Skip to main content

DeePMD-kit plugin for graph neural network models.

Project description

DeePMD-kit plugin for various graph neural network models

deepmd-gnn is a DeePMD-kit plugin for various graph neural network (GNN) models, which connects DeePMD-kit and atomistic GNN packages by enabling GNN models in DeePMD-kit.

Supported packages and models include:

After installing the plugin, you can train the GNN models using DeePMD-kit, run active learning cycles for the GNN models using DP-GEN, perform simulations with the MACE model using molecular dynamic packages supported by DeePMD-kit, such as LAMMPS and AMBER. You can follow DeePMD-kit documentation to train the GNN models using its PyTorch backend, after using the specific model parameters.

Credits

If you use this software, please cite the following unpublish paper:

  • Jinzhe Zeng, Timothy J. Giese, Duo Zhang, Han Wang, Darrin M. York, DeePMD-GNN: A DeePMD-kit Plugin for External Graph Neural Network Potentials, unpublished.

We will update the credit information once it is published.

Installation

First, clone this repository:

git clone https://gitlab.com/RutgersLBSR/deepmd-gnn
cd deepmd-gnn

Python interface plugin

Python 3.9 or above is required. A C++ compiler that supports C++ 14 (for PyTorch 2.0) or C++ 17 (for PyTorch 2.1 or above) is required.

Assume you have installed DeePMD-kit (v3.0.0b2 or above) and PyTorch in an environment, then execute

# expose PyTorch CMake modules
export CMAKE_PREFIX_PATH=$(python -c "import torch;print(torch.utils.cmake_prefix_path)")

pip install .

C++ interface plugin

DeePMD-kit version should be v3.0.0b4 or later.

Follow DeePMD-kit documentation to install DeePMD-kit C++ interface with PyTorch backend support and other related MD packages. After that, you can build the plugin

# Assume libtorch has been contained in CMAKE_PREFIX_PATH
mkdir -p build
cd build
cmake .. -D CMAKE_INSTALL_PREFIX=/prefix/to/install
cmake --build . -j8
cmake --install .

libdeepmd_gnn.so will be installed into the directory you assign. When using any DeePMD-kit C++ interface, set the following environment variable in advance:

export DP_PLUGIN_PATH=/prefix/to/install/lib/libdeepmd_gnn.so

Usage

Follow Parameters section to prepare a DeePMD-kit input file.

dp --pt train input.json
dp --pt freeze

A frozen model file named frozen_model.pth will be generated. You can use it in the MD packages or other interfaces. For details, follow DeePMD-kit documentation.

Running LAMMPS + MACE with period boundary conditions

GNN models use message passing neural networks, so the neighbor list built with traditional cutoff radius will not work, since the ghost atoms also need to build neighbor list. By default, the model requests the neighbor list with a cutoff radius of $r_c \times N_{L}$, where $r_c$ is set by r_max and $N_L$ is set by num_interactions (MACE) / num_layers (NequIP), and rebuilds the neighbor list for ghost atoms. However, this approach is very inefficient.

The alternative approach for the MACE model (note: NequIP doesn't support such approach) is to use the mapping passed from LAMMPS, which does not support MPI. One needs to set DP_GNN_USE_MAPPING when freezing the models,

DP_GNN_USE_MAPPING=1 dp --pt freeze

and request the mapping when using LAMMPS (also requires DeePMD-kit v3.0.0rc0 or above). By using the mapping, the ghost atoms will be mapped to the real atoms, so the regular neighbor list with a cutoff radius of $r_c$ can be used.

atom_modify map array

In the future, we will explore utilizing the MPI to communicate the neighbor list, while this approach requires a deep hack for external packages.

Parameters

MACE

To use the MACE model, set "type": "mace" in the model section of the training script. Below is default values for the MACE model, most of which follows default values in the MACE package:

"model": {
  "type": "mace",
  "type_map": [
    "O",
    "H"
  ],
  "r_max": 5.0,
  "sel": "auto",
  "num_radial_basis": 8,
  "num_cutoff_basis": 5,
  "max_ell": 3,
  "interaction": "RealAgnosticResidualInteractionBlock",
  "num_interactions": 2,
  "hidden_irreps": "128x0e + 128x1o",
  "pair_repulsion": false,
  "distance_transform": "None",
  "correlation": 3,
  "gate": "silu",
  "MLP_irreps": "16x0e",
  "radial_type": "bessel",
  "radial_MLP": [64, 64, 64],
  "std": 1.0,
  "precision": "float32"
}

NequIP

"model": {
  "type": "nequip",
  "type_map": [
    "O",
    "H"
  ],
  "r_max": 5.0,
  "sel": "auto",
  "num_layers": 4,
  "l_max": 2,
  "num_features": 32,
  "nonlinearity_type": "gate",
  "parity": true,
  "num_basis": 8,
  "BesselBasis_trainable": true,
  "PolynomialCutoff_p": 6,
  "invariant_layers": 2,
  "invariant_neurons": 64,
  "use_sc": true,
  "irreps_edge_sh": "0e + 1e",
  "feature_irreps_hidden": "32x0o + 32x0e + 32x1o + 32x1e",
  "chemical_embedding_irreps_out": "32x0e",
  "conv_to_output_hidden_irreps_out": "16x0e",
  "precision": "float32"
}

DPRc support

In deepmd-gnn, the GNN model can be used in a DPRc way. Type maps that starts with m (such as mH) or OW or HW will be recognized as MM types. Two MM atoms will not build edges with each other. Such GNN+DPRc model can be directly used in AmberTools24.

