An open API service indexing awesome lists of open source software.

https://github.com/adosar/aidsorb

Python package for deep learning on molecular point clouds.
https://github.com/adosar/aidsorb

3d-deep-learning 3d-point-clouds deep-learning geometric-deep-learning machine-learning material-informatics metal-organic-frameworks point-clouds pytorch pytorch-lightning

Last synced: 8 months ago
JSON representation

Python package for deep learning on molecular point clouds.

Awesome Lists containing this project

README

          





AIdsorb logo




Static Badge
Static Badge
GitHub Actions Workflow Status
GitHub Actions Workflow Status
GitHub Actions Workflow Status

[![Docs](https://img.shields.io/badge/foo-stable-black?style=for-the-badge&logo=readthedocs&logoColor=cyan&label=ReadTheDocs&labelColor=black&color=purple)](https://aidsorb.readthedocs.io/en/stable/)
[![PyPI](https://img.shields.io/pypi/v/aidsorb?style=for-the-badge&logo=pypi&logoColor=cyan&labelColor=black&color=purple)](https://pypi.org/project/aidsorb/)
[![App](https://img.shields.io/badge/online%20app-purple?style=for-the-badge&logo=streamlit&logoSize=auto&logoColor=cyan&label=streamlit&labelColor=black)](https://aidsorb-online.streamlit.app)

**AIdsorb** is a Python package for **deep learning on molecular point clouds**.

This package aims to provide a **simple, easy-to-use and reproduce** interface for:

- 📥 **Creating molecular point clouds**

- 🤖 **Training DL algorithms on molecular point clouds**


IRMOF-1
Cu-BTC
UiO-66

## ⚙️ Installation
> [!IMPORTANT]
> It is strongly recommended to **perform the installation inside a virtual environment**.

Assuming an activated virtual environment:
```bash
pip install aidsorb
```

## 🚀 Usage
> [!NOTE]
> Refer to the 📚 [Documentation](https://aidsorb.readthedocs.io/en/stable/) for more information.

Here is a summary of what you can do from the command line:

1. Visualize a molecular point cloud:
```bash
aidsorb visualize path/to/structure
```

2. Create and prepare point clouds:
```bash
aidsorb create path/to/structures path/to/pcd_data # Create and store point clouds
aidsorb prepare path/to/pcd_data # Split point clouds to train, valdation and test
```

3. Train and test a model:
```bash
aidsorb-lit fit --config=path/to/config.yaml
aidsorb-lit test --config=path/to/config.yaml --ckpt_path=path/to/ckpt
```

## 💡 Contributing

🙌 We welcome contributions from the community to help improve and expand this
project!

You can start by 🛠️ [opening an issue](https://github.com/adosar/aidsorb/issues) for:

* 🐛 Reporting bugs
* 🌟 Suggesting new features
* 📚 Improving documentation
* 🎨 Adding your example to the [Gallery](https://aidsorb.readthedocs.io/en/stable/auto_examples/index.html)

We appreciate your efforts to submit well-documented 🔃 [pull
requests](https://github.com/adosar/aidsorb/pulls) and participate in
discussions.

💪 Together, we can make this project even better!

## 📑 Citing
* **To cite the software**, please refer to the [citation file](./CITATION.cff) or click the citation button.
* **To cite the paper**, please use the following BibTeX entry:

Show BibTex entry

```bibtex
@article{Sarikas2024,
title = {Gas adsorption meets geometric deep learning: points, set and match},
volume = {14},
ISSN = {2045-2322},
url = {http://dx.doi.org/10.1038/s41598-024-76319-8},
DOI = {10.1038/s41598-024-76319-8},
number = {1},
journal = {Scientific Reports},
publisher = {Springer Science and Business Media LLC},
author = {Sarikas, Antonios P. and Gkagkas, Konstantinos and Froudakis, George E.},
year = {2024},
month = nov
}
```

## ⚖️ License
**AIdosrb** is released under the [GNU General Public License v3.0 only](https://spdx.org/licenses/GPL-3.0-only.html).