voomDDA: discovery of diagnostic biomarkers and classification of RNA-seq data

RNA-Seq is a recent and efficient technique that uses the capabilities of next-generation sequencing technology for characterizing and quantifying transcriptomes. One important task using gene-expression data is to identify a small subset of genes that can be used to build diagnostic classifiers particularly for cancer diseases. Microarray based classifiers are not directly applicable to RNA-Seq data due to its discrete nature. Overdispersion is another problem that requires careful modeling of mean and variance relationship of the RNA-Seq data. In this study, we present voomDDA classifiers: variance modeling at the observational level (voom) extensions of the nearest shrunken centroids (NSC) and the diagonal discriminant classifiers. VoomNSC is one of these classifiers and brings voom and NSC approaches together for the purpose of gene-expression based classification. For this purpose, we propose weighted statistics and put these weighted statistics into the NSC algorithm. The VoomNSC is a sparse classifier that models the mean-variance relationship using the voom method and incorporates voom’s precision weights into the NSC classifier via weighted statistics. A comprehensive simulation study was designed and four real datasets are used for performance assessment. The overall results indicate that voomNSC performs as the sparsest classifier. It also provides the most accurate results together with power-transformed Poisson linear discriminant analysis, rlog transformed support vector machines and random forests algorithms. In addition to prediction purposes, the voomNSC classifier can be used to identify the potential diagnostic biomarkers for a condition of interest. Through this work, statistical learning methods proposed for microarrays can be reused for RNA-Seq data. An interactive web application is freely available at http://www.biosoft.hacettepe.edu.tr/voomDDA/.

Gene expression analysis of ischemic and nonischemic cardiomyopathy: shared and distinct genes in the development of heart failure

Cardiomyopathy can be initiated by many factors, but the pathways from unique inciting mechanisms to the common end point of ventricular dilation and reduced cardiac output are unclear. We previously described a microarray-based prediction algorithm differentiating nonischemic (NICM) from ischemic cardiomyopathy (ICM) using nearest shrunken centroids. Accordingly, we tested the hypothesis that NICM and ICM would have both shared and distinct differentially expressed genes relative to normal hearts and compared gene expression of 21 NICM and 10 ICM samples with that of 6 nonfailing (NF) hearts using Affymetrix U133A GeneChips and significance analysis of microarrays. Compared with NF, 257 genes were differentially expressed in NICM and 72 genes in ICM. Only 41 genes were shared between the two comparisons, mainly involved in cell growth and signal transduction. Those uniquely expressed in NICM were frequently involved in metabolism, and those in ICM more often had catalytic activity. Novel genes included angiotensin-converting enzyme-2 (ACE2), which was upregulated in NICM but not ICM, suggesting that ACE2 may offer differential therapeutic efficacy in NICM and ICM. In addition, a tumor necrosis factor receptor was downregulated in both NICM and ICM, demonstrating the different signaling pathways involved in heart failure pathophysiology. These results offer novel insight into unique disease-specific gene expression that exists between end-stage cardiomyopathy of different etiologies. This analysis demonstrates that transcriptome analysis offers insight into pathogenesis-based therapies in heart failure management and complements studies using expression-based profiling to diagnose heart failure of different etiologies.