Machine learning approaches for analyzing and enhancing molecular dynamics simulations
arXiv:1909.11748
Abstract
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.
References in corpus (11)
- Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
- ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
- Density estimation using Real NVP
- Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
- A Variational Approach to Enhanced Sampling and Free Energy Calculations
- Caliber based spectral gap optimization of order parameters (SGOOP) for sampling complex molecular systems
- Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape exploration
- Variational Encoding of Complex Dynamics
- Unfolding Hidden Barriers by Active Enhanced Sampling
- Predictive Collective Variable Discovery with Deep Bayesian Models
- Artificial Intelligence Assists Discovery of Reaction Coordinates and Mechanisms from Molecular Dynamics Simulations