A graph neural network-state predictive information bottleneck (GNN-SPIB) approach for learning molecular thermodynamics and kinetics

Zou, Ziyue; Wang, Dedi; Tiwary, Pratyush

doi:10.1039/D4DD00315B

A graph neural network-state predictive information bottleneck (GNN-SPIB) approach for learning molecular thermodynamics and kinetics

Journal Article · Thu Nov 28 00:00:00 EST 2024 · Digital Discovery

DOI:https://doi.org/10.1039/D4DD00315B· OSTI ID:2500908

Zou, Ziyue ^[1]; Wang, Dedi ^[1]; ^[1]

Univ. of Maryland, College Park, MD (United States)

Molecular dynamics simulations offer detailed insights into atomic motions but face timescale limitations. Enhanced sampling methods have addressed these challenges but even with machine learning, they often rely on pre-selected expert-based features. Here, in this work, we present a Graph Neural Network-State Predictive Information Bottleneck (GNN-SPIB) framework, which combines graph neural networks and the state predictive information bottleneck to automatically learn low-dimensional representations directly from atomic coordinates. Tested on three benchmark systems, our approach predicts essential structural, thermodynamic and kinetic information for slow processes, demonstrating robustness across diverse systems. The method shows promise for complex systems, enabling effective enhanced sampling without requiring pre-defined reaction coordinates or input features.

View Journal Article

Research Organization:: Univ. of Maryland, College Park, MD (United States)

Sponsoring Organization:: USDOE; USDOE Office of Science (SC), Basic Energy Sciences (BES)

Grant/Contract Number:: SC0021009

OSTI ID:: 2500908

Alternate ID(s):: OSTI ID: 3003384

Journal Information:: Digital Discovery, Journal Name: Digital Discovery Journal Issue: 1 Vol. 4; ISSN 2635-098X

Publisher:: Royal Society of ChemistryCopyright Statement

Country of Publication:: United States

Language:: English

References (65)

