中文摘要：

DNA微阵列技术的发展为基因表达研究提供更有效的工具。分析这些大规模基因数据主要应用聚类方法。最近，提出双聚类技术来发现子矩阵以揭示各种生物模式。多目标优化算法可以同时优化多个相互冲突的目标，因而是求解基因表达矩阵的双聚类的一种很好的方法。本文基于克隆选择原理提出了一个新奇的多目标免疫优化双聚类算法，来挖掘微阵列数据的双聚类。在两个真实数据集上的实验结果表明该方法比其他多目标进化双聚娄算法表现出更优越的性能。

英文摘要：

The development of DNA microarray technologies provides an efficient tool for the experimental study of gene expression. Analysis of those large scale genomies data has initially focused on clustering methods. Recently, biclustering techniques were proposed for revealing submatriees showing unique patterns. Multi-objective optimization approach, which optimizes simultaneously several objectives in conflict with each other, is very good for solving biclustering problem. This paper proposes a novel multi - objective intmune optimization biclustering algorithm based on the clonal selection principle to mining biclusters from microarray data. Experimental are conducted on two real datasets, which shows that multi-objective immune optimization biclustering algorithm exhibits better and more stable performance than other multi - objective evolutionary biclustering algorithrns.