OpenPharmaco: Open-source Protein-based Pharmacophore Modeling Software

Open-Source software for Fully-automated Protein-based Pharmacophore Modeling and High-throughput Virtual Screening.

OpenPharmaco is currently powered by PharmacoNet: Accelerating Large-Scale Virtual Screening by Deep Pharmacophore Modeling, developed by Seonghwan Seo, KAIST.

If you are deep learning researcher, please visit PharmacoNet [github]. It provides more functions.

If you have any problems or need help, please add an github issue.

You can get more information at Wiki.

* Tested on Microsoft Window and Mac OS X (Apple Silicon).

Quick Start

# Download Source Codes
git clone https://github.com/SeonghwanSeo/OpenPharmaco.git

# Create Environment
cd OpenPharmaco/
conda env create -f environment.yml
conda activate openph
pip install .

# Start
conda activate openph
openph # or openpharmaco

Citation

Paper on arxiv

@article{seo2023pharmaconet,
  title = {PharmacoNet: Accelerating Large-Scale Virtual Screening by Deep Pharmacophore Modeling},
  author = {Seo, Seonghwan and Kim, Woo Youn},
  journal = {arXiv preprint arXiv:2310.00681},
  year = {2023},
  url = {https://arxiv.org/abs/2310.00681},
}

Future Plan

• Version 2.0.0
  • Performance Improvement (Provisional: PharmacoNet v2)
  • SMILES Input (Conformer-free inference)
• Verison 2.1.0:
  • Binding Site Detection for Apo Protein Structures
  • Pharmacophore Customizing
• Version 3
  • Binding Pose Prediction

Reference

• PyTorch
• NumPy
• Biopython
• Open Babel
• Open-Source PyMOL (github)
• PyQt5