Understanding recent deep‐learning techniques for identifying collective variables of molecular dynamics Zhang, Wei; Schütte, Christof PAMM, Vol. 23, Issue 4 https://doi.org/10.1002/pamm.202300189	journal	September 2023
Machine learning heralding a new development phase in molecular dynamics simulations Prašnikar, Eva; Ljubič, Martin; Perdih, Andrej Artificial Intelligence Review, Vol. 57, 102 https://doi.org/10.1007/s10462-024-10731-4	journal	March 2024
VMD: Visual molecular dynamics Humphrey, William; Dalke, Andrew; Schulten, Klaus Journal of Molecular Graphics, Vol. 14, Issue 1 https://doi.org/10.1016/0263-7855(96)00018-5	journal	February 1996
Computing committors in collective variables via Mahalanobis diffusion maps Evans, Luke; Cameron, Maria K.; Tiwary, Pratyush Applied and Computational Harmonic Analysis, Vol. 64 https://doi.org/10.1016/j.acha.2023.01.001	journal	May 2023
Recent advances in describing and driving crystal nucleation using machine learning and artificial intelligence Beyerle, Eric R.; Zou, Ziyue; Tiwary, Pratyush Current Opinion in Solid State and Materials Science, Vol. 27, Issue 4 https://doi.org/10.1016/j.cossms.2023.101093	journal	August 2023
Exploring Kinase Asp-Phe-Gly (DFG) Loop Conformational Stability with AlphaFold2-RAVE Vani, Bodhi P.; Aranganathan, Akashnathan; Tiwary, Pratyush Journal of Chemical Information and Modeling, Vol. 64, Issue 7 https://doi.org/10.1021/acs.jcim.3c01436	journal	November 2023
DeepIce: A Deep Neural Network Approach To Identify Ice and Water Molecules Fulford, Maxwell; Salvalaglio, Matteo; Molteni, Carla Journal of Chemical Information and Modeling, Vol. 59, Issue 5 https://doi.org/10.1021/acs.jcim.9b00005	journal	March 2019
SGOOP-d: Estimating Kinetic Distances and Reaction Coordinate Dimensionality for Rare Event Systems from Biased/Unbiased Simulations Tsai, Sun-Ting; Smith, Zachary; Tiwary, Pratyush Journal of Chemical Theory and Computation, Vol. 17, Issue 11 https://doi.org/10.1021/acs.jctc.1c00431	journal	October 2021
Accelerating All-Atom Simulations and Gaining Mechanistic Understanding of Biophysical Systems through State Predictive Information Bottleneck Mehdi, Shams; Wang, Dedi; Pant, Shashank Journal of Chemical Theory and Computation, Vol. 18, Issue 5 https://doi.org/10.1021/acs.jctc.2c00058	journal	April 2022
Constructing Collective Variables Using Invariant Learned Representations Šípka, Martin; Erlebach, Andreas; Grajciar, Lukáš Journal of Chemical Theory and Computation, Vol. 19, Issue 3 https://doi.org/10.1021/acs.jctc.2c00729	journal	January 2023
AlphaFold2-RAVE: From Sequence to Boltzmann Ranking Vani, Bodhi P.; Aranganathan, Akashnathan; Wang, Dedi Journal of Chemical Theory and Computation, Vol. 19, Issue 14 https://doi.org/10.1021/acs.jctc.3c00290	journal	May 2023
Machine Learning Nucleation Collective Variables with Graph Neural Networks Dietrich, Florian M.; Advincula, Xavier R.; Gobbo, Gianpaolo Journal of Chemical Theory and Computation, Vol. 20, Issue 4 https://doi.org/10.1021/acs.jctc.3c00722	journal	October 2023
Permutationally Invariant Networks for Enhanced Sampling (PINES): Discovery of Multimolecular and Solvent-Inclusive Collective Variables Herringer, Nicholas S. M.; Dasetty, Siva; Gandhi, Diya Journal of Chemical Theory and Computation, Vol. 20, Issue 1 https://doi.org/10.1021/acs.jctc.3c00923	journal	December 2023
Data-Driven Path Collective Variables France-Lanord, Arthur; Vroylandt, Hadrien; Salanne, Mathieu Journal of Chemical Theory and Computation, Vol. 20, Issue 8 https://doi.org/10.1021/acs.jctc.4c00123	journal	April 2024
100 Years of the Lennard-Jones Potential Schwerdtfeger, Peter; Wales, David J. Journal of Chemical Theory and Computation, Vol. 20, Issue 9 https://doi.org/10.1021/acs.jctc.4c00135	journal	April 2024
Machine Learning Classification of Local Environments in Molecular Crystals Kuroshima, Daisuke; Kilgour, Michael; Tuckerman, Mark E. Journal of Chemical Theory and Computation, Vol. 20, Issue 14 https://doi.org/10.1021/acs.jctc.4c00418	journal	July 2024
