A generalized deep learning approach for local structure identification in molecular simulations

We demonstrate a PointNet-based deep learning approach to classify local structure in molecular simulations, learning features directly from atomic coordinates.

[1]  Matteo Salvalaglio,et al.  DeepIce: A Deep Neural Network Approach To Identify Ice and Water Molecules , 2019, J. Chem. Inf. Model..

[2]  Yuqing Qiu,et al.  Ice Nucleation Efficiency of Hydroxylated Organic Surfaces Is Controlled by Their Structural Fluctuations and Mismatch to Ice. , 2017, Journal of the American Chemical Society.

[3]  Wei Chen,et al.  Collective variable discovery and enhanced sampling using autoencoders: Innovations in network architecture and error function design. , 2018, The Journal of chemical physics.

[4]  Andrew H. Nguyen,et al.  Role of stacking disorder in ice nucleation , 2017, Nature.

[5]  David Chandler,et al.  Premelting, fluctuations, and coarse-graining of water-ice interfaces. , 2014, The Journal of chemical physics.

[6]  Shekhar Garde,et al.  Efficient method to characterize the context-dependent hydrophobicity of proteins. , 2014, The journal of physical chemistry. B.

[7]  Nicholas Rego,et al.  Hydrophobicity of proteins and nanostructured solutes is governed by topographical and chemical context , 2017, Proceedings of the National Academy of Sciences.

[8]  Christoph Dellago,et al.  Neural networks for local structure detection in polymorphic systems. , 2013, The Journal of chemical physics.

[9]  Chris Benmore,et al.  Machine learning coarse grained models for water , 2019, Nature Communications.

[10]  P. Steinhardt,et al.  Bond-orientational order in liquids and glasses , 1983 .

[11]  Fabio Pietrucci,et al.  Pre-critical fluctuations and what they disclose about heterogeneous crystal nucleation , 2017, Nature Communications.

[12]  Sapna Sarupria,et al.  The surface charge distribution affects the ice nucleating efficiency of silver iodide. , 2016, The Journal of chemical physics.

[13]  Sapna Sarupria,et al.  Adsorption of amino acids on graphene: assessment of current force fields. , 2019, Soft matter.

[14]  Valeria Molinero,et al.  Why Is Gyroid More Difficult to Nucleate from Disordered Liquids than Lamellar and Hexagonal Mesophases? , 2018, The journal of physical chemistry. B.

[15]  Christoph Dellago,et al.  Accurate determination of crystal structures based on averaged local bond order parameters. , 2008, The Journal of chemical physics.

[16]  Christoph Dellago,et al.  Reaction coordinates for the crystal nucleation of colloidal suspensions extracted from the reweighted path ensemble. , 2011, The Journal of chemical physics.

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

[18]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[19]  Klaus-Robert Müller,et al.  Machine learning of accurate energy-conserving molecular force fields , 2016, Science Advances.

[20]  Jennifer M. Rieser,et al.  Identifying structural flow defects in disordered solids using machine-learning methods. , 2014, Physical review letters.

[21]  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.

[22]  Liam C. Jacobson,et al.  Order parameters for the multistep crystallization of clathrate hydrates. , 2011, The Journal of chemical physics.

[23]  Amish J. Patel,et al.  Characterizing Solvent Density Fluctuations in Dynamical Observation Volumes. , 2018, The journal of physical chemistry. B.

[24]  Graeme Ackland,et al.  Applications of local crystal structure measures in experiment and simulation , 2006 .

[25]  Ryan S. DeFever,et al.  Nucleation mechanism of clathrate hydrates of water-soluble guest molecules. , 2017, The Journal of chemical physics.

[26]  Fernando A. Escobedo,et al.  Developing Local Order Parameters for Order–Disorder Transitions From Particles to Block Copolymers: Methodological Framework , 2018, Macromolecules.

[27]  Fernando A. Escobedo,et al.  Developing Local Order Parameters for Order–Disorder Transitions From Particles to Block Copolymers: Application to Macromolecular Systems , 2018, Macromolecules.

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

[29]  Ting Xu,et al.  Self-assembly and applications of anisotropic nanomaterials: A review , 2015 .

[30]  T Kretz,et al.  Machine-learning approach for local classification of crystalline structures in multiphase systems. , 2017, Physical review. E.

[31]  C. Vega,et al.  Seeding approach to crystal nucleation. , 2016, The Journal of chemical physics.

[32]  R. Doolittle,et al.  A simple method for displaying the hydropathic character of a protein. , 1982, Journal of molecular biology.

