一种基于粒度的双聚类共表达基因深度挖掘方法
A Novel Granular-Based Bi-Clustering Method of Deep Mining the Co-Expressed Genes
摘要：
传统的聚类方法在处理海量、异质的基因表达数据时存在局限性，这促使了双聚类方法的发展。双聚类方法用于挖掘双聚类，其样本（基因）的子集在其测试条件下被共调节。研究表明，从基因表达数据中挖掘具有一致趋势和波动程度相似趋势的双聚类是生物信息学研究的关键。不幸的是，传统的双聚类方法在发现这样的双聚类时并不完全有效。因此，我们提出了一种新的双聚类方法，通过在这里涉及到粒度计算的理论。在该方案中，基因数据矩阵，被认为是一组时间序列，转化为一系列有序的信息粒。利用信息粒构建基因数据的特征矩阵，捕捉基因表达值在连续条件之间的波动趋势，挖掘理想的双聚类。实验结果与理论分析一致，表明了该方法的优越性。
英文摘要：
Traditional clustering methods are limited when dealing with huge and heterogeneous groups of gene expression data, which motivates the development of bi-clustering methods. Bi-clustering methods are used to mine bi-clusters whose subsets of samples (genes) are co-regulated under their test conditions. Studies show that mining bi-clusters of consistent trends and trends with similar degrees of fluctuations from the gene expression data is essential in bioinformatics research. Unfortunately, traditional bi-clustering methods are not fully effective in discovering such bi-clusters. Therefore, we propose a novel bi-clustering method by involving here the theory of Granular Computing. In the proposed scheme, the gene data matrix, considered as a group of time series, is transformed into a series of ordered information granules. With the information granules we build a characteristic matrix of the gene data to capture the fluctuation trend of the expression value between consecutive conditions to mine the ideal bi-clusters. The experimental results are in agreement with the theoretical analysis, and show the excellent performance of the proposed method.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
