Motivated by a real data set deriving from a study on the genetic determinants of the behavior of Mycobacterium tuberculosis (MTB) hosted in macrophage, we take advantage of the presence of control spots and illustrate modelling issues for background correction and the ensuing empirical findings resulting from a Bayesian hierarchical approach to the problem of detecting differentially expressed genes. We prove the usefulness of a fully integrated approach where background correction and normalization are embedded in a single model-based framework, creating a new tailored model to account for the peculiar features of DNA array data where null expressions are planned by design. We also advocate the use of an alternative normalization device resulting from a suitable reparameterization. The new model is validated by using both simulated and our MTB data. This work suggests that the presence of a substantial fraction of exact null expressions might be the effect of an imperfect background calibration and shows how this can be suitably re-calibrated with the information coming from control spots. The proposed idea can be extended to all experiments in which a subset of genes whose expression levels can be ascribed mainly to background noise is planned by design.
Azzalini A and Capitanio A (1999) Statistical applications of the multivariate skew normal distribution. Journal of the Royal Statistical Society Series B, 61, 579–602.
2.
Baldi P and Long AD (2001) A Bayesian framework for the analysis of microarray expression data: regularized t-test and statistical inferences of gene changes. Bioinformatics, 17, 509–19.
3.
Bayarri MJ and Berger J (2000) P-values for composite null models. Journal of American Statistical Association, 95, 1127–42.
4.
Benjamini Y and Hochberg Y (1995) Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of Royal Statistical Society, Series B: Methodological, 57, 289–300.
5.
Blangiardo M, Toti S, Giusti B, Abbate R, et al. (2006) Using a calibration experiment to assess gene-specific information: full Bayesian and empirical Bayesian models for two-channel microarray data. Bioinformatics, 22, 50–57.
6.
Blangiardo M and Richardson S (2007a) Statistical tools for synthesizing lists of differentially expressed features in related experiments. Genome Biology, 8, R54.
7.
Blangiardo M and Richardson S (2007b) A Bayesian calibration for combining different pre-processing methods in Affymetrix chips. Technical Report, Imperial College, London.
8.
Bolstad BM, Irizarry RA, Astrand M and Speed TP (2003) A comparison of normalization methods for high density oligonucleotide array data based on variance and bias. Bioinformatics, 22, 185–93.
9.
Cappelli G, Volpe E, Grassi M, Liseo B, et al. (2006) Profiling of Mycobacterium tuberculosis gene expression during human macrophage infection: upregulation of the alternative sigma factor G, a group of transcriptional regulators, an proteins with unknown function. Research in Microbiology, 157, 445–55.
10.
Cerecedo I, Zamora J, Shreffler WG, Ling J, et al. (2008) Mapping of the IgE and IgG4 sequential epitopes of milk allergens with a peptide microarray-based immunoassay. American Academy of Allergy, Asthma & Immunology, 122, 589–94.
11.
Chen K and Rajewsky N (2007) The evolution of gene regulation by transcription factors and microRNAs. Nature Reviews in Genetics, 8, 93–103.
12.
Dawes NL and Glassey J (2007) Normalisation of multicondition cDNA macroarray data. Comparative and Functional Genomics, 2007, Article ID 90578, 12.
13.
Dharmadhikari S and Joag-Dev K (1988) Unimodality, convexity, and applications. Probability and mathematical statistics. Boston: Academic Press.
14.
Ding LH, Xie Y, Park S, Xiao S et al. (2008) Enhanced identification and biological validation of differential gene expression via Illumina whole-genome expression arrays through the use of the model-based background correction methodology. Nucleic Acids Research, 36, e58.
15.
Do K, Muller P and Tang F (2005) A Bayesian mixture model for differential gene expression. Journal of Royal Statistical Society, Series C, 54, 111–39.
16.
Do KA, Muller P and Vannucci M (2006) Bayesian inference for gene expression and proteomics. New York: Cambridge University Press.
17.
Edwards D (2003) Non-linear normalization and background correction in one-channel cDNA microarray studies. Bioinformatics, 19, 825–33.
18.
Farcomeni A (2007) A review of modern multiple hypothesis testing, with particular attention to the false discovery proportion. Statistical Methods in Medical Research, 17, 1–42.
19.
Genovese CR and Wasserman L (2003) Bayesian and frequentist multiple testing. In Bernardo JM, Bayarri MJ, Berger JO, Dawid AP, Heckerman D, Smith AFM and West M (eds.). Bayesian Statistics, USA: Oxford University Press, 7, 145–62.
20.
