DeepRisk:A deep learning approach for genome-wide assessment of common disease risk

作     者：Jiajie Peng Zhijie Bao Jingyi Lia Ruijiang Han Yuxian Wang Lu Han Jinghao Peng Tao Wang Jianye Hao Zhongyu Wei Xuequn Shang 

作者机构：AI for Science Interdisciplinary Research CenterSchoolof Computer ScienceNorthwestern Polyechnical UniversityXi'an 129China Key Laboratoryof Bg Data Sorage and ManagementNorthwestern Polytechnical UniversityMinisty of Industy and Information TechnologyX'an 129Chin College of Intelligence and ComputingTianjin UniversityTianjin 300072China School of Data ScienceFudan UniversityShanghai 200433China Research and Development Institute of Northwestern Polytechnical University in ShenzhenShenzhen 518000China 

出 版 物：《Fundamental Research》 (自然科学基础研究（英文版）)

年 卷 期：2024年第4卷第4期

页      面：752-760页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the National Natural Science Foundation of China(62072376 and U1811262) Guangdong Provincial Basic and Applied Research Fund Project(2022A1515010144) Innovation Capability Support Program of Shaanxi(2022KJXX-75) the Fundamental Research Funds for the Central Universities(D5000230056) 

主　　题：Disease risk prediction Deep learning Polygenic risk score Common disease risk Disease prevention 

摘      要：The potential for being able to identify individuals at high disease risk solely based on genotype data has garnered significant *** widely applied,traditional polygenic risk scoring methods fall short,as they are built on additive models that fail to capture the intricate associations among single nucleotide polymorphisms(SNPs).This presents a limitation,as genetic diseases often arise from complex interactions between multiple *** address this challenge,we developed DeepRisk,a biological knowledge-driven deep learning method for modeling these complex,nonlinear associations among SNPs,to provide a more effective method for scoring the risk of common diseases with genome-wide genotype *** demonstrated that DeepRisk outperforms existing PRs-based methods in identifying individuals at high risk for four common diseases:Alzheimer s disease,inflammatory bowel disease,type 2diabetes,and breast cancer.