DeePMD-GNN: A DeePMD-kit Plugin for External Graph Neural Network Potentials

Machine learning potentials (MLPs) have revolutionized molecular simulation by providing efficient and accurate models for predicting atomic interactions. MLPs continue to advance and have had profound impact in applications that include drug discovery, enzyme catalysis, and materials design. The current landscape of MLP software presents challenges due to the limited interoperability between packages, which can lead to inconsistent benchmarking practices and necessitates separate interfaces with molecular dynamics (MD) software. To address these issues, we present DeePMD-GNN, a plugin for the DeePMD-kit framework that extends its capabilities to support external graph neural network (GNN) potentials.DeePMD-GNN enables the seamless integration of popular GNN-based models, such as NequIP and MACE, within the DeePMD-kit ecosystem. Furthermore, the new software infrastructure allows GNN models to be used within combined quantum mechanical/molecular mechanical (QM/MM) applications using the range corrected ΔMLP formalism.We demonstrate the application of DeePMD-GNN by performing benchmark calculations of NequIP, MACE, and DPA-2 models developed under consistent training conditions to ensure fair comparison.

• Publication year

  2025

• Venue

  Journal of Chemical Information and Modeling

• Publication date

  2025-03-27

• Fields of study

  Chemistry, Medicine, Materials Science, Computer Science

• Identifiers
  DOI 10.1021/acs.jcim.4c02441PMID 40150804PMCID 12030209
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• The QDπ dataset, training data for drug-like molecules and biopolymer fragments and their interactions

  2025cited by this paper
• Software Infrastructure for Next-Generation QM/MM-ΔMLP Force Fields.

  2024cited by this paper
• Amber free energy tools: Interoperable software for free energy simulations using generalized quantum mechanical/molecular mechanical and machine learning potentials.

  2024cited by this paper
• Deep Learning Potential Assisted Prediction of Local Structure and Thermophysical Properties of the SrCl2-KCl-MgCl2 Melt.

  2024cited by this paper
• i-PI 3.0: A flexible and efficient framework for advanced atomistic simulations.

  2024cited by this paper
• The Role of General Acid Catalysis in the Mechanism of an Alkyl Transferase Ribozyme

  2024cited by this paper
• Electronic and Nuclear Quantum Effects on Proton Transfer Reactions of Guanine–Thymine (G-T) Mispairs Using Combined Quantum Mechanical/Molecular Mechanical and Machine Learning Potentials

  2024cited by this paper
• DeePMD-kit v2: A software package for deep potential models

  2023cited by this paper
• A "short blanket" dilemma for a state-of-the-art neural network potential for water: Reproducing experimental properties or the physics of the underlying many-body interactions?

  2023cited by this paper
• Modern semiempirical electronic structure methods and machine learning potentials for drug discovery: Conformers, tautomers, and protonation states.

  2023cited by this paper
• QDπ: A Quantum Deep Potential Interaction Model for Drug Discovery.

  2023cited by this paper
• OpenMM 8: Molecular Dynamics Simulation with Machine Learning Potentials.

  2023cited by this paper
• DPA-2: a large atomic model as a multi-task learner

  2023cited by this paper
• MLatom 3: A Platform for Machine Learning-Enhanced Computational Chemistry Simulations and Workflows

  2023cited by this paper
• AmberTools

  2023cited by this paper
• Modern Alchemical Free Energy Methods for Drug Discovery Explained

  2023cited by this paper
• Combined QM/MM, Machine Learning Path Integral Approach to Compute Free Energy Profiles and Kinetic Isotope Effects in RNA Cleavage Reactions.

  2022cited by this paper
• Pretraining of attention-based deep learning potential model for molecular simulation

  2022cited by this paper
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning.

  2022cited by this paper
• Multireference Generalization of the Weighted Thermodynamic Perturbation Method.

  2022cited by this paper
• SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials

  2022cited by this paper
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations.

  2022cited by this paper
• REANN: A PyTorch-based end-to-end multi-functional deep neural network package for molecular, reactive, and periodic systems.

  2021cited by this paper
• E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials

  2021cited by this paper
• LAMMPS implementation of rapid artificial neural network derived interatomic potentials

  2021cited by this paper
• Development of Range-Corrected Deep Learning Potentials for Fast, Accurate Quantum Mechanical/Molecular Mechanical Simulations of Chemical Reactions in Solution.

  2021cited by this paper
• MLatom 2: An Integrative Platform for Atomistic Machine Learning

  2021cited by this paper
• AENET-LAMMPS and AENET-TINKER: Interfaces for accurate and efficient molecular dynamics simulations with machine learning potentials.

