基于蚁群算法的复杂疾病上位性分析方法
2014-09-18吴蓉晖卢友敏
吴蓉晖+卢友敏
收稿日期:20130930
基金项目:湖南省科技计划资助项目(2014FJ3079)
作者简介:吴蓉晖(1967-),女,河南太康人,湖南大学副教授,博士
通讯联系人,Email:55251983@qq.com
摘要:针对全基因组规模的上位性分析中存在的问题,首先采用基于多准则融合的过滤法对大量变异位点进行筛选以过滤无关位点,并结合蚁群算法对变异位点进行上位性分析,从而进一步剔除冗余位点,最后采用支持向量机作为上位性与复杂疾病关系的分类模型.实验结果表明,先过滤再分类的策略,不仅大大降低了上位性时间复杂度,并且在分类准确度上也有一定程度提高.
关键词:复杂疾病;上位性;支持向量机
中图分类号:TP399 文献标识码:A
An Epistasis Analysis Method of Complex
Diseases Based on Ant Colony Algorithm
WU Ronghui1, LU Youmin1,2
(1. College of Information Science and Engineering,Hunan Univ,Changsha,Hunan410082,China;
2. Dept of Computer Engineering,Huaihua Univ,Huaihua,Hunan418400,China)
Abstract: To solve the problem of epistasis analysis in genomewide, a filter method based on multiple criteria fusion was developed to remove the unrelated SNP loci. After that, ant colony algorithm was used to construct the SNP set with epistasis interaction. In the phase of constructing, a support vector machine was proposed to build the relationship between the SNP set and complex diseases. The experiment results show that, with multiple criteria evaluating each SNP and ant colony optimization, the prediction accuracy and running time have been improved, making it better than conventional methods.
Key words: complex disease; epistasis; support vector machines
随着人类基因组计划(HGP)测序工作的完成,生命科学的研究重点已经从确定 DNA序列组成转移到了研究基因功能.由于复杂疾病[1]在人群中具有高死亡率及难以治愈等特点,使得复杂疾病成为医学、生物学相关科研人员的重点研究对象.复杂疾病不同于孟德尔疾病,它的形成与发展通常涉及到多个基因的相互作用或者基因与环境的交互作用即上位作用.而从分子层次上看,上位作用即为基因调控网络或生物化学代谢通路中的生物分子(例如 DNA,RNA 的蛋白质等)之间的物理相互作用[2].通常上位作用在基因型和疾病表型之间一般都表现为非线性关系,从而难以被检测.在特殊情况下,单个基因与表型之间并没有表现出相关性,但是当该基因与其他基因……
