• 中国精品科技期刊
  • 《中文核心期刊要目总览》收录期刊
  • RCCSE 中国核心期刊(5/114,A+)
  • Scopus收录期刊
  • 美国《化学文摘》(CA)收录期刊
  • WHO 西太平洋地区医学索引(WPRIM)收录期刊
  • 《中国科学引文数据库(CSCD)》核心库期刊 (C)
  • 中国科技核心期刊
  • 中国科技论文统计源期刊
  • 《日本科学技术振兴机构数据库(中国)》(JSTChina)收录期刊
  • 美国《乌利希期刊指南》(UIrichsweb)收录期刊
  • 中华预防医学会系列杂志优秀期刊(2019年)

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

联邦学习在多中心遗传健康指数构建中的应用进展

赵艳艳 王金兰 王晓霞 薛付忠

赵艳艳, 王金兰, 王晓霞, 薛付忠. 联邦学习在多中心遗传健康指数构建中的应用进展[J]. 中华疾病控制杂志, 2022, 26(10): 1187-1191. doi: 10.16462/j.cnki.zhjbkz.2022.10.013
引用本文: 赵艳艳, 王金兰, 王晓霞, 薛付忠. 联邦学习在多中心遗传健康指数构建中的应用进展[J]. 中华疾病控制杂志, 2022, 26(10): 1187-1191. doi: 10.16462/j.cnki.zhjbkz.2022.10.013
ZHAO Yan-yan, WANG Jin-lan, WANG Xiao-xia, XUE Fu-zhong. Developments of federated learning in multi-centric genetic health index construction[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2022, 26(10): 1187-1191. doi: 10.16462/j.cnki.zhjbkz.2022.10.013
Citation: ZHAO Yan-yan, WANG Jin-lan, WANG Xiao-xia, XUE Fu-zhong. Developments of federated learning in multi-centric genetic health index construction[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2022, 26(10): 1187-1191. doi: 10.16462/j.cnki.zhjbkz.2022.10.013

联邦学习在多中心遗传健康指数构建中的应用进展

doi: 10.16462/j.cnki.zhjbkz.2022.10.013
基金项目: 

国家重点研发计划 2020YFC2003500

山东省医药卫生科技发展计划 2019WS522

详细信息
    通讯作者:

    薛付忠, E-mail: xuefzh@sdu.edu.cn

  • 中图分类号: Q39;O212.4

Developments of federated learning in multi-centric genetic health index construction

Funds: 

National Key Research and Development Program of China 2020YFC2003500

The Medicine and Health Science Technology Development Project of Shandong Province 2019WS522

More Information
  • 摘要: 个体健康指数是根据健康指数构建的一个重要维度。而遗传因素是个体健康水平评估的重要组成部分。众所周知,复杂疾病不遵循孟德尔遗传定律,其受多个效应微小基因位点影响。多基因风险评分(polygenic risk score,PRS)是近年来被广泛应用的个体遗传因素评分。PRS可以综合与疾病相关的基因位点,从而对复杂疾病实现风险预测和精准预防。但是种族的不平衡问题会影响多基因风险评分的泛化能力。而充分整合多个数据中心的数据可以有效增加不同种族样本量从而减轻不平衡性,是缩小种族之间健康差距的重要方法。随着人们对数据隐私安全和所有权的关注度不断提高,如何在保护数据隐私的前提下充分利用各个数据中心的数据资源和计算资源引起了越来越多学者的重视。而基因组数据的独特性使个体基因组数据的隐私保护变得格外重要。本文将讨论多中心基因组数据分析中的隐私保护方法,包括同态加密、安全多方计算、Meta分析、联邦学习、同态加密与联邦学习的结合。进而讨论联邦学习框架下多中心PRS构造的统计方法。
  • 图  1  GWAS多样性监视器对GWAS参与者种族多样性的总结

    Figure  1.  The summary of ancestry diversity of GWAS participants from GWAS diversity monitor

  • [1] Ma Y, Zhou X. Genetic prediction of complex traits with polygenic scores: a statistical review[J]. Trends Genet, 2021, 37(11): 995-1011. DOI: 10.1016/j.tig.2021.06.004.
    [2] Mills MC, Rahal C. The GWAS Diversity Monitor tracks diversity by disease in real time[J]. Nat Genet, 2020, 52(3): 242-243. DOI: 10.1038/s41588-020-0580-y.
    [3] Bonomi L, Huang Y, Ohno-Machado L. Privacy challenges and research opportunities for genomic data sharing[J]. Nat Genet, 2020, 52(7): 646-654. DOI: 10.1038/s41588-020-0651-0.
    [4] 刘海, 彭长根, 吴振强, 等. 基因组数据隐私保护理论与方法综述[J]. 计算机学报, 2021, 44(7): 1430-1480. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX202107009.htm

