Deep Learning Method for Computing Committor Functions with Adaptive Sampling (2404.06206v1)
Abstract: The committor function is a central object for quantifying the transitions between metastable states of dynamical systems. Recently, a number of computational methods based on deep neural networks have been developed for computing the high-dimensional committor function. The success of the methods relies on sampling adequate data for the transition, which still is a challenging task for complex systems at low temperatures. In this work, we propose a deep learning method with two novel adaptive sampling schemes (I and II). In the two schemes, the data are generated actively with a modified potential where the bias potential is constructed from the learned committor function. We theoretically demonstrate the advantages of the sampling schemes and show that the data in sampling scheme II are uniformly distributed along the transition tube. This makes a promising method for studying the transition of complex systems. The efficiency of the method is illustrated in high-dimensional systems including the alanine dipeptide and a solvated dimer system.
- Calculation of conformational transitions and barriers in solvated systems: Application to the alanine dipeptide in water. J. Chem. Phys., 110(4):2099–2108, 1999.
- Metadynamics. Wiley Interdiscip. Rev.: Comput. Mol. Sci., 1(5):826–843, 2011.
- Transition path sampling: Throwing ropes over rough mountain passes, in the dark. Annu. Rev. Phys. Chem., 53(1):291–318, 2002.
- Reaction coordinates of biomolecular isomerization. Proc. Natl. Acad. Sci., 97(11):5877–5882, 2000.
- Committor functions via tensor networks. J. Comput. Phys., 472:111646, 2023.
- On the calculation of reaction rate constants in the transition path ensemble. J. Chem. Phys., 110(14):6617–6625, 1999.
- Transition path sampling. Adv. Chem. Phys., 123:1–78, 2002.
- String method for the study of rare events. Phys. Rev. B, 66(5):052301, 2002.
- Transition pathways in complex systems: Reaction coordinates, isocommittor surfaces, and transition tubes. Chem. Phys. Lett., 413(1-3):242–247, 2005.
- Simplified and improved string method for computing the minimum energy paths in barrier-crossing events. J. Chem. Phys., 126(16), 2007.
- W. E and E. Vanden-Eijnden. Towards a theory of transition paths. J. Stat. Phys., 123(3):503–523, 2006.
- W. E and E. Vanden-Eijnden. Transition-path theory and path-finding algorithms for the study of rare events. Annu. Rev. Phys., 61:391–420, 2010.
- Computing committors in collective variables via mahalanobis diffusion maps. Appl. Comput. Harmon. Anal., 2023.
- C. W. Gardiner. Handbook of Stochastic Methods for Physics, Chemistry and the Natural Sciences. Springer Press, New York, 1997.
- Supervised learning and the finite-temperature string method for computing committor functions and reaction rates. J. Chem. Phys., 157(18):184111, 2022.
- F. Hecht. New development in freefem++. J. Numer. Math., 20(3-4):251–265, 2012.
- Nudged elastic band method for finding minimum energy paths of transitions. In Classical and quantum dynamics in condensed phase simulations, pages 385–404. World Scientific, 1998.
- Solving for high-dimensional committor functions using artificial neural networks. Res. Math. Sci., 6:1–13, 2019.
- Adam: A method for stochastic optimization, 2015. in: 3rd International Conference on Learning Representations (ICLR), San Diego.
- R. Lai and J. Lu. Point cloud discretization of fokker-planck operators for committor functions. Multiscale Model. Simul., 16(2):710–726, 2018.
- A. Laio and M. Parrinello. Escaping free-energy minima. Proc. Natl. Acad. Sci., 99(20):12562–12566, 2002.
- Computing committor functions for the study of rare events using deep learning. J. Chem. Phys., 151(5):054112, 2019.
- A. Ma and A. R. Dinner. Automatic method for identifying reaction coordinates in complex systems. J. Phys. Chem. B, 109(14):6769–6779, 2005.
- String method in collective variables: Minimum free energy paths and isocommittor surfaces. J. Chem. Phys., 125(2):024106, 2006.
- Scalable molecular dynamics with namd. J. Comput. Chem., 26(16):1781–1802, 2005.
- Transition pathways in complex systems: Application of the finite-temperature string method to the alanine dipeptide. J. Chem. Phys., 123(13), 2005.
- Active importance sampling for variational objectives dominated by rare events: Consequences for optimization and generalization, 2021. in: MSML21: Mathematical and Scientific Machine Learning.
- Schnet: A continuous-filter convolutional neural network for modeling quantum interactions. Adv. Neural Inf. Process., 30, 2017.
- Local and global perspectives on diffusion maps in the analysis of molecular systems. Proceedings of the Royal Society A, 476(2233):20190036, 2020.