Machine Learning Derived Collective Variables for the Study of Protein Homodimerization in Membrane Majumder, Ayan; Straub, John E. Journal of Chemical Theory and Computation, Vol. 20, Issue 13 https://doi.org/10.1021/acs.jctc.4c00454	journal	June 2024
Calculating Protein–Ligand Residence Times through State Predictive Information Bottleneck Based Enhanced Sampling Lee, Suemin; Wang, Dedi; Seeliger, Markus A. Journal of Chemical Theory and Computation, Vol. 20, Issue 14 https://doi.org/10.1021/acs.jctc.4c00503	journal	July 2024
Augmenting Human Expertise in Weighted Ensemble Simulations through Deep Learning-Based Information Bottleneck Wang, Dedi; Tiwary, Pratyush Journal of Chemical Theory and Computation, Vol. 20, Issue 23 https://doi.org/10.1021/acs.jctc.4c00919	journal	November 2024
Multiscale Reweighted Stochastic Embedding: Deep Learning of Collective Variables for Enhanced Sampling Rydzewski, Jakub; Valsson, Omar The Journal of Physical Chemistry A, Vol. 125, Issue 28 https://doi.org/10.1021/acs.jpca.1c02869	journal	July 2021
Influence of Long-Range Forces on the Transition States and Dynamics of NaCl Ion-Pair Dissociation in Water Wang, Dedi; Zhao, Renjie; Weeks, John D. The Journal of Physical Chemistry B, Vol. 126, Issue 2 https://doi.org/10.1021/acs.jpcb.1c09454	journal	January 2022
Enhanced Sampling of Crystal Nucleation with Graph Representation Learnt Variables Zou, Ziyue; Tiwary, Pratyush The Journal of Physical Chemistry B, Vol. 128, Issue 12, p. 3037-3045 https://doi.org/10.1021/acs.jpcb.4c00080	journal	March 2024
Topology-Based Phase Identification of Bulk, Interface, and Confined Water Using an Edge-Conditioned Convolutional Graph Neural Network Moradzadeh, A.; Oliaei, H.; Aluru, N. R. The Journal of Physical Chemistry C, Vol. 127, Issue 5 https://doi.org/10.1021/acs.jpcc.2c07423	journal	January 2023
Data-Driven Collective Variables for Enhanced Sampling Bonati, Luigi; Rizzi, Valerio; Parrinello, Michele The Journal of Physical Chemistry Letters, Vol. 11, Issue 8 https://doi.org/10.1021/acs.jpclett.0c00535	journal	April 2020
Collective Variables for Conformational Polymorphism in Molecular Crystals Elishav, Oren; Podgaetsky, Roy; Meikler, Olga The Journal of Physical Chemistry Letters, Vol. 14, Issue 4 https://doi.org/10.1021/acs.jpclett.2c03491	journal	January 2023
Structural absorption by barbule microstructures of super black bird of paradise feathers McCoy, Dakota E.; Feo, Teresa; Harvey, Todd Alan Nature Communications, Vol. 9, Issue 1 https://doi.org/10.1038/s41467-017-02088-w	journal	January 2018
Double-slit photoelectron interference in strong-field ionization of the neon dimer Kunitski, Maksim; Eicke, Nicolas; Huber, Pia Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-018-07882-8	journal	January 2019
Combining stochastic resetting with Metadynamics to speed-up molecular dynamics simulations Blumer, Ofir; Reuveni, Shlomi; Hirshberg, Barak Nature Communications, Vol. 15, Issue 1 https://doi.org/10.1038/s41467-023-44528-w	journal	January 2024
CEGANN: Crystal Edge Graph Attention Neural Network for multiscale classification of materials environment Banik, Suvo; Dhabal, Debdas; Chan, Henry npj Computational Materials, Vol. 9, Issue 1 https://doi.org/10.1038/s41524-023-00975-z	journal	February 2023
Computing the committor with the committor to study the transition state ensemble Kang, Peilin; Trizio, Enrico; Parrinello, Michele Nature Computational Science, Vol. 4, Issue 6 https://doi.org/10.1038/s43588-024-00645-0	journal	June 2024
A generalized deep learning approach for local structure identification in molecular simulations DeFever, Ryan S.; Targonski, Colin; Hall, Steven W. Chemical Science, Vol. 10, Issue 32 https://doi.org/10.1039/C9SC02097G	journal	January 2019
