Machine learning approaches for analyzing and enhancing molecular dynamics simulations.

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.

[1]  Frank Noé,et al.  Variational Approach to Molecular Kinetics. , 2014, Journal of chemical theory and computation.

[2]  Frank Noé,et al.  PyEMMA 2: A Software Package for Estimation, Validation, and Analysis of Markov Models. , 2015, Journal of chemical theory and computation.

[3]  Hao Wu,et al.  VAMPnets for deep learning of molecular kinetics , 2017, Nature Communications.

[4]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[5]  Diwakar Shukla,et al.  Reinforcement Learning Based Adaptive Sampling: REAPing Rewards by Exploring Protein Conformational Landscapes. , 2017, The journal of physical chemistry. B.

[6]  Michele Parrinello,et al.  Enhancing Important Fluctuations: Rare Events and Metadynamics from a Conceptual Viewpoint. , 2016, Annual review of physical chemistry.

[7]  Florian Sittel,et al.  Machine Learning of Biomolecular Reaction Coordinates. , 2018, The journal of physical chemistry letters.

[8]  Wei Chen,et al.  Capabilities and Limitations of Time-lagged Autoencoders for Slow Mode Discovery in Dynamical Systems , 2019, The Journal of Chemical Physics.

[9]  F. Noé,et al.  Dynamic graphical models of molecular kinetics , 2019, Proceedings of the National Academy of Sciences.

[10]  Dalibor Trapl,et al.  Anncolvar: Approximation of Complex Collective Variables by Artificial Neural Networks for Analysis and Biasing of Molecular Simulations , 2019, Front. Mol. Biosci..

[11]  Sebastian Johann Wetzel,et al.  Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders , 2017, Physical review. E.

[12]  Prafulla Dhariwal,et al.  Glow: Generative Flow with Invertible 1x1 Convolutions , 2018, NeurIPS.

[13]  Michele Parrinello,et al.  Simplifying the representation of complex free-energy landscapes using sketch-map , 2011, Proceedings of the National Academy of Sciences.

[14]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[15]  Aaron R Dinner,et al.  Automatic method for identifying reaction coordinates in complex systems. , 2005, The journal of physical chemistry. B.

[16]  Mohammad M. Sultan,et al.  Variational encoding of complex dynamics. , 2017, Physical review. E.

[17]  Sun-Ting Tsai,et al.  Multi-dimensional spectral gap optimization of order parameters (SGOOP) through conditional probability factorization , 2018 .

[18]  Christine Peter,et al.  EncoderMap: Dimensionality Reduction and Generation of Molecule Conformations. , 2019, Journal of chemical theory and computation.

[19]  Jing Zhang,et al.  Unfolding Hidden Barriers by Active Enhanced Sampling , 2017, Physical review letters.

[20]  R. Kondor,et al.  Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. , 2009, Physical review letters.

[21]  J. Preto,et al.  Fast recovery of free energy landscapes via diffusion-map-directed molecular dynamics. , 2014, Physical chemistry chemical physics : PCCP.

[22]  M. Parrinello,et al.  A time-independent free energy estimator for metadynamics. , 2015, The journal of physical chemistry. B.

[23]  B. Berne,et al.  Spectral gap optimization of order parameters for sampling complex molecular systems , 2015, Proceedings of the National Academy of Sciences.

[24]  G. Torrie,et al.  Nonphysical sampling distributions in Monte Carlo free-energy estimation: Umbrella sampling , 1977 .

[25]  Pratyush Tiwary,et al.  Reweighted autoencoded variational Bayes for enhanced sampling (RAVE). , 2018, The Journal of chemical physics.

[26]  K. Dill,et al.  Inferring Transition Rates of Networks from Populations in Continuous-Time Markov Processes. , 2015, Journal of chemical theory and computation.

[27]  Hao Wu,et al.  Deep Generative Markov State Models , 2018, NeurIPS.

[28]  Toni Giorgino,et al.  Identification of slow molecular order parameters for Markov model construction. , 2013, The Journal of chemical physics.

[29]  Michele Parrinello,et al.  Neural networks-based variationally enhanced sampling , 2019, Proceedings of the National Academy of Sciences.

[30]  Michele Parrinello,et al.  Variational approach to enhanced sampling and free energy calculations. , 2014, Physical review letters.

[31]  Pratyush Tiwary,et al.  Automatic mutual information noise omission (AMINO): generating order parameters for molecular systems , 2020 .

[32]  Hao Wu,et al.  Boltzmann generators: Sampling equilibrium states of many-body systems with deep learning , 2018, Science.

[33]  Jakub Rydzewski,et al.  Promoting transparency and reproducibility in enhanced molecular simulations , 2019, Nature Methods.

[34]  Hao Wu,et al.  Data-Driven Model Reduction and Transfer Operator Approximation , 2017, J. Nonlinear Sci..

[35]  Yihang Wang,et al.  Past–future information bottleneck for sampling molecular reaction coordinate simultaneously with thermodynamics and kinetics , 2019, Nature Communications.

[36]  Gerhard Hummer,et al.  Artificial Intelligence Assists Discovery of Reaction Coordinates and Mechanisms from Molecular Dynamics Simulations , 2019, 1901.04595.

[37]  Ann B. Lee,et al.  Geometric diffusions as a tool for harmonic analysis and structure definition of data: diffusion maps. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[38]  Ioannis G Kevrekidis,et al.  Intrinsic map dynamics exploration for uncharted effective free-energy landscapes , 2016, Proceedings of the National Academy of Sciences.

[39]  Wei Chen,et al.  Molecular enhanced sampling with autoencoders: On‐the‐fly collective variable discovery and accelerated free energy landscape exploration , 2017, J. Comput. Chem..

[40]  Markus Schöberl,et al.  Predictive Collective Variable Discovery with Deep Bayesian Models , 2018, The Journal of chemical physics.

[41]  Frank Noé,et al.  A Variational Approach to Modeling Slow Processes in Stochastic Dynamical Systems , 2012, Multiscale Model. Simul..

[42]  J S Smith,et al.  ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost , 2016, Chemical science.

[43]  M. Mezei.  Adaptive umbrella sampling: Self-consistent determination of the non-Boltzmann bias , 1987 .

[44]  Michele Parrinello,et al.  Generalized neural-network representation of high-dimensional potential-energy surfaces. , 2007, Physical review letters.