City University of Hong Kong, Kowloon Tong, Hong Kong.
Department of Computer Science, College of Engineering, City University of Hong Kong, Kowloon Tong, Hong Kong.
Methods Mol Biol. 2021;2212:325-335. doi: 10.1007/978-1-0716-0947-7_20.
Epistasis detection is a hot topic in bioinformatics due to its relevance to the detection of specific phenotypic traits and gene-gene interactions. Here, we present a step-by-step protocol to apply Epi-GTBN, a machine learning-based method based on genetic algorithm and Bayesian network to effectively mine the epistasis loci. Epi-GTBN utilizes the advantages of genetic algorithm that can achieve a global search and avoid falling into local optima incorporating it into the Bayesian network to obtain the best structure of the model. In this chapter, we describe an example of Epi-GTBN to help researchers to analyze the epistasis and gene-gene interactions of their own datasets and build the corresponding SNP-SNP network.
上位性检测是生物信息学中的一个热门话题，因为它与特定表型特征和基因-基因相互作用的检测有关。在这里，我们提出了一个逐步的方案来应用基于遗传算法和贝叶斯网络的机器学习方法 Epi-GTBN，以有效地挖掘上位性位点。Epi-GTBN 利用遗传算法的优势，能够实现全局搜索，避免陷入局部最优，并将其纳入贝叶斯网络中，以获得模型的最佳结构。在本章中，我们描述了一个 Epi-GTBN 的示例，以帮助研究人员分析自己数据集的上位性和基因-基因相互作用，并构建相应的 SNP-SNP 网络。
