Differentiable molecular simulation can learn all the parameters in a coarse-grained force field for proteins

PLoS One. 2021 Sep 2;16(9):e0256990. doi: 10.1371/journal.pone.0256990. eCollection 2021.

Abstract

Finding optimal parameters for force fields used in molecular simulation is a challenging and time-consuming task, partly due to the difficulty of tuning multiple parameters at once. Automatic differentiation presents a general solution: run a simulation, obtain gradients of a loss function with respect to all the parameters, and use these to improve the force field. This approach takes advantage of the deep learning revolution whilst retaining the interpretability and efficiency of existing force fields. We demonstrate that this is possible by parameterising a simple coarse-grained force field for proteins, based on training simulations of up to 2,000 steps learning to keep the native structure stable. The learned potential matches chemical knowledge and PDB data, can fold and reproduce the dynamics of small proteins, and shows ability in protein design and model scoring applications. Problems in applying differentiable molecular simulation to all-atom models of proteins are discussed along with possible solutions and the variety of available loss functions. The learned potential, simulation scripts and training code are made available at https://github.com/psipred/cgdms.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Crystallization
  • Deep Learning*
  • Molecular Dynamics Simulation*
  • Nuclear Energy
  • Protein Conformation, alpha-Helical
  • Protein Conformation, beta-Strand
  • Protein Structure, Tertiary
  • Proteins / chemistry*
  • Temperature*

Substances

  • Proteins

Grant support

This work was supported by the European Research Council (https://erc.europa.eu) Advanced Grant “ProCovar” (project ID 695558) awarded to DTJ. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.