predicting the categories of colon cancer using microarray data and nearest shrunken centroid

b a c k g r o u n d  & aim: it is very helpful to classify and predict the clinical  category  of a sample based  on  its  gene  expression  profile.  this  study  was  conducted  to predict  tissues  of colorectal adenoma,  adenocarcinoma,  and  paired  normal  in  colon  based  on  microarray  data  using  nearest shrunken centroid method. methods   &  materials:    in  this  study,   the  colon   cancer   dataset   were   used   including,   18 adenocarcinoma,  4 colorectal  adenoma, and 22 paired normal colon samples with 2360 common gene  expression  measurements.  in order  to predict  categories  of  colon  cancer  was used  nearest shrunken centroid method. r software was used for data analysis. r e s u lt s : based on our findings, performance of nearest shrunken centroid method was successful to reduce 2360 genes to a set of eleven genes containing rig, bigh3, gli3, homo sapiens guanylin, p78, 54kda, xbp-1, co-029, desmin, mlc-2, and hmg-1. this method predicted three classes. it predicted two classes- colorectal adenoma and adenocarcinoma with error of zero and normal class with error of 4.5%. c on c l u sio n : nearest shrunken centroid method succeeded to reduce several 1000 genes to 11 genes that were able to characterize colon tissue samples to one of the three classes of adenocarcinoma, colorectal adenoma and normal with 97.7% accuracy.