遗传 ›› 2018, Vol. 40 ›› Issue (3): 218-226.doi: 10.16288/j.yczz.17-254

• 综述 • 上一篇    下一篇

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()   

  1. 湖南师范大学物理与信息科学学院,长沙 410081
  • 收稿日期:2017-09-20 修回日期:2017-12-28 出版日期:2018-03-20 发布日期:2018-01-30
  • 基金资助:
    国家自然科学基金(编号:61772197,61370172)资助

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

Peng Zheye,Tang Zijun,Xie Minzhu()   

  1. College of Physics and Information Science, Hunan Normal University, Changsha 410081, China
  • Received:2017-09-20 Revised:2017-12-28 Online:2018-03-20 Published:2018-01-30
  • Supported by:
    [Supported by the National Natural Science Foundation of China (Nos. 61772197,61370172)]

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

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 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.

Key words: machine learning, gene-gene interactions, genome wide association studies, single nucleotide polymorphism, epistasis