GCIceNet: a graph convolutional network for accurate classification of water phases Kim, QHwan; Ko, Joon-Hyuk; Kim, Sunghoon Physical Chemistry Chemical Physics, Vol. 22, Issue 45 https://doi.org/10.1039/D0CP03456H	journal	January 2020
Neural networks for local structure detection in polymorphic systems Geiger, Philipp; Dellago, Christoph The Journal of Chemical Physics, Vol. 139, Issue 16 https://doi.org/10.1063/1.4825111	journal	October 2013
Reweighted autoencoded variational Bayes for enhanced sampling (RAVE) Ribeiro, João Marcelo Lamim; Bravo, Pablo; Wang, Yihang The Journal of Chemical Physics, Vol. 149, Issue 7 https://doi.org/10.1063/1.5025487	journal	August 2018
Reaction coordinates and rate constants for liquid droplet nucleation: Quantifying the interplay between driving force and memory Tsai, Sun-Ting; Smith, Zachary; Tiwary, Pratyush The Journal of Chemical Physics, Vol. 151, Issue 15 https://doi.org/10.1063/1.5124385	journal	October 2019
State predictive information bottleneck Wang, Dedi; Tiwary, Pratyush The Journal of Chemical Physics, Vol. 154, Issue 13 https://doi.org/10.1063/5.0038198	journal	April 2021
GraphVAMPNet, using graph neural networks and variational approach to Markov processes for dynamical modeling of biomolecules Ghorbani, Mahdi; Prasad, Samarjeet; Klauda, Jeffery B. The Journal of Chemical Physics, Vol. 156, Issue 18 https://doi.org/10.1063/5.0085607	journal	May 2022
GraphVAMPnets for uncovering slow collective variables of self-assembly dynamics Liu, Bojun; Xue, Mingyi; Qiu, Yunrui The Journal of Chemical Physics, Vol. 159, Issue 9 https://doi.org/10.1063/5.0158903	journal	September 2023
Classification of complex local environments in systems of particle shapes through shape symmetry-encoded data augmentation Lee, Shih-Kuang (Alex); Tsai, Sun-Ting; Glotzer, Sharon C. The Journal of Chemical Physics, Vol. 160, Issue 15 https://doi.org/10.1063/5.0194820	journal	April 2024
Deep learning path-like collective variable for enhanced sampling molecular dynamics Fröhlking, Thorben; Bonati, Luigi; Rizzi, Valerio The Journal of Chemical Physics, Vol. 160, Issue 17 https://doi.org/10.1063/5.0202156	journal	May 2024
Reaction coordinates of biomolecular isomerization Bolhuis, P. G.; Dellago, C.; Chandler, D. Proceedings of the National Academy of Sciences, Vol. 97, Issue 11 https://doi.org/10.1073/pnas.100127697	journal	May 2000
A self-learning algorithm for biased molecular dynamics Tribello, Gareth A.; Ceriotti, Michele; Parrinello, Michele Proceedings of the National Academy of Sciences, Vol. 107, Issue 41 https://doi.org/10.1073/pnas.1011511107	journal	September 2010
Escaping free-energy minima Laio, A.; Parrinello, M. Proceedings of the National Academy of Sciences, Vol. 99, Issue 20 https://doi.org/10.1073/pnas.202427399	journal	September 2002
Effective data-driven collective variables for free energy calculations from metadynamics of paths Müllender, Lukas; Rizzi, Andrea; Parrinello, Michele PNAS Nexus, Vol. 3, Issue 4 https://doi.org/10.1093/pnasnexus/pgae159	journal	March 2024
Learning high-dimensional reaction coordinates of fast-folding proteins using State Predictive information bottleneck and Bias Exchange Metadynamics Pomarici, Nancy D.; Mehdi, Shams; Quoika, Patrick K. https://doi.org/10.1101/2023.07.24.550401	preprint	July 2023
Bond-orientational order in liquids and glasses Steinhardt, Paul J.; Nelson, David R.; Ronchetti, Marco Physical Review B, Vol. 28, Issue 2 https://doi.org/10.1103/PhysRevB.28.784	journal	July 1983
From Metadynamics to Dynamics Tiwary, Pratyush; Parrinello, Michele Physical Review Letters, Vol. 111, Issue 23 https://doi.org/10.1103/PhysRevLett.111.230602	journal	December 2013
Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties Xie, Tian; Grossman, Jeffrey C. Physical Review Letters, Vol. 120, Issue 14 https://doi.org/10.1103/PhysRevLett.120.145301	journal	April 2018
