The DOI matches its Crossref record; 45 of the 47 references it cites were found in a registry or an index.
Machine learning approaches for analyzing and enhancing molecular dynamics simulations
Abstract
Molecular dynamics (MD) has become a powerful tool for studying biophysical systems, due to increasing computational power and availability of software. Although MD has made many contributions to better understanding these complex biophysical systems, there remain methodological difficulties to be surmounted. First, how to make the deluge of data generated in running even a microsecond long MD simulation human comprehensible. Second, how to efficiently sample the underlying free energy surface and kinetics. In this short perspective, we summarize machine learning based ideas that are solving both of these limitations, with a focus on their key theoretical underpinnings and remaining challenges.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Second, a number of groups in the molecular dynamics community are applying new machine learning methods to allow exploration of trajectories in less frustrated latent spaces30.”
From Critical assessment of methods of protein structure prediction (CASP)—Round XIV (2021) · cites this paper as [30]
Citations
Cites
Nonphysical sampling distributions in Monte Carlo free-energy estimation: Umbrella sampling
Torrie, G. M., & Valleau, J. P. (1977) · Journal of Computational Physics · doi:10.1016/0021-9991(77)90121-8 · Cited by 6,091
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
Behler, J., & Parrinello, M. (2007) · Physical Review Letters · doi:10.1103/physrevlett.98.146401 · Cited by 5,010
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
Bartók, A. P., Payne, M. C., Kondor, R., & Csányi, G. (2010) · Physical Review Letters · doi:10.1103/physrevlett.104.136403 · Cited by 3,242
Density estimation using Real NVP
Dinh, L., Sohl-Dickstein, J., & Bengio, S. (2016) · arXiv · Cited by 2,067
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost
Smith, J. S., Isayev, O., & Roitberg, A. E. (2017) · Chemical Science · doi:10.1039/c6sc05720a · Cited by 1,921
Coifman, R. R., Lafon, S., Lee, A. B., Maggioni, M., Nadler, B., Warner, F., & Zucker, S. W. (2005) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0500334102 · Cited by 1,675
Promoting transparency and reproducibility in enhanced molecular simulations
Bonomi, M., Bussi, G., Bernetti, M., Cesari, A., Laio, A., Camilloni, C., Paissoni, C., Tribello, G. A., Banáš, P., Barducci, A., et al. (2019) · Nature Methods · doi:10.1038/s41592-019-0506-8 · Cited by 1,193
Self-citationPyEMMA 2: A Software Package for Estimation, Validation, and Analysis of Markov Models
Scherer, M. K., Trendelkamp-Schroer, B., Paul, F., Pérez‐Hernández, G., Hoffmann, M., Plattner, N., Wehmeyer, C., Prinz, J.-H., & Noé, F. (2015) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5b00743 · Cited by 1,160
Identification of slow molecular order parameters for Markov model construction
Pérez-Hernández, G., Paul, F., Giorgino, T., De Fabritiis, G., & Noé, F. (2013) · The Journal of Chemical Physics · doi:10.1063/1.4811489 · Cited by 990 · cited 2×
“Methods such as TICA [9] implement VAC directly by learning slow eigenvectors as linear combinations of pre-selected basis functions, and are at the heart of building MSMs.”
