机器学习方法在基因交互作用探测中的研究进展-遗传.PDFVIP

Hereditas (Beijing) 2018 年 3 月, 40(3): 218 ―226 综 述 机器学习方法在基因交互作用探测中的研究进展 彭哲也，唐紫珺，谢民主 湖南师范大学物理与信息科学学院，长沙 410081 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。 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 Research progress in machine learning methods for gene-gene interaction detection Zheye Peng, Zijun Tang, Minzhu Xie College of Physics and Information Science, Hunan Normal University, Changsha 410081, China Abstract : 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 app- roaches have been developed to detect gene-gene interactions with some successes. In this review, we summarize the pro- gress 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 mul- tifactor dimensionality reduction (MDR), and provides some insights on the future research directions in the field. Keywords: machine learning; gene-gene interactions; genome wide association studies; single nucleotide polymorphism ; epistasis 收稿日期: 20 17−09−20; 修回日期: 20 17−12−28 基金项目: 国家自然科学基金(编号61370172)资助[Supported by the