This repository contains the code for the paper "Protein A-like Peptide Generation Based on a Generalized Diffusion Model". The core functionality is implemented in a Jupyter Notebook (GDM.ipynb).

Install the required dependencies to run the code:

• Python 3.8+
• PyTorch 1.10+
• NumPy
• pandas
• matplotlib
• Jupyter Notebook
• torchgeometry
• einops
• tqdm
• comet_ml (optional, for experiment tracking)

Install via pip:pip install torch numpy pandas matplotlib jupyter torchgeometry einops tqdm comet_ml

The main entry point is GDM.ipynb. Follow these steps:

1. Clone the repository:

   git clone <repository-url>
   cd ProteinGeneration-GeneralizedDiffusion

2. Launch Jupyter Notebook:

   jupyter notebook

3. Open GDM.ipynb and run all cells sequentially. This will:

   • Handle data loading and preprocessing
   • Initialize the diffusion model
   • Support training (from scratch) or loading pre-trained checkpoints
   • Generate Protein A-like peptides
   • Include basic evaluation and visualization of results

This project is licensed under the MIT License - see the LICENSE file for details.

If you use this code in your research, please cite our paper

For questions, please contact us or open an issue in the repository.