[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
10.1145/3549737.3549793acmotherconferencesArticle/Chapter ViewAbstractPublication PagessetnConference Proceedingsconference-collections
research-article

Developing Machine-Learned Potentials for Coarse-Grained Molecular Simulations: Challenges and Pitfalls

Published: 09 September 2022 Publication History

Abstract

Coarse graining (CG) enables the investigation of molecular properties for larger systems and at longer timescales than the ones attainable at the atomistic resolution. Machine learning techniques have been recently proposed to learn CG particle interactions, i.e. develop CG force fields. Graph representations of molecules and supervised training of a graph convolutional neural network architecture are used to learn the potential of mean force through a force matching scheme. In this work, the force acting on each CG particle is correlated to a learned representation of its local environment that goes under the name of SchNet, constructed via continuous filter convolutions. We explore the application of SchNet models to obtain a CG potential for liquid benzene, investigating the effect of model architecture and hyperparameters on the thermodynamic, dynamical, and structural properties of the simulated CG systems, reporting and discussing challenges encountered and future directions envisioned.

References

[1]
Mojtaba Haghighatlari and Johannes Hachmann. 2019. Advances of machine learning in molecular modeling and simulation. Curr. Opin. Chem. Eng. 23 (March 2019), 51–57. https://doi.org/10.1016/j.coche.2019.02.009%3c/bib>
[2]
Wujie Wang and Rafael Gómez-Bombarelli. 2019. Coarse-graining auto-encoders for molecular dynamics. npj Comput Mater. 5, 1 (December 2019), 125. https://doi.org/10.1038/s41524-019-0261-5%3c/bib>
[3]
Dimitris Nasikas, Eleonora Ricci, George Giannakopoulos, Vangelis Karkaletsis, Doros N. Theodorou and Niki Vergadou. 2022. Investigation of Machine Learning-based Coarse-Grained Mapping Schemes for Organic Molecules. In Proceedings of 12th Conference on Artificial Intelligence (SETN). ACM, New York, NY, USA, 8 pages. https://doi.org/10.1145/3549737.3549792
[4]
Niki Vergadou and Doros N. Theodorou. 2019. Molecular modeling investigations of sorption and diffusion of small molecules in Glassy polymers. Membranes 9, 8 (August 2019), 98. https://
[5]
Jurgis Ruza, Wujie Wang, Daniel Schwalbe-Koda, Simon Axelrod, William H. Harris, and Rafael Gómez-Bombarelli. 2020. Temperature-transferable coarse-graining of ionic liquids with dual graph convolutional neural networks. J. Chem. Phys. 153, 16 (October 2020), 164501. https://doi.org/10.1063/5.0022431
[6]
Kristof T. Schütt, Huziel E. Sauceda, Pieter-Jan Kindermans, Alexandre Tkatchenko, and Klaus-Robert Müller. 2018. SchNet – A deep learning architecture for molecules and materials. J. Chem. Phys. 148, 24 (June 2018), 241722. https://doi.org/10.1063/1.5019779
[7]
William G. Noid, Jhih-Wei Chu, Gary S. Ayton, Vinod Krishna, Sergei Izvekov, Gregory A. Voth, Avisek Das, and Hans C. Andersen. 2008. The multiscale coarse-graining method. I. A rigorous bridge between atomistic and coarse-grained models. J. Chem Phys. 128, 24 (June 2008), 244114. https://doi.org/10.1063/1.2938860
[8]
Furio Ercolessi and James B. Adams. 1994. Interatomic Potentials from First-Principles Calculations: The Force-Matching Method. Europhys. Lett. 26, 8 (June 1994), 583–8. https://doi.org/10.1209/0295-5075/26/8/005
[9]
Kristof T. Schütt, Pan Kessel, Michael Gastegger, Kim Nicoli, Alexandre Tkatchenko, and Klaus-Robert Müller. 2019. SchNetPack: A Deep Learning Toolbox for Atomistic Systems. J. Chem. Theory Comput. 15, 1 (June 2019), 448–55. https://doi.org/10.1209/0295-5075/26/8/005
[10]
Jiang Wang, Simon Olsson, Christoph Wehmeyer, Adrià Pérez, Nicholas E. Charron, Gianni de Fabritiis, Frank Noé, and Cecilia Clementi. 2019. Machine Learning of Coarse-Grained Molecular Dynamics Force Fields. ACS Cent. Sci. 5, 5 (May 2019), 755–67. https://doi.org/10.1021/acscentsci.8b00913
[11]
Ask Hjorth Larsen, Jens Jørgen Mortensen, Jakob Blomqvist, Ivano E. Castelli, Rune Christensen, Marcin Dułak, Jesper Friis, Michael N. Groves, Bjørk Hammer, Cory Hargus, Eric D. Hermes, Paul C. Jennings, Peter Bjerre Jensen, James Kermode, John R. Kitchin, Esben Leonhard Kolsbjerg, Joseph Kubal, Kristen Kaasbjerg, Steen Lysgaard, Jón Bergmann Maronsson, Tristan Maxson, Thomas Olsen, Lars Pastewka, Andrew Peterson, Carsten Rostgaard, Jakob Schiøtz, Ole Schütt, Mikkel Strange, Kristian S. Thygesen, Tejs Vegge, Lasse Vilhelmsen, Michael Walter, Zhenhua Zeng, and Karsten W. Jacobsen. 2017. The atomic simulation environment—a Python library for working with atoms. J. Phys. Condens. Matter. 29, 27 (July 2017), 273002. https://doi.org/10.1088/1361-648X/aa680e
[12]
Brooke E. Husic, Nicholas E. Charron, Dominik Lemm, Jiang Wang, Adrià Pérez, Maciej Majewski, Andreas Krämer, Yaoyi Chen, Simon Olsson, Gianni de Fabritiis, Frank Noé, and Cecilia Clementi. 2020. Coarse graining molecular dynamics with graph neural networks. J. Chem. Phys. 159, 19 (November 2020), 194101. https://doi.org/10.1063/5.0026133
[13]
Nikolas Zacharopoulos, Niki Vergadou, and Doros N. Theodorou. 2005. Coarse graining using pretabulated potentials: Liquid benzene. J. Chem. Phys. 122, (2005), 1–11. https://doi.org/10.1063/1.1948370

