An analysis of the use of genomic DNA as a universal reference in two channel DNA microarrays

Abstract

Background: DNA microarray is an invaluable tool for gene expression explorations. In the two-dye microarray, fluorescence intensities of two samples, each labeled with a different dye, are compared after hybridization. To compare a large number of samples, the 'reference design' is widely used, in which all RNA samples are hybridized to a common reference. Genomic DNA is an attractive candidate for use as a universal reference, especially for bacterial systems with a low percentage of non-coding sequences. However, genomic DNA, comprising of both the sense and anti-sense strands, is unlike the single stranded cDNA usually used in microarray hybridizations. The presence of the antisense strand in the 'reference' leads to reactions between complementary labeled strands in solution and may cause the assay result to deviate from true values.

Results: We have developed a mathematical model to predict the validity of using genomic DNA as a reference in the microarray assay. The model predicts that the assay can accurately estimate relative concentrations for a wide range of initial cDNA concentrations. Experimental results of DNA microarray assay using genomic DNA as a reference correlated well to those obtained by a direct hybridization between two cDNA samples. The model predicts that the initial concentrations of labeled genomic DNA strands and immobilized strands, and the hybridization time do not significantly affect the assay performance. At low values of the rate constant for hybridization between immobilized and mobile strands, the assay performance varies with the hybridization time and initial cDNA concentrations. For the case where a microarray with immobilized single strands is used, results from hybridizations using genomic DNA as a reference will correspond to true ratios under all conditions.

Conclusion: Simulation using the mathematical model, and the experimental study presented here show the potential utility of microarray assays using genomic DNA as a reference. We conclude that the use of genomic DNA as reference DNA should greatly facilitate comparative transcriptome analysis.

Figure 1

Schematic of the system for simulating hybridization for a two-color assay. A: Solution phase, B: spot phase

Figure 2

Effect of hybridization time on α and [SB'] for different levels of RNA abundance and differential expression. 2a) The variation in α with the hybridization time is shown for 8 different cases of abundance level and differential expression listed in Table 2. The parameters used are k_f = 10⁶ M^-1s^-1, k_f-bound = 10⁶ M^-1s^-1, k_b = 0 s^-1, initial genomic DNA concentration = 1 pM, bound strand concentration = 10⁶ pM, transport rate = 1 s^-1 2b) Change in concentration of SB', the intensity corresponding to the cDNA channel, with time for rare and intermediate species. □ S₀ = 0.1 pM, ○ S₀ = 1 pM, * S₀ = 2 pM

Figure 3

Scatter plot showing log₂ transformed ratios obtained from direct cDNA: cDNA hybridization and indirect comparison using genomic DNA as a reference. cDNA: cDNA hybridization was carried out using two RNA samples isolated from S. coelicolor mycelia obtained from liquid culture at early (Sample 1) and late (Sample 2) growth stages. For the indirect comparison using genomic DNA, each of the two samples was hybridized with genomic DNA.

Figure 4

Effect of a decreased rate of hybridization between mobile strands and immobilized strands for different differential expression ratios and RNA abundance levels on α. □ Differential expression = 2 fold, × Differential expression = 10 fold, Δ Differential expression = 100 fold. All other parameters are same as in Figure 2.