scConcept

This repository contains the python package to train and use scConcept (Single-cell contrastive cell pre-training) method for single-cell transcriptomics data.

Installation

Option 1: Using uv (Recommended)

1. Install uv if you haven't already:

curl -LsSf https://astral.sh/uv/install.sh | sh

2. Create and activate a virtual environment and install dependencies:

sh ./scripts/setup_uv.sh

Option 2: Using pip

1. Create and activate virtual environment:

python -m venv venv
source venv/bin/activate

2. Install the package and dependencies:

pip install -e .

3. Install Flash Attention 2:

pip install flash-attn==2.7.* --no-build-isolation

4. Install lamin-dataloader (optional: only required for training over large number of anndata objects):

pip install git+https://github.com/theislab/lamin_dataloader.git

Licence

scConcept is licensed under the MIT License