TorchMD: A deep learning framework for molecular simulations

Abstract

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}.

References in corpus (11)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• SchNet - a deep learning architecture for molecules and materials
• Identification of slow molecular order parameters for Markov model construction
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• FCHL revisited: faster and more accurate quantum machine learning
• Coarse Graining Molecular Dynamics with Graph Neural Networks
• Coarse-Graining Auto-Encoders for Molecular Dynamics
• Variational Selection of Features for Molecular Kinetics
• Temperature-transferable coarse-graining of ionic liquids with dual graph convolutional neural networks
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
• Coarse-graining Molecular Systems by Spectral Matching

Cited by in corpus (34)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Machine Learning Coarse-Grained Potentials of Protein Thermodynamics
• Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
• DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Graph Neural Networks Accelerated Molecular Dynamics
• TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations
• Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
• Deep Coarse-grained Potentials via Relative Entropy Minimization
• Accurate machine learning force fields via experimental and simulation data fusion
• Learning Pair Potentials using Differentiable Simulations
• From Static to Dynamic Structures: Improving Binding Affinity Prediction with Graph-Based Deep Learning
• On the design space between molecular mechanics and machine learning force fields
• Innate Dynamics and Identity Crisis of a Metal Surface Unveiled by Machine Learning of Atomic Environments
• chemtrain: Learning Deep Potential Models via Automatic Differentiation and Statistical Physics
• Automatic Differentiation for Orbital-Free Density Functional Theory
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Implicit Solvent Approach Based on Generalised Born and Transferable Graph Neural Networks for Molecular Dynamics Simulations
• Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks
• Differentiable Matrix Elements with MadJax
• Modeling lens potentials with continuous neural fields in galaxy-scale strong lenses
• AMARO: All Heavy-Atom Transferable Neural Network Potentials of Protein Thermodynamics
• Building Robust Machine Learning Models for Small Chemical Science Data: The Case of Shear Viscosity
• ImmunoLingo: Linguistics-based formalization of the antibody language
• The Enduring Relevance of Semiempirical Quantum Mechanics
• Fast, Modular, and Differentiable Framework for Machine Learning-Enhanced Molecular Simulations
• A Bond-Based Machine Learning Model for Molecular Polarizabilities and A Priori Raman Spectra
• Self-Tuning Hamiltonian Monte Carlo for Accelerated Sampling
• Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentials
• Differentiable Rotamer Sampling with Molecular Force Fields
• Theory of Moment Propagation for Quantum Dynamics in Single-Particle Description
• Large Language Models as AI Agents for Digital Atoms and Molecules: Catalyzing a New Era in Computational Biophysics
• Differentiable hybrid force fields support scalable autonomous electrolyte discovery
• Towards Conditional Generation of Minimal Action Potential Pathways for Molecular Dynamics