STRUCTURES25 Documentation
Welcome to the documentation for STRUCTURES25! This package enables Orbital-Free Density Functional Theory (OF-DFT) calculations by learning the kinetic energy functional from data using equivariant graph neural networks. For installation instructions, see the Installation Guide. To get familiar with the workflow, head to the Usage Guide. The code is available on GitHub.
The code is based on our publication Stable and Accurate Orbital-Free Density Functional Theory Powered by Machine Learning. To cite STRUCTURES25 in your work, please use the following BibTeX entry:
@article{Remme_Stable_and_Accurate_2025,
author = {Remme, Roman and Kaczun, Tobias and Ebert, Tim and Gehrig, Christof A. and
Geng, Dominik and Gerhartz, Gerrit and Ickler, Marc K. and Klockow, Manuel V. and
Lippmann, Peter and Schmidt, Johannes S. and Wagner, Simon and Dreuw, Andreas and
Hamprecht, Fred A.},
title = {Stable and Accurate Orbital-Free Density Functional Theory Powered by Machine Learning},
journal = {Journal of the American Chemical Society},
year = {2025},
volume = {147},
number = {32},
pages = {28851--28859},
doi = {10.1021/jacs.5c06219},
url = {https://doi.org/10.1021/jacs.5c06219}
}
Guides
References
Zhang, H.; Liu, S.; You, J.; Liu, C.; Zheng, S.; Lu, Z.; Wang, T.; Zheng, N.; Shao, B.: “Overcoming the barrier of orbital-free density functional theory for molecular systems using deep learning.” Nat Comput Sci 4, 210–223 (2024). https://doi.org/10.1038/s43588-024-00605-8
Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, Tie-Yan Liu: “Do Transformers really perform badly for graph representation?”. Advances in Neural Information Processing Systems, 34:28877–28888, 2021.