ALMO EDA
This repository contains a PyTorch-based neural network designed to predict electron delocalization energies of water molecules. By leveraging chemical descriptors (SOAP) as inputs, the model bypasses computationally expensive DFT calculations to provide rapid estimates of delocalization energies.
📂 Project Structure
.
├── README.md
├── requirements.txt
├── requirements-dev.txt
├── .gitignore
├── LICENSE
├── pyproject.toml
│
├── configs
│ ├── mof_config.yaml
│ ├── inference_config.yaml
│ └── train_config.yaml
├── data
│ └── soap_descriptor.py
├── models
│ └── best_model_donor.pt
├── examples
│ ├── run_mof.py
│ ├── run_inference.py
│ ├── run_optuna.py
│ └── run_training.py
├── tests
│ ├── test_dataset.py
│ ├── test_loss.py
│ ├── test_network.py
│ └── test_training_smoke.py
└── almo_eda
├── __init__.py
├── data_loader.py
├── logger.py
├── network.py
├── utils.py
├── visualization.py
├── optimization.py
└── trainer.py
Installation
git clone https://github.com/htahmasbi/ALMO_EDA.git
python -m pip install -e ".[dev]"
or
python -m pip install -r requirements.txt
Data Description
- Inputs: Descriptors derived from Cartesian ($XYZ$) coordinates of water molecules, capturing local geometric orientations.
- Target: Electron Delocalization Energy ($E$), calculated via the ALMO-EDA scheme implemented in CP2K.
Run examples
- Place your data in the
/datafolder. - Modify and run the example scripts:
python examples/run_training.py
Citation
If you publish work that uses or mentions this code, please cite the following paper:
@article{Tahmasbi2025,
title = {Scalable machine learning model for energy decomposition analysis in aqueous systems},
volume = {163},
ISSN = {1089-7690},
url = {http://dx.doi.org/10.1063/5.0303825},
DOI = {10.1063/5.0303825},
number = {21},
journal = {The Journal of Chemical Physics},
publisher = {AIP Publishing},
author = {Tahmasbi, Hossein and Beerbaum, Michael and Brzoza, Bartosz and Cangi, Attila and K\"{u}hne, Thomas D.},
year = {2025},
pages = {214115},
month = dec
}
Metadata
Release files for almo-eda 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| almo_eda-0.2.1.tar.gz | 13.5 kB | With provenance | Details for almo_eda-0.2.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| almo_eda-0.2.1-py3-none-any.whl | Python 3 | none | any | Details for almo_eda-0.2.1-py3-none-any.whl |
Total release size: 26.4 kB
Release files / almo_eda-0.2.1.tar.gz
| Download URL | almo_eda-0.2.1.tar.gz |
|---|---|
| Size | 13.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9f720b5171278eee8a295aae551a65d10948126d835375be8761f7f2ba9952ce
|
|
BLAKE2b-256 checksum How to use checksums |
22cc63336bc7c8c3e9ff56174af0716397e54d6dc258d8855c051d22f16cd095
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 28, 2026.
Transparency logRelease files / almo_eda-0.2.1-py3-none-any.whl
| Download URL | almo_eda-0.2.1-py3-none-any.whl |
|---|---|
| Size | 12.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b73d15ef675c315c64cffebb140c002a8c269353109ca940eb4e8cb481f11b66
|
|
BLAKE2b-256 checksum How to use checksums |
ff907cd25171f3f0f85af77bc6fccfa726ebe143dd17d593fd8a8d181d3e610e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 28, 2026.
Transparency logSecurity for almo-eda 0.2.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for almo_eda-0.2.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 28, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.