Disease Prediction Using Ranks of Gene Expressions

A large number of studies have been performed to identify biomarkers that will allow efficient detection and determination of the precise status of a patient's disease. The use of microarrays to assess biomarker status is expected to improve prediction accuracies, because a whole-genome approach is used. Despite their potential, however, patient samples can differ with respect to biomarker status when analyzed on different platforms, making it more difficult to make accurate predictions, because bias may exist between any two different experimental conditions. Because of this difficulty in experimental standardization of microarray data, it is currently difficult to utilize microarray-based gene sets in the clinic. To address this problem, we propose a method that predicts disease status using gene expression data that are transformed by their ranks, a concept that is easily applied to two datasets that are obtained using different experimental platforms. NCI and colon cancer datasets, which were assessed using both Affymetrix and cDNA microarray platforms, were used for method validation. Our results demonstrate that the proposed method is able to achieve good predictive performance for datasets that are obtained under different experimental conditions.

An Attempt for Combining Microarray Data Sets by Adjusting Gene Expressions / Journal of the Korean Cancer Association, 대한암학회지

PURPOSE: The diverse experimental environments in microarray technology, such as the different platforms or different RNA sources, can cause biases in the analysis of multiple microarrays. These systematic effects present a substantial obstacle for the analysis of microarray data, and the resulting information may be inconsistent and unreliable. Therefore, we introduced a simple integration method for combining microaray data sets that are derived from different experimental conditions, and we expected that more reliable information can be detected from the combined data set rather than from the separated data sets. MATERIALS AND METHODS: This method is based on the distributions of the gene expression ratios among the different microarray data sets and it transforms, gene by gene, the gene expression ratios into the form of the reference data set. The efficiency of the proposed integration method was evaluated using two microarray data sets, which were derived from different RNA sour-ces, and a newly defined measure, the mixture score. RESULTS: The proposed integration method intermixed the two data sets that were obtained from different RNA sources, which in turn reduced the experimental bias between the two data sets, and the mixture score increased by 24.2%. A data set combined by the proposed method preserved the inter-group relationship of the separated data sets. CONCLUSION: The proposed method worked well in adjusting systematic biases, including the source effect. The ability to use an effectively integrated microarray data set yields more reliable results due to the larger sample size and this also decreases the chance of false negatives.