mlsanityData to 7 Oct 2026

chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulations

arXiv 2506.04055 ↗First posted 4 Jun 2025physics.comp-ph cs.LG physics.chem-phcited by 6

Not on the map. Why?

Abstract (arXiv)

Machine learning potentials (MLPs) have advanced rapidly and show great promise to transform molecular dynamics (MD) simulations. However, most existing software tools are tied to specific MLP architectures, lack integration with standard MD packages, or are not parallelizable across GPUs. To address these challenges, we present chemtrain-deploy, a framework that enables model-agnostic deployment of MLPs in LAMMPS. chemtrain-deploy supports any JAX-defined semi-local potential, allowing users to exploit the functionality of LAMMPS and perform large-scale MLP-based MD simulations on multiple GPUs. It achieves state-of-the-art efficiency and scales to systems containing millions of atoms. We validate its performance and scalability using graph neural network architectures, including MACE, Allegro, and PaiNN, applied to a variety of systems, such as liquid-vapor interfaces, crystalline materials, and solvated peptides. Our results highlight the practical utility of chemtrain-deploy for real-world, high-performance simulations and provide guidance for MLP architecture selection and future design.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 30 of its 78 references that are in the map. First posted on arXiv 4 Jun 2025.

Builds on

30 of 78 references.

References · 30

  1. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  2. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
  3. 2020Directional Message Passing for Molecular Graphscited by 556
  4. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  5. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  6. 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 254
  7. 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 254
  8. 2017Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanicscited by 213
  9. 2020Machine Learning Force Fieldscited by 204
  10. 2019Machine learning for molecular simulationcited by 109
  11. 2022The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentialscited by 100
  12. 2022Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulationscited by 92
18 more
  1. 2022SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentialscited by 80
  2. 2017DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamicscited by 79
  3. 2025Learning Smooth and Expressive Interatomic Potentials for Physical Property Predictioncited by 79
  4. 2018Machine Learning of coarse-grained Molecular Dynamics Force Fieldscited by 68
  5. 2020TorchMD: A deep learning framework for molecular simulationscited by 55
  6. 2023Ewald-based Long-Range Message Passing for Molecular Graphscited by 46
  7. 2023Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic sizecited by 33
  8. 2021Learning neural network potentials from experimental data via Differentiable Trajectory Reweightingcited by 26
  9. 2024Latent Ewald summation for machine learning of long-range interactionscited by 26
  10. 202086 PFLOPS Deep Potential Molecular Dynamics simulation of 100 million atoms with ab initio accuracycited by 15
  11. 2024chemtrain: Learning Deep Potential Models via Automatic Differentiation and Statistical Physicscited by 12
  12. 2024Euclidean Fast Attention -- Machine Learning Global Atomic Representations at Linear Costcited by 12
  13. 2020Automated discovery of a robust interatomic potential for aluminumcited by 11
  14. 2023Uncertainty Estimation for Molecules: Desiderata and Methodscited by 11
  15. 2024Predicting solvation free energies with an implicit solvent machine learning potentialcited by 10
  16. 2024Stability-Aware Training of Machine Learning Force Fields with Differentiable Boltzmann Estimatorscited by 8
  17. 2025Learning Non-Local Molecular Interactions via Equivariant Local Representations and Charge Equilibrationcited by 5
  18. 2025DistMLIP: A Distributed Inference Platform for Machine Learning Interatomic Potentialscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025Enhanced Sampling for Efficient Learning of Coarse-Grained Machine Learning Potentialscited by 3
  2. 2025Refining Machine Learning Potentials through Thermodynamic Theory of Phase Transitionscited by 1
  3. 2025Facet: highly efficient E(3)-equivariant networks for interatomic potentialscited by 0
  4. 2026Coarse-Grained Boltzmann Generatorscited by 0
  5. 2026Making Room for AI: Multi-GPU Molecular Dynamics with Deep Potentials in GROMACScited by 0
  6. 2026Transferable Implicit Solvent Machine Learning Potential for Drugs and Proteins Approaching Ab Initio Accuracycited by 0