MethylGPT_clean

This is the official codebase for methylGPT : a foundation model for the DNA methylome.

    #   #   #

!UPDATE: [2025.02.10] methylGPT is now available on PyPI [2024.12.10] We made initial launching of the methylGPT codebase. [2025.11.04] Manuscript available on arXiv

Installation

Architecture Note : MethylGPT's backend architecture is largely based on scGPT, developed by the Wang Lab. As such, our project inherits and follows similar dependencies and architectural patterns. We acknowledge and thank the scGPT team for their foundational work.

methylGPT works with Python >= 3.9.10 and R >=3.6.1. Please make sure you have the correct version of Python and R installed pre-installation.

methylGPT is available on PyPI. To install methylGPT, run the following command:

pip install methylgpt "flash-attn<1.0.5"  # optional, recommended
# As of 2023.09, pip install may not run with new versions of the google orbax package, if you encounter related issues, please use the following command instead:
# pip install scgpt "flash-attn<1.0.5" "orbax<0.1.8"

[Optional] We recommend using wandb for logging and visualization.

pip install wandb

For developing, we are using the Poetry package manager. To install Poetry, follow the instructions here.

$ git clone this-repo-url
$ cd MethylGPT_clean
$ poetry install

Note: The flash-attn dependency usually requires specific GPU and CUDA version. If you encounter any issues, please refer to the flash-attn repository for installation instructions. For now, May 2023, we recommend using CUDA 11.7 and flash-attn<1.0.5 due to various issues reported about installing new versions of flash-attn.

Running pretraining

The primary pretraining code is implemented in methylgpt.pretraining.py. During training, model checkpoints are automatically saved to the save/ directory at the end of each epoch.

For a detailed walkthrough of the pretraining process, refer to our step-by-step examples in the pretraining tutorials.

(TODO) Pretrained methylGPT Model Zoo

Here is the list of pretrained models. Please find the links for downloading the checkpoint folders. We recommend using the whole-human model for most applications by default. If your fine-tuning dataset shares similar cell type context with the training data of the organ-specific models, these models can usually demonstrate competitive performance as well. A paired vocabulary file mapping gene names to ids is provided in each checkpoint folder. If ENSEMBL ids are needed, please find the conversion at gene_info.csv.

Fine-tune methylGPT for age prediction

Please see our example code in tutorials/finetuning_age_prediction. By default, the script assumes the scGPT checkpoint folder stored in the examples/save directory.

To-do-list

• Upload the pretrained model checkpoint
• Publish to pypi
• Provide the pretraining code with generative attention masking
• More tutorial examples for disease prediction
• Publish to huggingface model hub

Contributing

We greatly welcome contributions to methylGPT. Please submit a pull request if you have any ideas or bug fixes. We also welcome any issues you encounter while using scGPT.

Acknowledgements

We sincerely thank the authors of following open-source projects:

• flash-attention
• scanpy
• scvi-tools
• scib
• datasets
• transformers
• scGPT

Citing scGPT

@article{ying2024methylgpt,
  title={MethylGPT: a foundation model for the DNA methylome},
  author={Ying, Kejun and Song, Jinyeop and Cui, Haotian and Zhang, Yikun and Li, Siyuan and Chen, Xingyu and Liu, Hanna and Eames, Alec and McCartney, Daniel L and Marioni, Riccardo E and others},
  journal={bioRxiv},
  pages={2024--10},
  year={2024},
  publisher={Cold Spring Harbor Laboratory}
}