MethPriorGCN：一种用于推断DNA甲基化先验知识并指导个性化医疗的深度学习工具。

MethPriorGCN: a deep learning tool for inferring DNA methylation prior knowledge and guiding personalized medicine.

作者信息

Ni Jie, Li Bin, Miao Shumei, Zhang Xinting, Yan Donghui, Jing Shengqi, Lu Shan, Xie Zhuoying, Zhang Xin, Liu Yun

机构信息

Institute for Molecular Medical Technology, State Key Laboratory of Digital Medical Engineering, School of Biological Science and Medical Engineering, Southeast University, No. 2, Southeast University Road, Jiangning District, Nanjing, Jiangsu 211102, China.

Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, No. 101, Longmian Avenue, Jiangning District, Nanjing, Jiangsu 211166, China.

出版信息

Brief Bioinform. 2025 Mar 4;26(2). doi: 10.1093/bib/bbaf131.

DOI:10.1093/bib/bbaf131

PMID:40131311

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11934576/

Abstract

DNA methylation plays a crucial role in human diseases pathogenesis. Substantial experimental evidence from clinical and biological studies has confirmed numerous methylation-disease associations, which provide valuable prior knowledge for advancing precision medicine through biomarker discovery and disease subtyping. To systematically mine reliable methylation prior knowledge from known DNA methylation-disease associations and develop robust computational methods for precision medicine applications, we propose MethPriorGCN. By integrating layer attention mechanisms and feature weighting mechanisms, MethPriorGCN not only identified reliable methylation digital biomarkers but also achieved superior disease subtype classification accuracy.

摘要

DNA甲基化在人类疾病发病机制中起着至关重要的作用。来自临床和生物学研究的大量实验证据证实了众多甲基化与疾病的关联，这些关联为通过生物标志物发现和疾病亚型划分推进精准医学提供了宝贵的先验知识。为了从已知的DNA甲基化与疾病关联中系统地挖掘可靠的甲基化先验知识，并开发用于精准医学应用的强大计算方法，我们提出了MethPriorGCN。通过整合层注意力机制和特征加权机制，MethPriorGCN不仅识别出可靠的甲基化数字生物标志物，还实现了卓越的疾病亚型分类准确率。