Examples

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

deepmd_gnn-0.1.1.tar.gz (2.1 MB view details)

Uploaded Source

Built Distributions

deepmd_gnn-0.1.1-py2.py3-none-win_amd64.whl (73.0 kB view details)

Uploaded Python 2 Python 3 Windows x86-64

deepmd_gnn-0.1.1-py2.py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl (48.1 kB view details)

Uploaded Python 2 Python 3 manylinux: glibc 2.17+ x86-64 manylinux: glibc 2.28+ x86-64

deepmd_gnn-0.1.1-py2.py3-none-macosx_11_0_arm64.whl (47.0 kB view details)

Uploaded Python 2 Python 3 macOS 11.0+ ARM64

deepmd_gnn-0.1.1-py2.py3-none-macosx_10_13_x86_64.whl (47.5 kB view details)

Uploaded Python 2 Python 3 macOS 10.13+ x86-64

File details

Details for the file deepmd_gnn-0.1.1.tar.gz.

File metadata

  • Download URL: deepmd_gnn-0.1.1.tar.gz
  • Upload date:
  • Size: 2.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for deepmd_gnn-0.1.1.tar.gz
Algorithm Hash digest
SHA256 6772f1a6a9adcbfbfb63676c9aec19251eb9544ab95819243868eee1e2165821
MD5 5397dbb3e4aa46de8aa83c0cd411396a
BLAKE2b-256 ab82de0e56536370d7b1a7e9e5a9b2e3a30d8d36c30f0675dc41ce8d7a38b9e2

See more details on using hashes here.

Provenance

The following attestation bundles were made for deepmd_gnn-0.1.1.tar.gz:

Publisher: release.yaml on deepmodeling/deepmd-gnn

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file deepmd_gnn-0.1.1-py2.py3-none-win_amd64.whl.

File metadata

File hashes

Hashes for deepmd_gnn-0.1.1-py2.py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 443f8511eb5ca8e704ffc9b4dfd2cf1a07c462e82ad9b1b3033a5d77583d4df3
MD5 2fa0e40f73a4b7916bb5d27fbaf7a924
BLAKE2b-256 515341fbf7fc8a0878e803ee2d15f4e35ef36f068a62c88361d2f72fad28c09a

See more details on using hashes here.

Provenance

The following attestation bundles were made for deepmd_gnn-0.1.1-py2.py3-none-win_amd64.whl:

Publisher: release.yaml on deepmodeling/deepmd-gnn

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file deepmd_gnn-0.1.1-py2.py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for deepmd_gnn-0.1.1-py2.py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 5174ce97ccf32570d1c59a412130a91234f42db1282f43e09d7366f2ed6e4b44
MD5 96f45974931a331bd9ed79f5fed31279
BLAKE2b-256 de1540030113b05503d2ad728e4fb84ba7eda2f1b72ba60ef8702e3b7e383f57

See more details on using hashes here.

Provenance

The following attestation bundles were made for deepmd_gnn-0.1.1-py2.py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl:

Publisher: release.yaml on deepmodeling/deepmd-gnn

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file deepmd_gnn-0.1.1-py2.py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for deepmd_gnn-0.1.1-py2.py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 3e59179c3b5b6841f79e22971286e9418e1824fc5f98d2af150cea23ac356261
MD5 c174e9ef89cb6f3da65c78212578b94e
BLAKE2b-256 336cf61a06f4203098cf890ef8d54d02d7d180e0d4537c7d298a838ed49a2b27

See more details on using hashes here.

Provenance

The following attestation bundles were made for deepmd_gnn-0.1.1-py2.py3-none-macosx_11_0_arm64.whl:

Publisher: release.yaml on deepmodeling/deepmd-gnn

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file deepmd_gnn-0.1.1-py2.py3-none-macosx_10_13_x86_64.whl.

File metadata

File hashes

Hashes for deepmd_gnn-0.1.1-py2.py3-none-macosx_10_13_x86_64.whl
Algorithm Hash digest
SHA256 6b6b977d2127601eec1e2b480810da22a143f25d1f8710d925afc41c16205386
MD5 ba77919e4da86793b31fcbcb8792b1ba
BLAKE2b-256 37cd69803b6026b8b7036de48bf42fa2790cd38d6c5504d09c4e43f5507c2df8

See more details on using hashes here.

Provenance

The following attestation bundles were made for deepmd_gnn-0.1.1-py2.py3-none-macosx_10_13_x86_64.whl:

Publisher: release.yaml on deepmodeling/deepmd-gnn

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page