MethodBoltzmann generators: Sampling equilibrium states of many-body systems with deep learning
Noé, F., Olsson, S., Köhler, J., & Wu, H. (2019) · Science · doi:10.1126/science.aaw1147 · Cited by 863
Glow: Generative Flow with Invertible 1x1 Convolutions
Kingma, D. P., & Dhariwal, P. (2018) · arXiv · Cited by 825
VAMPnets for deep learning of molecular kinetics
Mardt, A., Pasquali, L., Wu, H., & Noé, F. (2017) · Nature Communications · doi:10.1038/s41467-017-02388-1 · Cited by 691
Identification of slow molecular order parameters for Markov model constructionPreprint
Perez-hern, G., Paul, F., Toni Giorgino, A., Fabritiis, G. D., Noé, F., & Contribution, E. (2013) · Cited by 657
Enhancing Important Fluctuations: Rare Events and Metadynamics from a Conceptual Viewpoint
Valsson, Ó., Tiwary, P., & Parrinello, M. (2016) · Annual Review of Physical Chemistry · doi:10.1146/annurev-physchem-040215-112229 · Cited by 646
Self-citationWetzel, S. J. (2017) · Physical review. E · doi:10.1103/physreve.96.022140 · Cited by 516
A Time-Independent Free Energy Estimator for Metadynamics
Tiwary, P., & Parrinello, M. (2014) · The Journal of Physical Chemistry B · doi:10.1021/jp504920s · Cited by 502
Self-citationVAMPnets for deep learning of molecular kinetics
Mardt, A., Pasquali, L., Wu, H., & Noé, F. (2018) · RePEc: Research Papers in Economics · doi:10.17169/refubium-964 · Cited by 464
Automatic Method for Identifying Reaction Coordinates in Complex Systems
Ma, A., & Dinner, A. R. (2005) · The Journal of Physical Chemistry B · doi:10.1021/jp045546c · Cited by 400
Simplifying the representation of complex free-energy landscapes using sketch-map
Ceriotti, M., Tribello, G. A., & Parrinello, M. (2011) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1108486108 · Cited by 340
Variational Approach to Enhanced Sampling and Free Energy Calculations
Valsson, O., & Parrinello, M. (2014) · Physical Review Letters · doi:10.1103/physrevlett.113.090601 · Cited by 336
Reweighted autoencoded variational Bayes for enhanced sampling (RAVE)
Ribeiro, J. M. L., Collado, P. B., Wang, Y., & Tiwary, P. (2018) · The Journal of Chemical Physics · doi:10.1063/1.5025487 · Cited by 332
Self-citationA Variational Approach to Modeling Slow Processes in Stochastic Dynamical Systems
Noé, F., & Nüske, F. (2013) · Multiscale Modeling & Simulation · doi:10.1137/110858616 · Cited by 327 · cited 1×
“[7, 8] show how to calculate such matrix elements given unbiased MD data.”
BackgroundData-Driven Model Reduction and Transfer Operator Approximation
Klus, S., Nüske, F., Koltai, P., Wu, H., Kevrekidis, I., Schütte, C., & Noé, F. (2018) · Journal of Nonlinear Science · doi:10.1007/s00332-017-9437-7 · Cited by 317
Variational approach to molecular kinetics
Nüske, F., Keller, B. G., Pérez-Hernández, G., Mey, A. S. J. S., & Noé, F. (2014) · Journal of Chemical Theory and Computation · doi:10.1021/ct4009156 · Cited by 308
Adaptive umbrella sampling: Self-consistent determination of the non-Boltzmann bias
Mezei, M. (1987) · Journal of Computational Physics · doi:10.1016/0021-9991(87)90054-4 · Cited by 280
Spectral gap optimization of order parameters for sampling complex molecular systems
Tiwary, P., & Berne, B. J. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1600917113 · Cited by 259
Self-citationChen, W., & Ferguson, A. L. (2018) · Journal of Computational Chemistry · doi:10.1002/jcc.25520 · Cited by 244
Variational encoding of complex dynamics
Hernández, C. X., Wayment-Steele, H. K., Sultan, M. M., Husic, B. E., & Pande, V. S. (2018) · Physical review. E · doi:10.1103/physreve.97.062412 · Cited by 184
Wang, Y., Ribeiro, J. M. L., & Tiwary, P. (2019) · Nature Communications · doi:10.1038/s41467-019-11405-4 · Cited by 180
Self-citationNeural networks-based variationally enhanced sampling
Bonati, L., Zhang, Y., & Parrinello, M. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1907975116 · Cited by 137
Fast recovery of free energy landscapes via diffusion-map-directed molecular dynamics
Preto, J., & Clementi, C. (2014) · Physical Chemistry Chemical Physics · doi:10.1039/c3cp54520b · Cited by 129
Intrinsic map dynamics exploration for uncharted effective free-energy landscapes
Chiavazzo, E., Covino, R., Coifman, R. R., Gear, C. W., Georgiou, A. S., Hummer, G., & Kevrekidis, I. G. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1621481114 · Cited by 125 · cited 1×
“In the more recent iMapD approach[33], the boundary in a low-dimensional manifold comprising the top few eigenvectors of the diffusion map is constructed, and independent simulations are launched from points sampled from this boundary.”
BackgroundShamsi, Z., Cheng, K. J., & Shukla, D. (2018) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.8b06521 · Cited by 125
EncoderMap: Dimensionality Reduction and Generation of Molecule Conformations.
