基于并行免疫遗传算法基因表达数据的动态模糊聚类

Dynamic Fuzzy Clustering for Analyzing Microarray Gene Expression Data Based on a Parallel Immune Genetic Algorithm

提出一种改进的并行免疫遗传算法,通过在群体规模上引入"岛"的概念,实现了可变的群体规模;通过在适应度函数内引入免疫算子,避免了算法过早收敛.因此,解决了寻优算法中局部收敛的困扰,提高了获得全局最优解的几率.把此算法应用于斯坦福大学酵母细胞周期表达数据库的数据进行共表达聚类,并将实验结果与Spellman按照功能基因组学进行聚类所得结果进行了对比,证明了所给算法在功能基因组学聚类上的有效性.

We proposed an improved parallel immune genetic algorithm. The introduced island concept on the population size can make the sizes of populations variable; The immune operator introduced in the fitness function can avoid the algorithm premature convergence. Hence, this method can prevent local convergence in the optimal algorithm in a great extent, and make the probability of approaching the global convergence bigger. The algorithm was used via the Yeast Saccharomyces cerevisiae cell cycle gene expression profile from SGD to co-express clusters. Compared to the experiment analyzed by Spellman for functional genomics, the efficiency of this algorithm in the functional genomics can be proved.