Leukemia and small round blue-cell tumor cancer detection using\ud microarray gene expression data set: Combining data dimension\ud reduction and variable selection technique

摘要

Using gene expression data in cancer classification plays an important role for solving the fundamental problems\udrelating to cancer diagnosis. Because of high throughput of gene expression data for healthy and patient samples,\uda variable selection method can be applied to reduce complexity of the model and improve the classification\udperformance. Since variable selection procedures pose a risk of over-fitting, when a large number of variables\udwith respect to sample are used,we have proposed a method for coupling data dimension reduction and variable\udselection in the present study. This approach uses the concept of variable clustering for the original data set.\udSignificant components of local principal component analysis models have just been retained from all clusters.\udThen, the variable selection algorithm is performed on these locally derived principal component variables.\udThe proposed algorithm has been evaluated on two gene expression data sets; namely, acute Leukemia and\udsmall round blue-cell tumor (SRBCT). Our results confirmed that the classification models achieved on the\udreduced data were better than those obtained on the entire microarray gene expression profile.