Doerr, Stefan, 1987-Majewski, MaciejPérez, AdriàKrämer, AndreasClementi, CeciliaNoé, FrankGiorgino, ToniDe Fabritiis, Gianni2022-01-252022-01-252021Doerr S, Majewski M, Pérez A, Krämer A, Clementi C, Noe F, Giorgino T, De Fabritiis G. TorchMD: a deep learning framework for molecular simulations. J Chem Theory Comput. 2021;17(4):2355-63. DOI: 10.1021/acs.jctc.0c013431549-9618http://hdl.handle.net/10230/52303Molecular 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 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 github.com/torchmd.application/pdfeng© 2021 American Chemical Society. This work is licensed under a Creative Commons Attribution 4.0 International Licenseinfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1021/acs.jctc.0c01343info:eu-repo/semantics/openAccess