人工鱼群算法在基因调控网络中的应用研究  

Research on Application of Artificial Fish Swarm Algorithm in Gene Regulatory Network

作　　者：田旺兰[1] 李加升[1] 

机构地区：[1]湖南城市学院通信与电子工程学院,湖南益阳413000

出　　处：《计算机工程》2014年第10期204-209,共6页Computer Engineering

基　　金：湖南省科技计划基金资助项目(2012FJ3025)

摘　　要：在分析基因调控网络现状及优缺点的基础上,提出利用人工鱼群算法对阈值布尔网络模型构建下的基因调控网络进行研究。将阈值布尔网络模型应用于花发育形态模型,构建基于预定义吸引子和极限环的综合网络。比较人工鱼群算法与模拟退火算法在基因调控网络中的应用情况,分析网络节点更新机制变化时布尔网络保留吸引子的能力,发现在极限环长度为2和特定网络拓扑下网络才具有鲁棒性。实验结果表明,与模拟退火算法相比,人工鱼群算法在网络发现、鲁棒性方面具有更好的性能,因此利用人工鱼群算法学习布尔网络结构是有效可行的。Based on the analysis of the advantages and disadvantages of the current appliance of swarm intelligence algorithm into Gene Regulatory Network （ GRN ） , this paper studies the gene regulatory network constructed under Boolean network model using Artificial Fish Swarm Algorithm （ AFSA ） . Especially, the comprehensive network of predefined attractors and limit cycle is formulated by applying Boolean network model into flower growth morphogenesis. After comparing AFSA with Simulated Annealing（ SA） and analyzing the ability of the networks to preserve the attractors when the updating schemes is changed from parallel to sequential,the paper finds the network has robustness within the limit cycle length equal to two and specific network topologies. Experimental results show that the intelligence algorithm outperforms simulated annealing in network discovery and robustness. Therefore,it is feasible to learn Boolean network using AFSA.

关 键 词：人工鱼群算法 模拟退火算法 布尔网络 吸引子 极限环 花发育形态模型 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]