Please also have a look at our multi-omics multi-task DL freamwork 👀: OmiEmbed

The FIRST GANs-based omics-to-omics translation framework

Xiaoyu Zhang (x.zhang18@imperial.ac.uk)

Data Science Institute, Imperial College London

OmiTrans is a generative adversarial networks (GANs) based omics-to-omics translation framework.

• CPU or NVIDIA GPU + CUDA CuDNN
• Python 3.6+
• Python Package Manager
  • Anaconda 3 (recommended)
  • or pip 21.0+
• Python Packages
  • PyTorch 1.2+
  • TensorBoard 1.10+
  • Tables 3.6+
  • prefetch-generator 1.0+
• Git 2.7+

• Clone the repo

git clone https://github.com/zhangxiaoyu11/OmiTrans.git
cd OmiTrans

• Install the dependencies
  • For conda users

  conda env create -f environment.yml
  conda activate omitrans

  • For pip users

  pip install -r requirements.txt

• Put the gene expression data (A.tsv) and DNA methylation data (B.tsv) in the default data path (./data)
• Train and test using the default settings

python train_test.py

• Check the output files

cd checkpoints/test/

• Visualise the metrics and losses

tensorboard --logdir=tb_log --bind_all

Please also have a look at our multi-omics multi-task DL freamwork 👀: OmiEmbed

This source code is licensed under the MIT license.