Skip to content

Latest commit

 

History

History
67 lines (45 loc) · 1.33 KB

README.md

File metadata and controls

67 lines (45 loc) · 1.33 KB
Raw

SAILER

Pytorch implementation for SAILER: Scalable and Accurate Invariant Representation Learning for Single-Cell ATAC-Seq Processing and Integration

Setup

Clone the repository.

git clone https://github.com/uci-cbcl/SAILER.git

Navigate to the root of this repo and setup the conda environment.

conda env create -f deepatac.yml

Activate conda environment.

conda activate deepatac

Data

Please download data here and setup your data folder as the following structure:

SAILER
|___data  
    |___MouseAtlas
        |___...
    |___SimATAC
        |___...

Visualizing Results

Please download the pretrained model here and setup your data folder as the following structure:

SAILER
|___models  
    |___MouseAtlas.pt

Navigate to the root of this repo and run the following command. Result will be stored under ./results directory.

python eval.py -l './models/MouseAtlas.pt' -d atlas

Training

To train the model from scratch, use the following command.

python train.py -b 400 -d atlas --name mouse_atlas

For more information, see

python train.py -h