Bayesian Robust Inference for Differential Gene Expression in cDNA Microarrays with Multiple Samples

Abstract

Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. AbstractWe consider the problem of identifying differentially expressed genes under different conditions using cDNA microarrays. Standard statistical methods cannot be used because typically there are thousands of genes and few replicates. Because of the many steps involved in the experimental process, from hybridization to image analysis, cDNA microarray data often contain outliers. For example, an outlying data value could occur because of scratches or dust on the surface, imperfections in the glass, or imperfections in the array production. We develop a robust Bayesian hierarchical model for testing for differential expression. Outliers are modeled explicitly using a t-distribution. The model includes an exchangeable prior for the variances which allow different variances for the genes but still shrink extreme empirical variances. Our model can be used for testing for differentially expressed genes among multiple samples, and can distinguish between the different possible patterns of differential expression when there are three or more samples. Parameter estimation is carried out using a novel version of Markov Chain Monte Carlo that is appropriate when the model puts mass on subspaces of the full parameter space. The method is illustrated using two publicly available gene expression data sets. We compare our method to five other commonly used techniques, namely the one-sample t-test, the Bonferroni-adjusted t-test, Significance Analysis of Microarrays (SAM), and EBarrays in both its Lognormal-Normal and Gamma-Gamma forms. In an experiment with HIV data, our method performed better than these alternatives, on the basis of between-replicate agreement and disagreement.

A Flexible and Powerful Bayesian Hierarchical Model for ChIP–Chip Experiments

“…This is due to the fact that HGMM assumes a constant coefficient of variation. Similar observations have been made with the original GG model used by Newton et al (2001) in the context of differential gene expression; see Gottardo et al (2006).…”

“…To model the fact that enrichment effects can be exactly zero, we use the following prior: which is a mixture of a point mass at zero and a Gaussian distribution with mean ξ and variance τ −1 truncated at zero, where w p is the mixing weight representing the a priori probability that probe p has positive enrichment effect. Such mixture priors have been widely used in the analysis of gene expression data (Lönnstedt and Speed, 2002; Gottardo et al, 2003, 2006). Here we use a truncated normal at zero as enrichment effects should be positive.…”

“…We regularize noisy variance estimates by borrowing strength from all the probes with an exchangeable prior for the probe precisions (Parmigiani et al, 2002; Gottardo et al, 2006; Lewin et al, 2006), defined by , that is, a gamma distribution with mean α c and variance β c .…”

“…Bayesian hierarchical models have become increasingly popular in the analysis of gene expression data (Newton et al, 2001; Lönnstedt and Speed, 2002; Parmigiani et al, 2002; Gottardo et al, 2006); they can make the best of available prior information while borrowing strength from the data when estimating the quantities of interest. Using such models, inference is usually based on the posterior distribution of the parameters.…”

Robustification of Naïve Bayes Classifier and Its Application for Microarray Gene Expression Data Analysis

“…The detailed discussion is shown in [33] for preprocessing of HNC dataset. We first select the differentially expressed (DE) genes whose posterior probability is more than 0.9; otherwise the genes are equally expressed (EE) using bridge R package [35] which is shown in Figure 6 that shows 594 differentially expressed genes from 12626 genes. We have performed the Anderson-Darling (A-D) normality test [36, 37] for the HNC dataset.…”