Intelligent K-Means clustering for expressed genes identification linked to malignancy of human colorectal carcinoma

摘要

Cancer is one kind of deadly disease. Colorectal carcinoma is one type of cancer which is difficult to detect in its early stage. It has dangerous malignancy in its advance stage. Identify gene expressed and cancer linked to phenotype is an effort to identify and analyze correlation of genes and clinical phenotype (metastasis). In this paper Intelligent K-Means is used to cluster genes expression. It is a non parametric clustering that more powerful and more stable than GMM clustering which is used in previous research. After getting clusters of genes, then correlation ratio is used to identify whether genes in a cluster has a correlation with clinical metastasis. As the result in this paper, genes in cluster C and cluster E have correlation with normal-cancer tissue metastasis and distant metastasis. But, there is no cluster of genes has correlation with lymph node metastasis.