Lemke, T., & Peter, C. (2019) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.8b00975 · Cited by 102
Machine Learning of Biomolecular Reaction Coordinates
Brandt, S., Sittel, F., Ernst, M., & Stock, G. (2018) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.8b00759 · Cited by 74
Ravindra, P., Smith, Z., & Tiwary, P. (2019) · Molecular Systems Design & Engineering · doi:10.1039/c9me00115h · Cited by 67
Self-citationInferring Transition Rates of Networks from Populations in Continuous-Time Markov Processes
Dixit, P. D., Jain, A., Stock, G., & Dill, K. A. (2015) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5b00537 · Cited by 66
Deep Generative Markov State ModelsPreprint
Wu, H., Mardt, A., Pasquali, L., & Noé, F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07601 · Cited by 55
Dynamic graphical models of molecular kinetics
Olsson, S., & Noé, F. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1901692116 · Cited by 44
Chen, W., Sidky, H., & Ferguson, A. L. (2019) · The Journal of Chemical Physics · doi:10.1063/1.5112048 · Cited by 42
Unfolding Hidden Barriers by Active Enhanced Sampling
Zhang, J., & Chen, M. (2017) · Physical Review Letters · doi:10.1103/physrevlett.121.010601 · Cited by 41
Smith, Z., Pramanik, D., Tsai, S.-T., & Tiwary, P. (2018) · The Journal of Chemical Physics · doi:10.1063/1.5064856 · Cited by 39
Self-citationPredictive collective variable discovery with deep Bayesian models
Schöberl, M., Zabaras, N. J., & Koutsourelakis, P. (2019) · The Journal of Chemical Physics · doi:10.1063/1.5058063 · Cited by 37
Jung, H., Covino, R., & Hummer, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.04595 · Cited by 36
Trapl, D., Horvacanin, I., Mareška, V., Özçelik, F., Ünal, G., & Spiwok, V. (2019) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2019.00025 · Cited by 31
Flagged first, then by citations
2 of the 47 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Critical assessment of methods of protein structure prediction (CASP)—Round XIV
Kryshtafovych, A., Schwede, T., Topf, M., Fidelis, K., & Moult, J. (2021) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26237 · Cited by 503
Recent Progress of Amorphous Nanomaterials
Kang, J., Yang, X., Hu, Q. L., Cai, Z. D., Liu, L., & Guo, L. (2023) · Chemical Reviews · doi:10.1021/acs.chemrev.3c00229 · Cited by 411
Enhanced Sampling Methods for Molecular Dynamics Simulations [Article v1.0]
Hénin, J., Tony Lelièvre, A., Shirts, M. R., Valsson, Ó., & Delemotte, L. (2022) · Living Journal of Computational Molecular Science · doi:10.33011/livecoms.4.1.1583 · Cited by 460
AI in drug discovery and its clinical relevance
Qureshi, R., Irfan, M., Gondal, T. M., Khan, S., Wu, J., Hadi, M. U., Heymach, J., Le, X., Yan, H., & Alam, T. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e17575 · Cited by 319
Bottom-up Coarse-Graining: Principles and Perspectives
Jin, J., Pak, A. J., Durumeric, A. E. P., Loose, T. D., & Voth, G. A. (2022) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.2c00643 · Cited by 321
Metadata
- Authors
- Wang, Y., Lamim Ribeiro, J. M., & Tiwary, P.
- Affiliations
- University of Maryland, College Park (US)
- Corresponding author
- Tiwary, Pratyush
- Venue
- Current Opinion in Structural Biology
- Publisher
- Elsevier BV
- Published
- 2020-04
- Volume
- 61
- Pages
- 139-145
- ISSN
- 0959-440X (ISSN-L)
- OpenAlex
- W3000999892
- Cited by
- 303
- References
- 47
- Citations by year
- 2026: 36 · 2025: 53 · 2024: 49 · 2023: 61 · 2022: 49 · 2021: 35 · 2020: 20
- FWCI
- 3.95
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Current Opinion in Structural Biology (publishedVersion)
- PubMed (publishedVersion)
- Funders
- NCI-UMD Partnership for Integrative Cancer Research
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Keywords
- machine learning, molecular dynamics simulation, free energy landscape, reaction kinetics, sampling efficiency, biophysical systems
- MeSH terms
- Machine Learning, Algorithms, Models, Theoretical, Software, Neural Networks, Computer, Molecular Dynamics Simulation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
