Browsing by Author "Wu, Wei-Sheng"

Now showing 1 - 2 of 2

Shrinkage regression-based methods for microarray missing value imputation
(2013-12-13)
Wang, Hsiuying
;
Chiu, Chia-Chun
;
Wu, Yi-Ching
;
Wu, Wei-Sheng
;
統計學研究所
Background: Missing values commonly occur in the microarray data, which usually contain more than 5% missing values with up to 90% of genes affected. Inaccurate missing value estimation results in reducing the power of downstream microarray data analyses. Many types of methods have been developed to estimate missing values. Among them, the regression-based methods are very popular and have been shown to perform better than the other types of methods in many testing microarray datasets. Results: To further improve the performances of the regression-based methods, we propose shrinkage regression-based methods. Our methods take the advantage of the correlation structure in the microarray data and select similar genes for the target gene by Pearson correlation coefficients. Besides, our methods incorporate the least squares principle, utilize a shrinkage estimation approach to adjust the coefficients of the regression model, and then use the new coefficients to estimate missing values. Simulation results show that the proposed methods provide more accurate missing value estimation in six testing microarray datasets than the existing regression-based methods do. Conclusions: Imputation of missing values is a very important aspect of microarray data analyses because most of the downstream analyses require a complete dataset. Therefore, exploring accurate and efficient methods for estimating missing values has become an essential issue. Since our proposed shrinkage regression-based methods can provide accurate missing value estimation, they are competitive alternatives to the existing regression-based methods.
Yeast cell cycle transcription factors identification by variable selection criteria
(2011-10-10)
Wang, Hsiuying
;
Wang, Yu-Han
;
Wu, Wei-Sheng
;
統計學研究所
;
Institute of Statistics
Identifying cell cycle transcription factors (TFs) is important for understanding the transcriptional regulation of the cell cycle process which controls the growth and development of all organisms. Existing computational approaches for identifying cell cycle TFs are mainly based on methods with a fixed selection criterion. That is, the same criterion was applied to each TF to determine whether it is a cell cycle TF or not. Since the characteristic of each TF may be quite different, it is not suitable to use a fixed selection criterion in identifying cell cycle TFs. Instead of using a fixed selection criterion, we propose a method with variable selection criteria to identify cell cycle TFs in yeast by integrating the ChIP-chip and cell cycle gene expression data. Our method is shown to outperform five existing methods which used the same ChIP-chip dataset as we did. Fifteen cell cycle TFs were identified by our approach, 12 of which are known cell cycle TFs, while the remaining three (Hap4, Reb1 and Tye7) are novel cell cycle TFs. The biological significance of our predictions is shown by four lines of indirect evidence derived from the protein-protein interaction data, TF mutant data, ChIP-chip data and the results of the previous computational studies. (C) 2011 Elsevier B.V. All rights reserved.