GOAT: Gene-level biomarker discovery from multi-Omics data using graph ATtention neural network for eosinophilic asthma subtype
Note
GOAT 2.0 has been released. Checkout here , please.
We propose a novel deep graph attention model for biomarker discovery for the asthma subtype by incorporating complex interactions between biomolecules and capturing key biomarker candidates using the attention mechanism.
Full manuscript available here
You can build a docker image from Dockerfile.
# Pull base image from docker hub
docker pull dabinjeong/cuda:10.1-cudnn7-devel-ubuntu18.04
# Build docker image
docker build --tag biomarker:0.1.1 .
You can also download the docker image from Docker hub (https://hub.docker.com/repository/docker/dabinjeong/biomarker/general).
docker pull dabinjeong/biomarker:0.1.1
conda create -n biomarker python=3.9
conda activate biomarker
conda install -c bioconda nextflow=21.04.0
nextflow run biomarker_discovery.nf -c pipeline.config -with-docker biomarker:0.1.1
For comparative analysis, please refer to the following repository, comparative_analysis_multi-omics_biomarker.
@article{jeong2023goat,
title={GOAT: Gene-level biomarker discovery from multi-Omics data using graph ATtention neural network for eosinophilic asthma subtype},
author={Jeong, Dabin and Koo, Bonil and Oh, Minsik and Kim, Tae-Bum and Kim, Sun},
journal={Bioinformatics},
volume={39},
number={10},
pages={btad582},
year={2023},
publisher={Oxford University Press}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent