Diagnosis of multiple cancer types by shrunken centroids of gene expression
Diagnosis of multiple cancer types by shrunken centroids of gene expression
复制标题
DOI：
10.1073/pnas.082099299
复制
发表时间：
2002-05-14
影响因子：
11.1
通讯作者：
Chu, G
中科院分区：
文献类型：
--
作者：
Tibshirani, R;Hastie, T;Chu, G
我们基于简单的最近原型（质心）分类器的增强，设计了一种通过基因表达谱预测癌症类别的方法。我们缩小了原型，从而获得了一个通常比竞争方法更准确的分类器。我们的“最近收缩质心”方法识别出最能表征每个类别的基因子集。该技术是通用的，可以用于许多其他分类问题。为了证明其有效性，我们证明该方法在寻找用于分类小圆形蓝细胞肿瘤和白血病的基因方面非常有效。
We have devised an approach to cancer class prediction from gene expression profiling, based on an enhancement of the simple nearest prototype (centroid) classifier. We shrink the prototypes and hence obtain a classifier that is often more accurate than competing methods. Our method of "nearest shrunken centroids" identifies subsets of genes that best characterize each class. The technique is general and can be used in many other classification problems. To demonstrate its effectiveness, we show that the method was highly efficient in finding genes for classifying small round blue cell tumors and leukemias.