返回
Optimization of dynamic bi-clustering based on improved genetic algorithm for microarray data
DOI:10.1007/s10044-024-01309-5.png)
摘要
En 中文
Due to the nature of microarray data, the analysis of genes/features for disease diagnosis is a challenging task. Generally, the data comes in the form of a 2D matrix, where the row represents the genes and the column indicates the various conditions. Bi-clustering is an emerging technique that can efficiently reveal patterns of genes. It can perform simultaneously with a subset of genes and conditions. Inspired by this, dynamic bi-clustering based on an improved genetic algorithm (GA) is proposed. The chromosomes are efficiently designed. In addition, the fitness function is derived by considering multiple conflicting objectives to measure the quality of a cluster. A novel mutation is designed by the correlation technique. The crossover and mutation rates are dynamically changed. The obtained outcomes of the proposed approach are compared with the various existing approaches, such as traditional GA, the dynamic dame parallel GA, the evolutionary local search algorithm, bi-phase evolutionary searching, and the evolutionary bi-clustering algorithm. Further, statistical tests such as the analysis of variance and Friedman test are executed to show the significance of the proposed model. A biological analysis is also performed.
Keyword:
Bi-cluster
GA
Correlation
ANOVA
Microarray data
期刊
IF:
2
论文数:
1.9K
被引数:
1.9K
机构
引用论文
Evolutionary Local Search Algorithm for the biclustering of gene expression data based on biological knowledge基于生物知识的基因表达数据双聚类进化局部搜索算法
A novel biclustering of gene expression data based on hybrid BAFS-BSA algorithm基于混合bafs-bsa算法的基因表达数据双聚类
Utilization of Urea and Water Metabolism by Zebu Cattle and Buffaloes under Tropical Conditions热带条件下瘤牛和 buffalo 对尿素及水代谢的利用
Competencies for One Health Workforce Quality Assurance: Disciplinary Diversity and Consensus in a Global eDelphi Panel面向“同一健康”工作队伍质量保证的胜任力:全球电子德尔菲小组中的学科多样性与共识

