Graph-based Clustering using the Wilcoxon Test to Extract the Biological Communication of Cells and Tissues

Finding a graph-based clustering is an applied method for detecting the relationship between nodes in complex networks, which has attracted considerable attention. Since recognizing different communities in large-scale data is a challenging task, by understanding the relationship between the behavior of elements in a society (cluster), we can predict the general characteristics of the clusters. Graph-based clustering techniques have played an important role in the clustering of gene expression data due to their ability to show the relationship between data. In order to detect effective genes in the development of diseases, it is necessary to achieve the relationship between cells or tissues. The interaction between cells or different tissues can be demonstrated by expressing different genes between them. In this research, the problem of cell-to-cell and tissue-to-cell communication is expressed as a graph and is extracted by the recognition of relationships. The Phantom 5 database is used to simulate and calculate the similarity between cells and tissues. After preprocessing and normalizing the data, for the conversion of these data to the graph, the expression of the gene in different cells and tissues has been examined and considering the threshold and the Wilcoxon test, using clustering of communications They were identified.