    Liu H, Peng CG, Wu ZQ, et al. A survey of the theories and methods of privacy preserving of genome data[J]. Chinese Journal of Computers, 2021, 44(7): 1430-1480. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX202107009.htm
    [5] 宋思嘉, 单晨璐, 王爽, 等. 基因数据隐私问题及相关保护技术进展研究[J]. 医学信息学杂志, 2021, 42(6): 2-9, 23. https://www.cnki.com.cn/Article/CJFDTOTAL-YXQB202106001.htm

    Song SJ, Shan CL, Wang S, et al. Study on the privacy issues of genetic data and the progress of related protection technologies[J]. Journal of medical informatics, 2021, 42(6): 2-9, 23. https://www.cnki.com.cn/Article/CJFDTOTAL-YXQB202106001.htm
    [6] Gürsoy G, Li T, Liu S, et al. Functional genomics data: privacy risk assessment and technological mitigation[J]. Nat Rev Genet, 2022, 23(4): 245-258. DOI: 10.1038/s41576-021-00428-7.
    [7] Blatt M, Gusev A, Polyakov Y, et al. Secure large-scale genome-wide association studies using homomorphic encryption[J]. Proc Natl Acad Sci, 2020, 117(21): 11608-11613. DOI: 10.1073/pnas.1918257117.
    [8] Shi H, Jiang C, Dai W, et al. Secure multi-party computation grid logistic regression (SMAC-GLORE)[J]. BMC Med Inform Decis Mak, 2016, 16(3): 89. DOI: 10.1186/s12911-016-0316-1.
    [9] Constable SD, Tang Y, Wang S, et al. Privacy-preserving GWAS analysis on federated genomic datasets[J]. BMC Med Inform Decis Mak, 2015, 15 suppl 5: s2. DOI: 10.1186/1472-6947-15-s5-s2.
    [10] Zhou W, Global Biobank Meta-analysis Initiative. Global Biobank Meta-analysis Initiative: powering genetic discovery across human diseases[J]. MedRxiv, 2021.
    [11] Tang L, Zhou L, Song PXK. Distributed simultaneous inference in generalized linear models via confidence distribution[J]. J Multivar Anal, 2020, 176: 104567. DOI: 10.1016/j.jmva.2019.104567.
    [12] Duan R, Ning Y, Chen Y. Heterogeneity-aware and communication-efficient distributed statistical inference[J]. Biometrika, 2022, 109(1): 67-83. DOI: 10.1093/biomet/asab007.
    [13] Kairouz P, McMahan HB, Avent B, et al. Advances and open problems in federated learning[J]. Foundations and Trends® in Machine Learning, 2021, 14(1-2): 1-210.
    [14] Wu X, Zheng H, Dou Z, et al. A novel privacy-preserving federated genome-wide association study framework and its application in identifying potential risk variants in ankylosing spondylitis[J]. Brief Bioinform, 2021, 22(3): bbaa090. DOI: 10.1093/bib/bbaa090.
    [15] Nasirigerdeh R, Torkzadehmahani R, Matschinske J, et al. sPLINK: a hybrid federated tool as a robust alternative to meta-analysis in genome-wide association studies[J]. Genome Biol, 2022, 23(1): 32. DOI: 10.1186/s13059-021-02562-1.
    [16] Froelicher D, Troncoso-Pastoriza JR, Raisaro JL, et al. Truly privacy-preserving federated analytics for precision medicine with multiparty homomorphic encryption[J]. Nat Commun, 2021, 12(1): 5910. DOI: 10.1038/s41467-021-25972-y.
    [17] Cai T, Liu M, Xia Y. Individual data protected integrative regression analysis of high-dimensional heterogeneous data[J]. J Am Stat Assoc, 2021: 1-15. DOI: 10.1080/01621459.2021.1904958.
    [18] Gottesman II, Shields J. A polygenic theory of schizophrenia[J]. Proc Natl Acad Sci USA. 1967, 58(1): 199-205. DOI: 10.1073/pnas.58.1.199.
    [19] Wray NR, Goddard ME, Visscher PM. Prediction of individual genetic risk to disease from genome-wide association studies[J]. Genome Res, 2007, 17(10): 1520-1528. DOI: 10.1101/gr.6665407.
    [20] International Schizophrenia Consortium, Purcell SM, Wray NR, et al. Common polygenic variation contributes to risk of schizophrenia and bipolar disorder[J]. Nature, 2009, 460(7256): 748-752. DOI: 10.1038/nature08185.
    [21] Li S, Cai T, Duan R. Targeting underrepresented populations in precision medicine: a federated transfer learning approach[J]. arXiv preprint arXiv, 2021, 2108: 12112.
  • 加载中
图(1)
计量
  • 文章访问数:  226
  • HTML全文浏览量:  176
  • PDF下载量:  89
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-05-07
  • 修回日期:  2022-08-21
  • 刊出日期:  2022-10-10

目录

    /

    返回文章
    返回