Neural-Network-Based Path Collective Variables for Enhanced Sampling of Phase Transformations Rogal, Jutta; Schneider, Elia; Tuckerman, Mark E. Physical Review Letters, Vol. 123, Issue 24 https://doi.org/10.1103/PhysRevLett.123.245701	journal	December 2019
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces Behler, Jörg; Parrinello, Michele Physical Review Letters, Vol. 98, Issue 14 https://doi.org/10.1103/PhysRevLett.98.146401	journal	April 2007
On the orthogonal transformation used for structural comparisons Kearsley, S. K. Acta Crystallographica Section A Foundations of Crystallography, Vol. 45, Issue 2 https://doi.org/10.1107/S0108767388010128	journal	February 1989
Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs Monti, Federico; Boscaini, Davide; Masci, Jonathan 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2017.576	conference	July 2017
Autapse-induced multiple inverse stochastic resonance in a neural system Zhang, Ni; Li, Dongxi; Xing, Yanya The European Physical Journal B, Vol. 94, Issue 1 https://doi.org/10.1140/epjb/s10051-020-00008-4	journal	January 2021
Enhancing Important Fluctuations: Rare Events and Metadynamics from a Conceptual Viewpoint Valsson, Omar; Tiwary, Pratyush; Parrinello, Michele Annual Review of Physical Chemistry, Vol. 67, Issue 1 https://doi.org/10.1146/annurev-physchem-040215-112229	journal	May 2016
Machine Learning for Molecular Simulation Noé, Frank; Tkatchenko, Alexandre; Müller, Klaus-Robert Annual Review of Physical Chemistry, Vol. 71, Issue 1 https://doi.org/10.1146/annurev-physchem-042018-052331	journal	April 2020
Enhanced Sampling with Machine Learning Mehdi, Shams; Smith, Zachary; Herron, Lukas Annual Review of Physical Chemistry, Vol. 75, Issue 1 https://doi.org/10.1146/annurev-physchem-083122-125941	journal	February 2024
Machine learning for molecular simulations of crystal nucleation and growth Sarupria, Sapna; Hall, Steven W.; Rogal, Jutta MRS Bulletin, Vol. 47, Issue 9 https://doi.org/10.1557/s43577-022-00407-1	journal	September 2022
Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials Jørgensen, Peter Bjørn; Jacobsen, Karsten Wedel; Schmidt, Mikkel N. arXiv https://doi.org/10.48550/arXiv.1806.03146	preprint	January 2018
Fast Graph Representation Learning with PyTorch Geometric Fey, Matthias; Lenssen, Jan Eric arXiv https://doi.org/10.48550/arXiv.1903.02428	preprint	January 2019
PyTorch: An Imperative Style, High-Performance Deep Learning Library Paszke, Adam; Gross, Sam; Massa, Francisco arXiv https://doi.org/10.48550/arXiv.1912.01703	preprint	January 2019
E(n) Equivariant Graph Neural Networks Satorras, Victor Garcia; Hoogeboom, Emiel; Welling, Max arXiv https://doi.org/10.48550/arXiv.2102.09844	preprint	January 2021
A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems Duval, Alexandre; Mathis, Simon V.; Joshi, Chaitanya K. arXiv https://doi.org/10.48550/arXiv.2312.07511	preprint	January 2023
Descriptors-free Collective Variables From Geometric Graph Neural Networks Zhang, Jintu; Bonati, Luigi; Trizio, Enrico arXiv https://doi.org/10.48550/arXiv.2409.07339	preprint	January 2024
Assessing interaction recovery of predicted protein-ligand poses Errington, David; Schneider, Constantin; Bouysset, Cédric arXiv https://doi.org/10.48550/arXiv.2409.20227	preprint	January 2024
Empowering AlphaFold2 for protein conformation selective drug discovery with AlphaFold2-RAVE Gu, Xinyu; Aranganathan, Akashnathan; Tiwary, Pratyush eLife, Vol. 13 https://doi.org/10.7554/eLife.99702	journal	September 2024

Similar Records

AGS-GNN: Attribute-guided Sampling for Graph Neural Networks

Conference · Sat Aug 24 00:00:00 EDT 2024 · OSTI ID:2468651

Scalable algorithms for physics-informed neural and graph networks

Journal Article · Tue Jun 28 20:00:00 EDT 2022 · Data-Centric Engineering · OSTI ID:1872036

A graph neural network-state predictive information bottleneck (GNN-SPIB) approach for learning molecular thermodynamics and kinetics

Citation Formats

References (65)

Similar Records

Related Subjects