Gottardo R, Raftery AE, Yeung KY and Bumgarner RE (2006) Quality control and robust estimation for cDNA microarrays with replicates. Journal of American Statistical Association, 101, 30–40.
21.
Griffith M, Tang MJ, Griffith O, Morin RD, et al. (2008) ALEXA: a microarray design platform for alternative expression analysis. Nature Methods, 5, 118–21
22.
Jelinek DF, Tschumper RC, Stolovitzky GA, Iturria SJ, et al. (2003) Identification of a global gene expression signature of B-chronic lymphocytic leukemia. Molecular Cancer Research, 1, 346–61.
23.
Kim JH, Kim HY and Lee YS (2002) Effect of local background intensities in the normalization of cDNA microarray data with a skewed expression profiles. Experimental Molecular Medicine, 34, 224–32.
24.
Kooperberg C, Fazzio TG, Delrow JJ and Tsukiyama T (2002) Improved background correction for spotted DNA microarray. Journal of Computational Biology, 9, 55–66.
25.
Kuhn K, Baker SC, Chudin E, Lieu MH, et al. (2004) A novel, high-performance random array platform for quantitative gene expression profiling. Genome Research, 14, 2347–56.
26.
Küppers R, Klein U, Schwering I, Distler V, et al. (2003) Identification of Hodgkin and Reed-Sternberg cell-specific genes by gene expression profiling. Journal of Clinical Investigation, 111, 529–37.
27.
Lewin A, Richardson S, Marshall C, Glazier A, et al. (2006) Bayesian modeling of differential gene expression. Biometrics, 62, 1–9.
28.
McLachlan GJ, Bean RW and Peel D (2002) A mixture model based approach to the clustering of microarray expression data. Bioinformatics, 18, 413–22.
Neuhäauser M, Boes T and Jöckel KH (2005) Two-part permutation tests for DNA methylation and microarray data. BMC Bioinformatics, 6, 1–17.
31.
Newton M, Noueiry A, Sarkar D and Ahlquisi P (2004) Detecting differential gene expression with a semiparametric hierarchical mixture model. Biostatistics, 5, 155–76.
32.
Nguyen AB, Arpat DV, Wang N and Carroll RJ (2002) DNA microarray experiments: biological and technological aspects. Biometrics, 58, 701–17.
33.
Oshlack A, Emslie D, Corcoran LM and Smyth GK (2007) Normalization of boutique two-color microarrays with a high proportion of differentially expressed probes. Genome Biology, 8, R2.
34.
Pan W (2002) A comparative review of statistical methods for discovering differentially expressed genes in replicated microarray experiments. Bioinformatics, 18, 546–54.
35.
Parmigiani G, Garett ES, Irizarry RA and Zeger SL (2003) The analysis of gene expression data. Springer.
36.
R Development Core Team (2006) R: A language and environment for statistical computing. R Foundation for Statistical Computing. Vienna, Austria: http://www.R-project.org.
37.
Ritchie ME, Silver J, Oshlack A, Holmes M, et al. (2007) A comparison of background correction methods for two-color microarrays. Bioinformatics, 23, 2700–07.
38.
Scharpf RB, Iacobuzio-Donahue CA, Sneddon JB and Parmigiani G (2007) When should one subtract background fluorescence in 2-color microarrays?Biostatistics, 8, 695–707.
39.
Spiegelhalter DJ, Thomas A and Best NG (1999) WinBUGS Version 1.2 User Manual. MRC Biostatistics Unit.
40.
Tschentscher F, Hüusing JHölter T, Kruse E, et al. (2003) Tumor classification based on gene expression profiling shows that uveal melanomas with and without monosomy 3 represent two distinct entities. Cancer Research, 63, 2578–84.
41.
Tusher V, Tibshirani R and Gilbert C (2001) Significance analysis microarray applied to the ionizing radiation response. Proceedings of the National Academy of Sciences USA, 98, 5116–121.
42.
Wessel R, Foos V, Aspelmeier A, Juergens M, et al. (2006) CorrXpression—identification of significant groups of genes and experiments by means of correspondence analysis and ratio analysis. Silico Biology, 6, 61–70.
43.
Wit E and McClure J (2004) Statistics for Microarrays. John Wiley & Sons.
44.
Yang YH, Buckley MJ, Dudoit S and Speed TP (2002) Comparison of methods for image analysis on cDNA microarray data. Journal of Computational and Graphical Statistics, 11, 108–36.
45.
Yoon D, Yi SG, Kim JH and Park T (2004) Two-stage normalization using background intensities in cDNA microarray data. Bioinformatics, 5, 1–12.
