Profound effect of normalization on detection of differentially expressed genes in oligonucleotide microarray data analysis

Abstract

Background: Oligonucleotide microarrays measure the relative transcript abundance of thousands of mRNAs in parallel. A large number of procedures for normalization and detection of differentially expressed genes have been proposed. However, the relative impact of these methods on the detection of differentially expressed genes remains to be determined.

Results: We have employed four different normalization methods and all possible combinations with three different statistical algorithms for detection of differentially expressed genes on a prototype dataset. The number of genes detected as differentially expressed differs by a factor of about three. Analysis of lists of genes detected as differentially expressed, and rank correlation coefficients for probability of differential expression shows that a high concordance between different methods can only be achieved by using the same normalization procedure.

Conclusions: Normalization has a profound influence of detection of differentially expressed genes. This influence is higher than that of three subsequent statistical analysis procedures examined. Algorithms incorporating more array-derived information than gene-expression values alone are urgently needed.

Figure 1

Pre- and post-normalization signal intensity scatterplots. The x-axis in all panels except (c) represents the not normalized average difference values (AD) derived from the Affymetrix GeneChip software after scanning. (a) y-axis is invariant-feature normalization with calculation of AD values. (b) y-axis is invariant-feature normalization with model-based expression values (MBEV). (c) x-axis is invariant-feature normalization with calculation of AD values; y-axis is invariant-feature normalization with MBEV. (d) y-axis is invariant probe set normalization. (e) y-axis is global scaling. Blue dots, subA-array; pink dots, subB-array.

Figure 2

Invariant sets and normalization curves generated by nonlinear normalization methods using identical randomly chosen arrays, (a) Invariant-feature method, x-axis, Mature B cells, replicate 3, not normalized; y-axis, baseline: pre-BI cells, replicate 2. Black dots, feature intensities; red circles, invariant set of features (connected by the green line). The blue line forms the diagonal with slope of I. (b) Invariant set method. Cells as in (a). Black dots, probe set average difference values; red circles, invariant set. Blue dots form the diagonal with slope of I. Axes are labeled with average difference intensities.

Figure 3

Results of testing different combinations of analysis methods. (a) Numbers of genes reaching a 99% confidence level in all possible combinations of normalization and statistical analysis algorithms. x-axis, normalization methods; y-axis, statistical analysis algorithms. Column height, number of genes. (b) Percentage of genes from Figure 2a that additionally reach a ratio of at least 2 and an absolute difference of at least 100 units. Layout is as in Figure 2a. AD, average difference; F, F-statistics; KW, Kruskal-Wallis; MBEV, model-based expression values; significance analysis of microarrays (SAM).

Figure 4

Numbers of genes detected by one or more of the 12 possible combinations between normalization and statistical analysis. x-axis, count of different combinations between normalization and statistical algorithm, y-axis, number of genes detected as differentially expressed in the respective number of different analysis combinations. A total of 12 different analysis combinations (four normalization procedures times three methods to detect differentially expressed genes) have been investigated.