| Summary: | 碩士 === 國立中興大學 === 資訊管理學系所 === 105 === Primary skin cancer can be divided into Basal cell carcinoma, Squamous cell carcinoma and Melanoma, which basal cell carcinoma incidence rate is as high as 80%, and the global annual increase of 10% incidence. Although basal cell carcinoma has a low metastatic character, the mortality rate is also lower than the other two types of skin cancer, but this malignant tumor has a very high incidence, and therefore a great burden on global medical expenses. Imiquimod and Resiquimod are the pharmaceuticals for basal cell carcinoma, where Imiquimod has been shown to be highly effective for topical treatment of basal cell carcinoma. Therefore, the purpose of this study is to use the machine learning algorithm in the pharmaceuticals of basal cell carcinoma microarray analysis, and to construct its genetic network model.
The Basal Cell Carcinoma Pharmaceuticals Microarray Dataset is used in this study, which contains 30968 groups of gene expression. This study is divided into four parts. The first part is to use different feature selection method to select the important genes of microarray which have the most relation to basal cell carcinoma pharmaceuticals. The Linear regression analysis, Gain Ratio and OneR algorithms etc. four kinds of feature selection algorithms are used to select Biomarker. In the second part, through the hierarchical clustering analysis, the Biomarkers were grouped to explore the association of Biomarkers. In the third part, C4.5, CART and CHAID are used to construct an intelligent classification model and to explore its classification accuracy. Finally, a genetic network was constructed to analyze the relationship between basal cell carcinoma and Biomarkers. It is expected that the Biomarkers selected by this study will provide the basis for the study of pharmaceuticals of basal cell carcinoma after biological experiments in the future.
|
|---|
