An extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets
The reaction coordinate (RC) is the principal collective variable or feature that determines the progress along an activated or reactive process. In a molecular simulation using enhanced sampling, a good description of the RC is crucial for generating sufficient statistics. Moreover, the RC provides...
Published in: | The Journal of Chemical Physics |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://dare.uva.nl/personal/pure/en/publications/an-extended-autoencoder-model-for-reaction-coordinate-discovery-in-rare-event-molecular-dynamics-datasets(b400073a-a8d2-478c-9791-31ada61ae105).html https://doi.org/10.1063/5.0058639 https://hdl.handle.net/11245.1/b400073a-a8d2-478c-9791-31ada61ae105 https://pure.uva.nl/ws/files/68430291/5.0058639.pdf https://www.scopus.com/inward/record.uri?eid=2-s2.0-85112781689&doi=10.1063%2f5.0058639&partnerID=40&md5=8ef88e09f813c8895d442024cbb2f565 |
id |
ftunivamstpubl:oai:dare.uva.nl:openaire_cris_publications/b400073a-a8d2-478c-9791-31ada61ae105 |
---|---|
record_format |
openpolar |
spelling |
ftunivamstpubl:oai:dare.uva.nl:openaire_cris_publications/b400073a-a8d2-478c-9791-31ada61ae105 2024-09-30T14:38:31+00:00 An extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets Frassek, M. Arjun, A. Bolhuis, P.G. 2021-08-14 application/pdf https://dare.uva.nl/personal/pure/en/publications/an-extended-autoencoder-model-for-reaction-coordinate-discovery-in-rare-event-molecular-dynamics-datasets(b400073a-a8d2-478c-9791-31ada61ae105).html https://doi.org/10.1063/5.0058639 https://hdl.handle.net/11245.1/b400073a-a8d2-478c-9791-31ada61ae105 https://pure.uva.nl/ws/files/68430291/5.0058639.pdf https://www.scopus.com/inward/record.uri?eid=2-s2.0-85112781689&doi=10.1063%2f5.0058639&partnerID=40&md5=8ef88e09f813c8895d442024cbb2f565 eng eng https://dare.uva.nl/personal/pure/en/publications/an-extended-autoencoder-model-for-reaction-coordinate-discovery-in-rare-event-molecular-dynamics-datasets(b400073a-a8d2-478c-9791-31ada61ae105).html info:eu-repo/semantics/openAccess Frassek , M , Arjun , A & Bolhuis , P G 2021 , ' An extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets ' , Journal of Chemical Physics , vol. 155 , no. 6 , 064103 . https://doi.org/10.1063/5.0058639 article 2021 ftunivamstpubl https://doi.org/10.1063/5.0058639 2024-09-12T16:38:40Z The reaction coordinate (RC) is the principal collective variable or feature that determines the progress along an activated or reactive process. In a molecular simulation using enhanced sampling, a good description of the RC is crucial for generating sufficient statistics. Moreover, the RC provides invaluable atomistic insight into the process under study. The optimal RC is the committor, which represents the likelihood of a system to evolve toward a given state based on the coordinates of all its particles. As the interpretability of such a high dimensional function is low, a more practical approach is to describe the RC by some low-dimensional molecular collective variables or order parameters. While several methods can perform this dimensionality reduction, they usually require a preselection of these low-dimension collective variables (CVs). Here, we propose to automate this dimensionality reduction using an extended autoencoder, which maps the input (many CVs) onto a lower-dimensional latent space, which is subsequently used for the reconstruction of the input as well as the prediction of the committor function. As a consequence, the latent space is optimized for both reconstruction and committor prediction and is likely to yield the best non-linear low-dimensional representation of the committor. We test our extended autoencoder model on simple but nontrivial toy systems, as well as extensive molecular simulation data of methane hydrate nucleation. The extended autoencoder model can effectively extract the underlying mechanism of a reaction, make reliable predictions about the committor of a given configuration, and potentially even generate new paths representative for a reaction. Article in Journal/Newspaper Methane hydrate Universiteit van Amsterdam: Digital Academic Repository (UvA DARE) The Journal of Chemical Physics 155 6 |
institution |
Open Polar |
collection |
Universiteit van Amsterdam: Digital Academic Repository (UvA DARE) |
op_collection_id |
ftunivamstpubl |
language |
English |
description |
The reaction coordinate (RC) is the principal collective variable or feature that determines the progress along an activated or reactive process. In a molecular simulation using enhanced sampling, a good description of the RC is crucial for generating sufficient statistics. Moreover, the RC provides invaluable atomistic insight into the process under study. The optimal RC is the committor, which represents the likelihood of a system to evolve toward a given state based on the coordinates of all its particles. As the interpretability of such a high dimensional function is low, a more practical approach is to describe the RC by some low-dimensional molecular collective variables or order parameters. While several methods can perform this dimensionality reduction, they usually require a preselection of these low-dimension collective variables (CVs). Here, we propose to automate this dimensionality reduction using an extended autoencoder, which maps the input (many CVs) onto a lower-dimensional latent space, which is subsequently used for the reconstruction of the input as well as the prediction of the committor function. As a consequence, the latent space is optimized for both reconstruction and committor prediction and is likely to yield the best non-linear low-dimensional representation of the committor. We test our extended autoencoder model on simple but nontrivial toy systems, as well as extensive molecular simulation data of methane hydrate nucleation. The extended autoencoder model can effectively extract the underlying mechanism of a reaction, make reliable predictions about the committor of a given configuration, and potentially even generate new paths representative for a reaction. |
format |
Article in Journal/Newspaper |
author |
Frassek, M. Arjun, A. Bolhuis, P.G. |
spellingShingle |
Frassek, M. Arjun, A. Bolhuis, P.G. An extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets |
author_facet |
Frassek, M. Arjun, A. Bolhuis, P.G. |
author_sort |
Frassek, M. |
title |
An extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets |
title_short |
An extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets |
title_full |
An extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets |
title_fullStr |
An extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets |
title_full_unstemmed |
An extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets |
title_sort |
extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets |
publishDate |
2021 |
url |
https://dare.uva.nl/personal/pure/en/publications/an-extended-autoencoder-model-for-reaction-coordinate-discovery-in-rare-event-molecular-dynamics-datasets(b400073a-a8d2-478c-9791-31ada61ae105).html https://doi.org/10.1063/5.0058639 https://hdl.handle.net/11245.1/b400073a-a8d2-478c-9791-31ada61ae105 https://pure.uva.nl/ws/files/68430291/5.0058639.pdf https://www.scopus.com/inward/record.uri?eid=2-s2.0-85112781689&doi=10.1063%2f5.0058639&partnerID=40&md5=8ef88e09f813c8895d442024cbb2f565 |
genre |
Methane hydrate |
genre_facet |
Methane hydrate |
op_source |
Frassek , M , Arjun , A & Bolhuis , P G 2021 , ' An extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets ' , Journal of Chemical Physics , vol. 155 , no. 6 , 064103 . https://doi.org/10.1063/5.0058639 |
op_relation |
https://dare.uva.nl/personal/pure/en/publications/an-extended-autoencoder-model-for-reaction-coordinate-discovery-in-rare-event-molecular-dynamics-datasets(b400073a-a8d2-478c-9791-31ada61ae105).html |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.1063/5.0058639 |
container_title |
The Journal of Chemical Physics |
container_volume |
155 |
container_issue |
6 |
_version_ |
1811641138480676864 |