摘要
针对大鼠肝再生基因表达谱芯片数据挖掘问题,根据肝再生的生理活动过程与时间有关的特点,将其转化为多分类问题,进而利用正则化多项式回归对每一个子过程分别进行相关基因选择.此外,还分析了所选择基因间的通路关系,验证了所选基因的生物合理性.
Aiming at the problem of gene expression profile data mining in rat liver regeneration,and according to the characteristics of physiological process and time related to liver regeneration which is transformed into multiclassification problem. Then the regularized polynomial regression was used to select the genes for each subprocess.In addition,the relationship between the selected genes was analyzed and the biological rationality of the selected genes was verified.
引文
[1]王小玉,陈留院,刘云卿,等.基于弹性网络的大鼠肝再生关键基因选择[J].河南师范大学学报(自然科学版),2013,41(5):26-28.
[2] GOLU T,SLONIM D,TAMAYO P,et al. Molecular classification of cancer:Class discovery and class prediction by gene expression monitoring[J]. Science,1999,286(5439):531-536.
[3]李钧涛,杨瑞峰,左红亮.统计机器学习[J].河南师范大学学报(自然科学版),2010,38(6):35-40.
[4] GUYON I,WESTON J,BARNHILL S,et al. Gene selection for cancer classification using support vector machine[J]. Machine Learning,2002,46(1):389-422.
[5] CHEN LIUYUAN,YANG JIE,LI JUNTAO,et al. Multinomial regression with elastic net penalty and its grouping effect in gene selection[J]. Abstract and Applied Analysis,2014,31(1):1-7.
[6]王小玉,李钧涛,陈留院.稀疏对数回归及其在基因选择中的应用[J].河南师范大学学报(自然科学版),2012,41(5):153-156.