机器学习方法在基因交互作用探测中的研究进展  

Research progress in machine learning methods for gene-gene interaction detection

作　　者：彭哲也 唐紫珺 谢民主[1] 赵方庆 Zheye Peng;Zijun Tang;Minzhu Xie(College of Physics and Information Science, Hunan Normal University, Changsha 410081, China)

机构地区：[1]湖南师范大学物理与信息科学学院,长沙410081 [2]不详

出　　处：《遗传》2018年第3期218-226,共9页Hereditas（Beijing)

基　　金：国家自然科学基金(编号:61772197,61370172)资助

摘　　要：复杂疾病是基因与基因、基因与环境交互作用的结果,高维基因交互作用的探测给计算带来了极大的挑战。在过去20年间,机器学习方法被用于探测基因-基因交互作用,并取得了一定的效果。本文综述了机器学习方法在基因交互作用探测中的研究进展,系统地介绍了神经网络(neural networks,NN)、随机森林(random forest,RF)、支持向量机(support vector machines,SVM)和多因子降维法(multifactor dimensionality reduction,MDR)等机器学习方法在全基因组关联研究(genome wide association study,GWAS)中探测基因交互作用的原理和局限性,并对未来的研究进行了展望。Complex diseases are results of gene-gene and gene-environment interactions.However,the detection of high-dimensional gene-gene interactions is computationally challenging.In the last two decades,machine-learning approaches have been developed to detect gene-gene interactions with some successes.In this review,we summarize the progress in research on machine learning methods,as applied to gene-gene interaction detection.It systematically examines the principles and limitations of the current machine learning methods used in genome wide association studies(GWAS)to detect gene-gene interactions,such as neural networks(NN),random forest(RF),support vector machines(SVM)and multifactor dimensionality reduction(MDR),and provides some insights on the future research directions in the field.

关 键 词：机器学习 基因交互 全基因组关联分析 单核苷酸多态性 上位性 

分 类 号：Q811.4[生物学—生物工程]