Data-Driven Methods in Multiscale Modeling of Soft Matter
- 1k Downloads
As in many other scientific fields, data-driven methods are rapidly impacting multiscale modeling. This chapter will illustrate some of the many ways advanced statistical models and a data-centric perspective help augmenting computer simulations in soft matter. A specific focus on force fields, sampling, and simulation analysis is presented, taking advantage of machine learning, high-throughput schemes, and Bayesian inference.
Various discussions have helped shape some of the views developed in this chapter. I am especially grateful to Denis Andrienko, Kurt Kremer, Joseph F. Rudzinski, Omar Valsson, and Anatole von Lilienfeld.
This work was supported in part by the Emmy Noether Programme of the Deutsche Forschungsgemeinschaft (DFG).
- Bereau T (2018) Example: ML model of Hirshfeld ratios. https://gitlab.mpcdf.mpg.de/trisb/handbook_example. Accessed 28 Feb 2018
- Bowman GR, Pande VS, Noé F (Eds) (2013) An introduction to Markov state models and their application to long timescale molecular simulation, Advances in Experimental Medicine and Biology 797. Springer, Dordrecht (NL)Google Scholar
- Faber FA, Hutchison L, Huang B, Gilmer J, Schoenholz SS, Dahl GE, Vinyals O, Kearnes S, Riley PF, von Lilienfeld OA (2017) Machine learning prediction errors better than DFT accuracy. arXiv e-preprints arXiv:170205532Google Scholar
- Ferguson AL, Panagiotopoulos AZ, Debenedetti PG, Kevrekidis IG (2011) Integrating diffusion maps with umbrella sampling: application to alanine dipeptide. J Chem Phys 134(13):04B606Google Scholar
- Fisher DH, Pazzani MJ, Langley P (eds) (2014) Concept formation: knowledge and experience in unsupervised learning. Morgan Kaufmann Series in Machine Learning, San Mateo (CA)Google Scholar
- Huan TD, Batra R, Chapman J, Krishnan S, Chen L, Ramprasad R (2017) A universal strategy for the creation of machine learning-based atomistic force fields. npj Comput Mater 3(1):37Google Scholar
- John S (2016) Many-body coarse-grained interactions using gaussian approximation potentials. arXiv preprint arXiv:161109123Google Scholar
- Noid W (2013) Perspective: coarse-grained models for biomolecular systems. J Chem Phys 139(9):09B201_1Google Scholar
- Ramakrishnan R, von Lilienfeld OA (2017) Machine learning, quantum chemistry, and chemical space. Rev Comput Chem 30:225–256Google Scholar
- Schiilkopf B (2001) The kernel trick for distances. In: Advances in neural information processing systems. Proceedings of the 2000 conference, vol 13. MIT Press, Cambridge (MA), p 301Google Scholar
- Shaw DE, Grossman J, Bank JA, Batson B, Butts JA, Chao JC, Deneroff MM, Dror RO, Even A, Fenton CH et al (2014) Anton 2: raising the bar for performance and programmability in a special-purpose molecular dynamics supercomputer. In: Proceedings of the international conference for high performance computing, networking, storage and analysis. IEEE Press, New Orleans, pp 41–53Google Scholar