The problem of determining the rate of rare events in dynamical systems is quite well-known but still difficult to solve. Recent attempts to overcome this problem exploit the fact that dynamic systems can be represented by a linear operator, such as the Koopman operator. Mathematically, the rare event problem comes down to the difficulty in finding invariant subspaces of these Koopman operators K. In this article, we describe a method to learn basis functions of invariant subspaces using an artificial neural network.

1.
A. K.
Faradjian
and
R.
Elber
, “
Computing time scales from reaction coordinates by
,”
J. Chem. Phys.
120
,
10880
10889
(
2004
).
2.
W.
E
and
E.
Vanden-Eijnden
, “
Towards a theory of transition paths
,”
J. Stat. Phys.
123
,
503
523
(
2006
).
3.
W.
Huisinga
, “
Metastability of Markovian systems
,” Ph.D. thesis,
FU Berlin
,
Germany
,
2001
.
4.
M.
Weber
, “
A subspace approach to molecular Markov state models via a new infinitesimal generator
,” Habilitation thesis,
FU Berlin
,
2011
.
5.
A.
Mardt
,
L.
Pasquali
,
H.
Wu
, and
F.
Noé
, “
VAMPnets for deep learning of molecular kinetics
,”
Nat. Commun.
9
,
4443
(
2018
).
6.
B.
Reuter
,
K.
Fackeldey
, and
M.
Weber
, “
Generalized Markov modeling of nonreversible molecular kinetics
,”
J. Chem. Phys.
150
,
174103
(
2019
).
7.
M.
Weber
and
N.
Ernst
, “
A fuzzy-set theoretical framework for computing exit rates of rare events in potential-driven diffusion processes
,” arXiv:1708.00679v1 (
2017
).
8.
T.
Schlick
,
Molecular Modeling and Simulation: An Interdisciplinary Guide/Tamar Schlick
, Interdisciplinary Applied Mathematics Vol. v. 21. Mathematical biology (
Springer
,
New York; London
,
2002
).
9.
J.
Quer
, “
Importance sampling for metastable dynamical systems in molecular dynamics
,” Ph.D. thesis,
FU Berlin
,
2018
.
10.
H. J. C.
Berendsen
,
D.
van der Spoel
, and
R.
van Drunen
, “
GROMACS: A message-passing parallel molecular dynamics implementation
,”
Comput. Phys. Commun.
91
,
43
56
(
1995
).
11.
K.
Fackeldey
,
A.
Sikorski
, and
M.
Weber
, “
Spectral clustering for non-reversible Markov chains
,”
Comput. Appl. Math.
37
,
6376
6391
(
2018
).
12.
R. V.
Mises
and
H.
Pollaczek-Geiringer
, “
Praktische verfahren der gleichungsauflösung
,”
Z. Angew. Math. Mech.
9
,
152
164
(
1929
).
13.
The SciPy Community
, Scipy v1.4.1 reference guide: scipy.stats.pearsonr, https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.pearsonr.html, 2019; online accessed 10 November 2019.
14.
S.
Park
,
M. K.
Sener
,
D.
Lu
, and
K.
Schulten
, “
Reaction paths based on mean first-passage times
,”
J. Chem. Phys.
119
,
1313
1319
(
2003
).
15.
D. P.
Kingma
and
J.
Ba
, “
Adam: A method for stochastic optimization
,” arXiv:1412.6980v9 (
2014
).
16.
F.
Chollet
 et al, Keras, https://github.com/keras-team/keras,
2019
.
17.
Google Brain Team
, TensorFlow, https://github.com/tensorflow/tensorflow,
2019
.
18.
P.
Deuflhard
and
M.
Weber
, “
Robust Perron cluster analysis in conformation dynamics
,”
Linear Algebra Appl.
398
,
161
184
(
2005
).
19.
G. M.
Rotskoff
and
E.
Vanden-Eijnden
, “
Trainability and accuracy of neural networks: An interacting particle system approach
,” arXiv:1805.00915v3 (
2018
).
20.
A.
Koehl
,
H.
Hu
,
S.
Maeda
,
Y.
Zhang
,
Q.
Qu
,
J. M.
Paggi
,
N. R.
Latorraca
,
D.
Hilger
,
R.
Dawson
,
H.
Matile
,
G. F. X.
Schertler
,
S.
Granier
,
W. I.
Weis
,
R. O.
Dror
,
A.
Manglik
,
G.
Skiniotis
, and
B. K.
Kobilka
, “
Structure of the μ-opioid receptor–Gi protein complex
,”
Nature
558
,
547
552
(
2018
).
21.
V.
Spahn
,
G.
Del Vecchio
,
D.
Labuz
,
A.
Rodriguez-Gaztelumendi
,
N.
Massaly
,
J.
Temp
,
V.
Durmaz
,
P.
Sabri
,
M.
Reidelbach
,
H.
Machelska
,
M.
Weber
, and
C.
Stein
, “
A nontoxic pain killer designed by modeling of pathological receptor conformations
,”
Science
355
,
966
969
(
2017
).

Supplementary Material

You do not currently have access to this content.