[33]  Peter J Rossky,et al.  A simple atomic-level hydrophobicity scale reveals protein interfacial structure. , 2014, Journal of molecular biology.

[34]  Raffaela Cabriolu,et al.  Ice nucleation on carbon surface supports the classical theory for heterogeneous nucleation. , 2015, Physical review. E, Statistical, nonlinear, and soft matter physics.

[35]  Andrew L. Ferguson,et al.  Machine learning for autonomous crystal structure identification. , 2017, Soft matter.

[36]  Ioannis G. Kevrekidis,et al.  Nonlinear dimensionality reduction in molecular simulation: The diffusion map approach , 2011 .

[37]  M. Engel,et al.  Self-Assembly of Colloidal Nanocrystals: From Intricate Structures to Functional Materials. , 2016, Chemical reviews.

[38]  Sapna Sarupria,et al.  Heterogeneous Ice Nucleation: Interplay of Surface Properties and Their Impact on Water Orientations. , 2017, Langmuir : the ACS journal of surfaces and colloids.

[39]  Pablo G Debenedetti,et al.  Direct calculation of ice homogeneous nucleation rate for a molecular model of water , 2015, Proceedings of the National Academy of Sciences.

[40]  H. C. Andersen,et al.  Molecular dynamics study of melting and freezing of small Lennard-Jones clusters , 1987 .

[41]  Michele Parrinello,et al.  Predicting polymorphism in molecular crystals using orientational entropy , 2018, Proceedings of the National Academy of Sciences.

[42]  David Quigley,et al.  NaCl nucleation from brine in seeded simulations: Sources of uncertainty in rate estimates. , 2018, The Journal of chemical physics.

[43]  Brian C. Barnes,et al.  Two-component order parameter for quantifying clathrate hydrate nucleation and growth. , 2014, The Journal of chemical physics.

[44]  Samuel S. Schoenholz,et al.  Machine learning determination of atomic dynamics at grain boundaries , 2018, Proceedings of the National Academy of Sciences.

[45]  J. Doye,et al.  Local order parameters for use in driving homogeneous ice nucleation with all-atom models of water. , 2012, The Journal of chemical physics.

[46]  Sapna Sarupria,et al.  Molecular dynamics study of carbon dioxide hydrate dissociation. , 2011, The journal of physical chemistry. A.

[47]  Felix Kling,et al.  Structure and Dynamics of the Quasi-Liquid Layer at the Surface of Ice from Molecular Simulations , 2018, The Journal of Physical Chemistry C.

[48]  David Chandler,et al.  Quantifying Density Fluctuations in Volumes of All Shapes and Sizes Using Indirect Umbrella Sampling , 2011, Journal of statistical physics.

[49]  A. Michaelides,et al.  Crystal Nucleation in Liquids: Open Questions and Future Challenges in Molecular Dynamics Simulations , 2016, Chemical reviews.

[50]  D. Wolf,et al.  Deformation-mechanism map for nanocrystalline metals by molecular-dynamics simulation , 2004, Nature materials.

[51]  Valeria Molinero,et al.  Self-Assembly of Mesophases from Nanoparticles. , 2017, The journal of physical chemistry letters.

[52]  Athanassios Z Panagiotopoulos,et al.  Automated crystal characterization with a fast neighborhood graph analysis method. , 2018, Soft matter.

[53]  P. B. Shepson,et al.  Molecular dynamics simulations of ice growth from supercooled water , 2005 .

[54]  Sharon C Glotzer,et al.  Machine learning for crystal identification and discovery , 2017, 1710.09861.

[55]  J. Behler.  Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations. , 2011, Physical chemistry chemical physics : PCCP.

[56]  Christoph Dellago,et al.  Kinetic pathways of ion pair dissociation in water , 1999 .

[57]  Adam P Willard,et al.  Characterizing Hydration Properties Based on the Orientational Structure of Interfacial Water Molecules. , 2018, Journal of chemical theory and computation.

[58]  S. Garde,et al.  Mapping hydrophobicity at the nanoscale: applications to heterogeneous surfaces and proteins. , 2010, Faraday discussions.

[59]  S. Schmidt,et al.  Robust structural identification via polyhedral template matching , 2016, 1603.05143.

[60]  Andrew H. Nguyen,et al.  Identification of Clathrate Hydrates, Hexagonal Ice, Cubic Ice, and Liquid Water in Simulations: the CHILL+ Algorithm. , 2015, The journal of physical chemistry. B.

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