Analysis and sampling of molecular simulations with adversarial autoencoders
Open Access
- 24 March 2026
- journal article
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 164 (12)
Abstract
The design of good collective variables for analysis and the enhancement of sampling of molecular simulations is not a trivial task. It often relies on the knowledge of the system and the experience of the scientist. Machine learning and artificial neural networks can be used for this purpose. Here, we demonstrate for the first time the use of an adversarial autoencoder to design collective variables. Similar to other autoencoders, it encodes data into the latent space and decodes them back with minimal loss of information. Furthermore, it uses the “adversarial game” to control the distribution of the latent space. The coordinates of the latent space can be used as efficient collective variables for analysis and sampling enhancement. The method was applied to the alanine dipeptide trajectory and thermal unfolding trajectory of the tryptophan cage miniprotein. We demonstrate efficient visualization of the conformational space of both molecules. The latent space coordinates of the tryptophan cage were very efficient in accelerating its folding by metadynamics.Keywords
Funding Information
- Grantová Agentura České Republiky (22-29667S)
- Ministry of Education, Youth, and Sports of the Czech Republic (90254)
- Ministry of Education, Youth, and Sports of the Czech Republic (LM2023055)
This publication has 34 references indexed in Scilit:
- Enhanced Sampling in the Age of Machine Learning: Algorithms and ApplicationsChemical Reviews, 2025
- Acceleration of Molecular Simulations by Parametric Time-Lagged tSNE MetadynamicsThe Journal of Physical Chemistry B, 2024
- Chasing Collective Variables Using Autoencoders and Biased TrajectoriesJournal of Chemical Theory and Computation, 2021
- Data-Driven Collective Variables for Enhanced SamplingThe Journal of Physical Chemistry Letters, 2020
- Deep Learning of Representations: Looking Forward2013
- Comparison of multiple Amber force fields and development of improved protein backbone parametersProteins: Structure, Function, and Bioinformatics, 2006
- Increasing Temperature Accelerates Protein Unfolding Without Changing the Pathway of UnfoldingJournal of Molecular Biology, 2002
- Algorithms for clustering molecular dynamics configurationsJournal of Computational Chemistry, 1994
- Nonphysical sampling distributions in Monte Carlo free-energy estimation: Umbrella samplingJournal of Computational Physics, 1977
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948