

F. Manuchehrfar, H. Li, W. Tian, A. Ma, and J. Liang, “Exact topology of

the dynamic probability surface of an activated process by persistent homology,”

J. Phys. Chem. B 125, 4667–4680 (2021).

79

D. Antoniou, M. R. Abolfath, and S. D. Schwartz, “Transition path sampling

study of classical rate-promoting vibrations,” J. Chem. Phys. 121, 6442–6447

(2004).

80

A. Adadi and M. Berrada, “Peeking inside the black-box: A survey on

explainable artificial intelligence (XAI),” IEEE Access 6, 52138–52160 (2018).

81

C. Molnar, Interpretable Machine Learning (Lulu Press, Morisville, NC, 2020).

82

M. T. Ribeiro, S. Singh, and C. Guestrin, “‘Why should I trust you?’: Explaining

the predictions of any classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Association for

Computational Linguistics, San Diego, CA, 2016), pp. 97–101.

83

S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model

predictions,” in Proceedings of the 31st International Conference on Neural

Information Processing Systems (Curran Associates, Red Hook, NY, 2017),

pp. 4768–4777.

84

A. L. Maas, A. Y. Hannun, and A. Y. Ng, “Rectifier nonlinearities improve neural network acoustic models,” in ICML Workshop on Deep Learning for Audio,

Speech and Language Processing (2013).

85

D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,”

arXiv:1412.6980 (2014).

86

M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado,

A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M.

Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mane, R. Monga,

S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever,

K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Viegas, O. Vinyals, P.

Warden, M. Wattenberg, M. Wicke, Y. Yu, and X. Zheng, “TensorFlow: Largescale machine learning on heterogeneous distributed systems,” arXiv:1603.04467

(2016).

87

L. S. Shapley, “17. A value for n-person games,” in Contributions to the Theory of

Games (AM-28), Volume II, edited by H. W. Kuhn and A. W. Tucker (Princeton

University Press, 1953), pp. 307–318.

156, 154108-8

...