https://github.com/theislab/ssl_in_scg

https://github.com/theislab/ssl_in_scg

Last synced: 10 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/theislab/ssl_in_scg
• Owner: theislab
• License: mit
• Created: 2024-01-26T12:38:27.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2024-08-22T08:59:50.000Z (almost 2 years ago)
• Last Synced: 2025-03-22T09:28:44.366Z (over 1 year ago)
• Language: Jupyter Notebook
• Size: 6.93 MB
• Stars: 12
• Watchers: 1
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.rst
  • License: LICENSE

Awesome Lists containing this project

README

          
Delineating the Effective Use of Self-Supervised Learning in Single-Cell Genomics

=================================================================================

Repository for the `paper `_.

System Requirements

-------------------

- Python 3.10

- Dependencies listed in `requirements.txt`

Installation Guide

-------------------

1. Create a conda environment:

   .. code-block:: bash

       conda env create -f environment.yml

2. Activate the environment:

   .. code-block:: bash

       conda activate ssl

3. Install the package in development mode:

   .. code-block:: bash

       cd directory_where_you_have_your_git_repos/ssl_in_scg

       pip install -e .

4. Create symlink to the storage folder for experiments:

   .. code-block:: bash

       cd directory_where_you_have_your_git_repos/ssl_in_scg

       ln -s folder_for_experiment_storage project_folder

Demo

----

**Large Dataset:**

For large datasets, use the store-creation notebooks in the `scTab repository `_ to create a Merlin datamodule for efficient data loading.

**Small Dataset or Single Adata Object:**

For small datasets or a single Adata object, a simple PyTorch dataloader suffices. Refer to our `multiomics application `_. A minimal example for masked pre-training of a smaller adata object is available in `sc_mae `_.

**Expected output:**

Running the models will generate a checkpoint file with trained model parameters, saved using PyTorch Lightning's checkpointing functionality. This file can be used for inference, further training, or reproducibility.

**Expected run time:**

We pre-trained on a single GPU for approximately 1-2 days and fine-tuned on a single GPU about 12-24 hours. This depends, among others, on the underlying architecture, dataset, and hyperparameters. So, convergence should be watched.

Model checkpoints

-----------------

Pre-trained model checkpoints are available on `Hugging Face `_.

Retraining

----------

Obtain the dataset from the `scTab repository `_ or write a Merlin store on your custom data. Then change `DATA_DIR` in `paths.py` to your custom dataset or keep it with the scTab dataset. After that, follow the scripts for pre-training and fine-tuning.

Citation

--------

If you find our work useful, please cite the following paper:

**Delineating the Effective Use of Self-Supervised Learning in Single-Cell Genomics**

`Link to the paper `_

If you use the scTab data in your research, please cite the following paper:

**Scaling cross-tissue single-cell annotation models**

`Link to the paper `_

Licence

-------

`self_supervision` is licensed under the `MIT License `_.

Authors

-------

`ssl_in_scg` was written by `Till Richter `_, `Mojtaba Bahrami `_, `Yufan Xia `_ and `Felix Fischer  `_ .