TorchMD: A deep learning framework for molecular simulations
This framework provides a useful tool-set for researchers in molecular simulations to leverage machine learning potentials, potentially improving the quality and transferability of empirical potentials.
This paper introduces TorchMD, a deep learning framework that integrates classical and machine learning potentials for molecular simulations. It allows all force computations to be expressed as PyTorch operations, enabling the learning and simulation of neural network potentials, validated through various simulations including ab-initio and coarse-grained protein folding models.
Molecular dynamics simulations provide a mechanistic description of molecules by relying on empirical potentials. The quality and transferability of such potentials can be improved leveraging data-driven models derived with machine learning approaches. Here, we present TorchMD, a framework for molecular simulations with mixed classical and machine learning potentials. All of force computations including bond, angle, dihedral, Lennard-Jones and Coulomb interactions are expressed as PyTorch arrays and operations. Moreover, TorchMD enables learning and simulating neural network potentials. We validate it using standard Amber all-atom simulations, learning an ab-initio potential, performing an end-to-end training and finally learning and simulating a coarse-grained model for protein folding. We believe that TorchMD provides a useful tool-set to support molecular simulations of machine learning potentials. Code and data are freely available at \url{github.com/torchmd}.