Biomedical subjects

Chang-Yung Yu

Publications and source records attributed to Chang-Yung Yu.

3 recordsLinked to original sources

PubMed2003

Cell and tumor classification using gene expression data: construction of forests.

The advent of gene chips has led to a promising technology for cell, tumor, and cancer classification. We exploit and expand the methodology of recursive partitioning trees for tumor and cell classification from microarray gene expression data. To improve classification and prediction accuracy, we introduce a deterministic procedure to form forests of classification trees and compare their performance with extant alternatives. When two published and commonly used data sets are used, we find that the deterministic forests perform similarly to the random forests in terms of the error rate obtained from the leave-one-out procedure, and all of the forests are far better than the single trees. In addition, we provide graphical presentations to facilitate interpretation of complex forests and compare our findings with the current biological literature. In addition to numerical improvement, the main advantage of deterministic forests is reproducibility and scientific interpretability of all steps in tree construction.

Cells↗

PubMed2003

Tree-based disease classification using protein data.

A reliable and precise classification of diseases is essential for successful diagnosis and treatment. Using mass spectrometry from clinical specimens, scientists may find the protein variations among disease and use this information to improve diagnosis. In this paper, we propose a novel procedure to classify disease status based on the protein data from mass spectrometry. Our new tree-based algorithm consists of three steps: projection, selection and classification tree. The projection step aims to project all observations from specimens into the same bases so that the projected data have fixed coordinates. Thus, for each specimen, we obtain a large vector of 'coefficients' on the same basis. The purpose of the selection step is data reduction by condensing the large vector from the projection step into a much lower order of informative vector. Finally, using these reduced vectors, we apply recursive partitioning to construct an informative classification tree. This method has been successfully applied to protein data, provided by the Department of Radiology and Chemistry at Duke University.

Computational Biology↗

PubMed2002

Tree-based analysis of microarray data for classifying breast cancer.

DNA microarray data have provided us with the opportunity to assess the expression levels for thousands of genes simultaneously. One of the uses of this information is to classify cancer tumors. A noted challenge in using microarray information is analytical. Following the work of Zhang et al. (1), we further pursue the use of recursive partitioning in analyses of microarray data for cancer classification. Not only does the recursive partitioning technique create intuitive classification rules, but also it is most flexible as to the handling of a massive number of genes, missing expressions, and multi-class tissues. Using a published data set (2), we demonstrate that the recursive partitioning technique creates a more precise and simpler classification rule than other commonly used approaches. In particular, we introduce the concept of A-tree and propose a procedure to assess a large number of A-trees. One of the identified genes (ERBB2) is in the close region of BRCA1 (17q21.1) and has been shown by others to have altered expression levels in breast cancer. Nonetheless, our identified genes warrant further investigation as to whether they play a role in the etiology of breast cancer.

Breast Neoplasms↗