Machine Learning of coarsegrained Molecular Dynamics Force Fields
Abstract
Atomistic or abinitio molecular dynamics simulations are widely used to predict thermodynamics and kinetics and relate them to molecular structure. A common approach to go beyond the time and lengthscales accessible with such computationally expensive simulations is the definition of coarsegrained molecular models. Existing coarsegraining approaches define an effective interaction potential to match defined properties of highresolution models or experimental data. In this paper, we reformulate coarsegraining as a supervised machine learning problem. We use statistical learning theory to decompose the coarsegraining error and crossvalidation to select and compare the performance of different models. We introduce CGnets, a deep learning approach, that learns coarsegrained free energy functions and can be trained by a force matching scheme. CGnets maintain all physically relevant invariances and allow one to incorporate prior physics knowledge to avoid sampling of unphysical structures. We show that CGnets can capture allatom explicitsolvent free energy surfaces with models using only a few coarsegrained beads and no solvent, while classical coarsegraining methods fail to capture crucial features of the free energy surface. Thus, CGnets are able to capture multibody terms that emerge from the dimensionality reduction.
 Publication:

arXiv eprints
 Pub Date:
 December 2018
 DOI:
 10.48550/arXiv.1812.01736
 arXiv:
 arXiv:1812.01736
 Bibcode:
 2018arXiv181201736W
 Keywords:

 Physics  Computational Physics;
 Computer Science  Machine Learning;
 Statistics  Machine Learning