Cited By

View all
  • (2024)Self-Adaptive Optimization of Coefficients in Multi-Objective Loss FunctionsProceedings of the 13th Hellenic Conference on Artificial Intelligence10.1145/3688671.3688742(1-9)Online publication date: 11-Sep-2024
  • (2024)Molecular Simulation of Coarse-grained Systems using Machine LearningProceedings of the 13th Hellenic Conference on Artificial Intelligence10.1145/3688671.3688739(1-6)Online publication date: 11-Sep-2024
  • (2023)Transferable Implicit Solvation via Contrastive Learning of Graph Neural NetworksACS Central Science10.1021/acscentsci.3c011609:12(2286-2297)Online publication date: 16-Nov-2023
  • Show More Cited By

Index Terms

  1. Developing Machine-Learned Potentials for Coarse-Grained Molecular Simulations: Challenges and Pitfalls

      Recommendations

      Comments

      Please enable JavaScript to view thecomments powered by Disqus.

      Information & Contributors

      Information

      Published In

      cover image ACM Other conferences
      SETN '22: Proceedings of the 12th Hellenic Conference on Artificial Intelligence
      September 2022
      450 pages
      ISBN:9781450395977
      DOI:10.1145/3549737
      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 09 September 2022

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. Coarse-graining
      2. Hierarchical Modelling
      3. Machine Learning
      4. Molecular Simulations
      5. Neural Network Potential

      Qualifiers

      • Research-article
      • Research
      • Refereed limited

      Funding Sources

      Conference

      SETN 2022

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)65
      • Downloads (Last 6 weeks)4
      Reflects downloads up to 17 Jan 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2024)Self-Adaptive Optimization of Coefficients in Multi-Objective Loss FunctionsProceedings of the 13th Hellenic Conference on Artificial Intelligence10.1145/3688671.3688742(1-9)Online publication date: 11-Sep-2024
      • (2024)Molecular Simulation of Coarse-grained Systems using Machine LearningProceedings of the 13th Hellenic Conference on Artificial Intelligence10.1145/3688671.3688739(1-6)Online publication date: 11-Sep-2024
      • (2023)Transferable Implicit Solvation via Contrastive Learning of Graph Neural NetworksACS Central Science10.1021/acscentsci.3c011609:12(2286-2297)Online publication date: 16-Nov-2023
      • (2023)Statistically Optimal Force Aggregation for Coarse-Graining Molecular DynamicsThe Journal of Physical Chemistry Letters10.1021/acs.jpclett.3c0044414:17(3970-3979)Online publication date: 20-Apr-2023
      • (2023)Perspective: Advances, Challenges, and Insight for Predictive Coarse-Grained ModelsThe Journal of Physical Chemistry B10.1021/acs.jpcb.2c08731127:19(4174-4207)Online publication date: 7-May-2023
      • (2023)Integrating Machine Learning in the Coarse-Grained Molecular Simulation of PolymersThe Journal of Physical Chemistry B10.1021/acs.jpcb.2c06354127:11(2302-2322)Online publication date: 8-Mar-2023

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      HTML Format

      View this article in HTML Format.

      HTML Format

      Media

      Figures

      Other

      Tables

      Share

      Share

      Share this Publication link

      Share on social media