https://github.com/zhangxiaoyu11/OmiEmbed
Multi-task deep learning framework for multi-omics data analysis
https://github.com/zhangxiaoyu11/OmiEmbed
cancer deep-learning multi-omics multi-task-learning
Last synced: 5 months ago
JSON representation
Multi-task deep learning framework for multi-omics data analysis
- Host: GitHub
- URL: https://github.com/zhangxiaoyu11/OmiEmbed
- Owner: zhangxiaoyu11
- License: mit
- Created: 2021-01-29T08:07:50.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2022-05-05T19:51:52.000Z (over 3 years ago)
- Last Synced: 2024-10-29T18:07:15.334Z (12 months ago)
- Topics: cancer, deep-learning, multi-omics, multi-task-learning
- Language: Python
- Homepage:
- Size: 17.9 MB
- Stars: 39
- Watchers: 3
- Forks: 20
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# OmiEmbed
***Please also have a look at our brand new omics-to-omics DL freamwork 👀:***
[OmiTrans](https://github.com/zhangxiaoyu11/OmiTrans)
[](https://zenodo.org/badge/latestdoi/334077812)
[](https://www.codacy.com/gh/zhangxiaoyu11/OmiEmbed/dashboard?utm_source=github.com&utm_medium=referral&utm_content=zhangxiaoyu11/OmiEmbed&utm_campaign=Badge_Grade)
[](https://github.com/zhangxiaoyu11/OmiEmbed/blob/main/LICENSE)
[](https://github.com/zhangxiaoyu11/OmiEmbed/stargazers)
[](https://github.com/zhangxiaoyu11/OmiEmbed/network/members)
**OmiEmbed: A Unified Multi-task Deep Learning Framework for Multi-omics Data**
**Xiaoyu Zhang** (x.zhang18@imperial.ac.uk)
Data Science Institute, Imperial College London
## Introduction
OmiEmbed is a unified framework for deep learning-based omics data analysis, which supports:
1. Multi-omics integration
2. Dimensionality reduction
3. Omics embedding learning
4. Tumour type classification
5. Phenotypic feature reconstruction
6. Survival prediction
7. Multi-task learning for aforementioned tasks
Paper Link: [https://doi.org/10.3390/cancers13123047](https://doi.org/10.3390/cancers13123047)
## Getting Started
### Prerequisites
- CPU or NVIDIA GPU + CUDA CuDNN
- [Python](https://www.python.org/downloads) 3.6+
- Python Package Manager
- [Anaconda](https://docs.anaconda.com/anaconda/install) 3 (recommended)
- or [pip](https://pip.pypa.io/en/stable/installing/) 21.0+
- Python Packages
- [PyTorch](https://pytorch.org/get-started/locally) 1.2+
- TensorBoard 1.10+
- Tables 3.6+
- scikit-survival 0.6+
- prefetch-generator 1.0+
- [Git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git) 2.7+
### Installation
- Clone the repo
```bash
git clone https://github.com/zhangxiaoyu11/OmiEmbed.git
cd OmiEmbed
```
- Install the dependencies
- For conda users
```bash
conda env create -f environment.yml
conda activate omiembed
```
- For pip users
```bash
pip install -r requirements.txt
```
### Try it out
- Train and test using the built-in sample dataset with the default settings
```bash
python train_test.py
```
- Check the output files
```bash
cd checkpoints/test/
```
- Visualise the metrics and losses
```bash
tensorboard --logdir=tb_log --bind_all
```
## Citation
If you use this code in your research, please cite our paper.
```bibtex
@Article{OmiEmbed2021,
AUTHOR = {Zhang, Xiaoyu and Xing, Yuting and Sun, Kai and Guo, Yike},
TITLE = {OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data},
JOURNAL = {Cancers},
VOLUME = {13},
YEAR = {2021},
NUMBER = {12},
ARTICLE-NUMBER = {3047},
ISSN = {2072-6694},
DOI = {10.3390/cancers13123047}
}
```
## OmiTrans
***Please also have a look at our brand new omics-to-omics DL freamwork 👀:***
[OmiTrans](https://github.com/zhangxiaoyu11/OmiTrans)
## License
This source code is licensed under the [MIT](https://github.com/zhangxiaoyu11/OmiEmbed/blob/main/LICENSE) license.