Metadata-Version: 2.4
Name: gnnepcsaft
Version: 0.5.2
Summary: The GNNPCSAFT Project focuses on using Graph Neural Networks to estimate the pure-component parameters of the Equation of State PC-SAFT
License-Expression: GPL-3.0-or-later
License-File: LICENSE
Keywords: pcsaft,graph-neural-network,gnn,equation-of-state,chemical-engineering,thermodynamics
Author: wildsonbbl
Author-email: wil_bbl@hotmail.com
Maintainer: wildsonbbl
Maintainer-email: wil_bbl@hotmail.com
Requires-Python: >=3.10
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Provides-Extra: dev
Requires-Dist: ConfigSpace ; extra == "dev"
Requires-Dist: PCSAFTsuperanc ; extra == "dev"
Requires-Dist: absl-py
Requires-Dist: feos (>=0.9.0,<0.10.0)
Requires-Dist: hpbandster ; extra == "dev"
Requires-Dist: ipywidgets ; extra == "dev"
Requires-Dist: jax ; extra == "dev"
Requires-Dist: lightning ; extra == "dev"
Requires-Dist: matplotlib ; extra == "dev"
Requires-Dist: matplotlib-venn ; extra == "dev"
Requires-Dist: ml_collections ; extra == "dev"
Requires-Dist: nbformat ; extra == "dev"
Requires-Dist: numpy (>=2.2.4,<3.0.0)
Requires-Dist: ogb ; extra == "dev"
Requires-Dist: onnx ; extra == "dev"
Requires-Dist: onnxruntime ; extra == "dev"
Requires-Dist: onnxscript ; extra == "dev"
Requires-Dist: plotly ; extra == "dev"
Requires-Dist: polars ; extra == "dev"
Requires-Dist: pylint ; extra == "dev"
Requires-Dist: pytest ; extra == "dev"
Requires-Dist: ray[train] ; extra == "dev"
Requires-Dist: ray[tune] ; extra == "dev"
Requires-Dist: rdkit (>=2024.9.6,<2025.0.0)
Requires-Dist: scipy ; extra == "dev"
Requires-Dist: seaborn ; extra == "dev"
Requires-Dist: si-units (>=0.11.0,<0.12.0)
Requires-Dist: teqp ; extra == "dev"
Requires-Dist: torch ; extra == "dev"
Requires-Dist: torch_geometric ; extra == "dev"
Requires-Dist: torchmetrics ; extra == "dev"
Requires-Dist: wandb (>=0.24.0) ; extra == "dev"
Requires-Dist: xgboost ; extra == "dev"
Project-URL: Issues, https://github.com/wildsonbbl/gnnepcsaft/issues
Project-URL: Repository, https://github.com/wildsonbbl/gnnepcsaft
Description-Content-Type: text/markdown

# GNNPCSAFT Project

[![DOI](https://zenodo.org/badge/609414994.svg)](https://doi.org/10.5281/zenodo.17371237)

The project focuses on using Graph Neural Networks ([GNN](https://en.wikipedia.org/wiki/Graph_neural_network)) to estimate the pure-component parameters of the Equation of State [PC-SAFT](https://en.wikipedia.org/wiki/PC-SAFT).

Currently, the model takes into account the hard-chain, dispersive, and associative terms of PC-SAFT. Future work on polar and ionic terms is being studied.

Use cases of this package are demonstrated in Jupyter Notebooks:

- `compare.ipynb` ([Open in Colab](https://colab.research.google.com/github/wildsonbbl/gnnepcsaft/blob/main/compare.ipynb)): comparison of the performance of trained models
- `training.ipynb` ([Open in Colab](https://colab.research.google.com/github/wildsonbbl/gnnepcsaft/blob/main/training.ipynb)): notebook for model training
- `tuning.ipynb` ([Open in Colab](https://colab.research.google.com/github/wildsonbbl/gnnepcsaft/blob/main/tuning.ipynb)): notebook for hyperparameter tuning

Model checkpoints can be found at [Hugging Face](https://huggingface.co/wildsonbbl/gnnepcsaft).

Implementations with GNNPCSAFT:

- [GNNPCSAFT CLI](https://github.com/wildsonbbl/gnnepcsaftcli)
- [GNNPCSAFT APP](https://github.com/wildsonbbl/gnnpcsaftapp)
- [GNNPCSAFT MCP](https://github.com/wildsonbbl/gnnepcsaft_mcp_server)
- [GNNPCSAFT Webapp](https://github.com/wildsonbbl/gnnepcsaftwebapp)
- [GNNPCSAFT Chat](https://github.com/wildsonbbl/gnnpcsaftchat)