  2021cited by this paper
• Choosing the right molecular machine learning potential

  2021cited by this paper
• LAMMPS - A flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales

  2021cited by this paper
• TorchANI: A Free and Open Source PyTorch-Based Deep Learning Implementation of the ANI Neural Network Potentials

  2020cited by this paper
• Neural Network Potential Energy Surfaces for Small Molecules and Reactions.

  2020cited by this paper
• Extending the applicability of the ANI deep learning molecular potential to Sulfur and Halogens.

  2020cited by this paper
• Extended tight‐binding quantum chemistry methods

  2020cited by this paper
• CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations.

  2020cited by this paper
• PyXtal_FF: a python library for automated force field generation

  2020cited by this paper
• The MLIP package: moment tensor potentials with MPI and active learning

  2020cited by this paper
• The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules

  2019cited by this paper
• Machine learning for molecular simulation

  2019cited by this paper
• DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models

  2019cited by this paper
• SIMPLE-NN: An efficient package for training and executing neural-network interatomic potentials

  2019cited by this paper
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments, and Partial Charges.

  2019cited by this paper
• Library-Based LAMMPS Implementation of High-Dimensional Neural Network Potentials.

  2019cited by this paper
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems.

  2018cited by this paper
• Machine learning for molecular and materials science

  2018cited by this paper
• sGDML: Constructing accurate and data efficient molecular force fields using machine learning

  2018cited by this paper
• GFN2-xTB-An Accurate and Broadly Parametrized Self-Consistent Tight-Binding Quantum Chemical Method with Multipole Electrostatics and Density-Dependent Dispersion Contributions.

  2018cited by this paper
• The atomic simulation environment-a Python library for working with atoms.

  2017cited by this paper
• SchNet - A deep learning architecture for molecules and materials.

  2017cited by this paper
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics

  2017cited by this paper
• Perspective: Machine learning potentials for atomistic simulations.

  2016cited by this paper
• ωB97M-V: A combinatorially optimized, range-separated hybrid, meta-GGA density functional with VV10 nonlocal correlation.

  2016cited by this paper
• ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost

  2016cited by this paper
• Large-scale ab initio simulations based on systematically improvable atomic basis

  2015cited by this paper
• GROMACS: High performance molecular simulations through multi-level parallelism from laptops to supercomputers

  2015cited by this paper
• Density-functional expansion methods: grand challenges

  2012cited by this paper
• Extended polarization in third-order SCC-DFTB from chemical-potential equalization.

  2012cited by this paper
• Virtual exploration of the small-molecule chemical universe below 160 Daltons.

  2005cited by this paper
• Improvement of semiempirical response properties with charge-dependent response density.

  2005cited by this paper

• DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials.

  2025cites this paper
• EMFF-2025: a general neural network potential for energetic materials with C, H, N, and O elements

  2025cites this paper
• Are Foundational Atomistic Models Reliable for Finite-Temperature Molecular Dynamics?

  2025cites this paper
• FE-ToolKit: A Versatile Software Suite for Analysis of High-Dimensional Free Energy Surfaces and Alchemical Free Energy Networks

  2025cites this paper
• Ứng dụng mô hình máy học trong mô phỏng vật liệu bằng Python trên Google Colab

  2025cites this paper
• Transferability of MACE Graph Neural Network for Range Corrected Δ‑Machine Learning Potential QM/MM Applications

  2025cites this paper
• chemtrain-deploy: A Parallel and Scalable Framework for Machine Learning Potentials in Million-Atom MD Simulations

  2025cites this paper
• Accelerating Data Set Population for Training Machine Learning Potentials with Automated System Generation and Strategic Sampling

  2025cites this paper
• Toward understanding whole enzymatic reaction cycles using multi-scale molecular simulations.

  2025cites this paper
• Efficient Deep Learning Rhodium Potential and Feasibility Validation in Large-Scale Molecular Dynamics Simulations

  2025cites this paper
• Molecular dynamics simulations of proteins: an in-depth review of computational strategies, structural insights, and their role in medicinal chemistry and drug development

  2025cites this paper
• Strategies for the drug development of cancer therapeutics

  2025cites this paper
• dpdata: A Scalable Python Toolkit for Atomistic Machine Learning Data Sets

  2025cites this paper
• OMetaNet: an efficient hybrid deep learning model based on multimodal data fusion and contrastive learning for predicting 2ʹ-O-methylation sites in human RNA

  2025cites this paper
• Machine learning interatomic potentials in biomolecular modeling: principles, architectures, and applications

  2025cites this paper