metadata
license: mit
tags:
- DNA-methylation
- epigenetics
- foundation-model
- aging
- biology
CpGPT Model Checkpoints
Model weights, configurations, and vocabularies for CpGPT: A Foundation Model for DNA Methylation.
Contents
weights/ # PyTorch Lightning checkpoint files (.ckpt)
config/ # Hydra YAML configuration files
vocab/ # CpG vocabulary files (.json)
Pre-trained Models
| Model | Size | Parameters | Model Name |
|---|---|---|---|
| CpGPT-2M | 30MB | ~2.5M | small |
| CpGPT-100M | 1.1GB | ~101M | large |
Download
# Install huggingface_hub
pip install huggingface_hub
# Download all model files
huggingface-cli download lucascamillomd/cpgpt-models --local-dir dependencies/model
# Or download a specific model
huggingface-cli download lucascamillomd/cpgpt-models weights/small.ckpt config/small.yaml vocab/small.json --local-dir dependencies/model
Dependencies
You will also need the DNA embeddings for your species of interest:
- Human: lucascamillomd/cpgpt-human-dependencies
- Mammalian (multi-species): lucascamillomd/cpgpt-mammalian-dependencies
Usage
After downloading the model files and species dependencies, follow the tutorials at the CpGPT GitHub repository to get started.
Citation
@article{camillo2024cpgpt,
title={CpGPT: A Foundation Model for DNA Methylation},
author={de Lima Camillo, Lucas Paulo et al.},
journal={bioRxiv},
year={2024},
doi={10.1101/2024.10.24.619766}
}
License
MIT License — see the GitHub repository for details.