Contact map overlap maximization using adaptive distributed modified extremal optimization
Contact map overlap maximization using adaptive distributed modified extremal optimization
复制标题
DOI：
10.1109/iwcia.2016.7805754
复制
发表时间：
2016-11
期刊：
影响因子：
--
通讯作者：
Keiichi Tamura;H. Kitakami;Tatsuhiro Sakai
中科院分区：
文献类型：
--
作者：
Keiichi Tamura;H. Kitakami;Tatsuhiro Sakai
在后基因组时代，蛋白质相似结构的检测受到了相当大的关注。蛋白质结构比对与序列比对类似，可以根据蛋白质的三维结构来检测蛋白质之间的结构同源性。寻找最佳蛋白质结构比对的最简单但最强大的技术之一是最大化接触图重叠（CMO）。这种优化被称为CMO问题。我们一直在开发生物启发式模型，使用分布式修改极值优化（DMEO）的CMO问题。DMEO受到分布式遗传算法的启发，这种算法被称为岛屿模型。DMEO是基于群体的改进极值优化（PMEO）和岛屿模型的混合。在我们以前的工作中，我们提出了一种新的生物启发式模型，即，DMEO与不同的进化策略（DMEODES），以保持种群多样性。DMEODES是基于岛屿模型;然而，一些岛屿，称为热点岛，有一个不同的进化策略。在本文中，我们提出了一个国家的最先进的启发式模型，以提高DMEO的能力，以防止进化停滞。新模型集成了DMEO中的自适应世代交替机制ADMEO。为了评估ADMEO，我们使用了实际的蛋白质结构。实验结果表明，ADMEO优于DMEODES。
The detection of similar structures in proteins has received considerable attention in the post-genome era. Protein structure alignment, which is similar to sequence alignment, can detect the structural homology between two proteins according to their three-dimensional structures. One of the simplest yet most robust techniques for finding optimal protein structure alignment is to maximize the contact map overlap (CMO). This optimization is known as the CMO problem. We have been developing bio-inspired heuristic models using distributed modified extremal optimization (DMEO) for the CMO problem. DMEO is inspired by distributed genetic algorithms, which are known as island models. DMEO is a hybrid of population-based modified extremal optimization (PMEO) and the island model. In our previous work, we proposed a novel bio-inspired heuristic model, i.e., DMEO with different evolutionary strategies (DMEODES) to maintain population diversity. DMEODES is based on the island model; however, some of the islands, called hot-spot islands, have a different evolutionary strategy. In this paper, we propose a state-of-art heuristic model to improve the DMEO's ability to prevent evolution stagnation. The new model integrates an adaptive generation alternation mechanism in DMEO called ADMEO. To evaluate ADMEO, we used actual protein structures. Experimental results show that ADMEO outperforms DMEODES.