almo-eda 0.2.0

Machine learning models for ALMO-EDA energy prediction

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
└── almo_eda
    ├── __init__.py
    ├── data_loader.py
    ├── logger.py
    ├── network.py
    ├── utils.py
    ├── visualization.py
    ├── optimization.py
    └── trainer.py

Installation

python -m pip install -e ".[dev]"

or

python -m pip install -r requirements.txt

Run examples

1. Place your data in the /data folder.

2. Run the training: 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 
}