Estimating accuracy of RNA-Seq and microarrays with proteomics

Abstract

Background: Microarrays revolutionized biological research by enabling gene expression comparisons on a transcriptome-wide scale. Microarrays, however, do not estimate absolute expression level accurately. At present, high throughput sequencing is emerging as an alternative methodology for transcriptome studies. Although free of many limitations imposed by microarray design, its potential to estimate absolute transcript levels is unknown.

Results: In this study, we evaluate relative accuracy of microarrays and transcriptome sequencing (RNA-Seq) using third methodology: proteomics. We find that RNA-Seq provides a better estimate of absolute expression levels.

Conclusion: Our result shows that in terms of overall technical performance, RNA-Seq is the technique of choice for studies that require accurate estimation of absolute transcript levels.

Figure 1

Correlation between mRNA expression levels measured by Affymetrix microarrays and RNA-Seq. mRNA expression levels measured by RNA-Seq in two pooled samples of 5 individuals and by microarrays in the same samples (A) or in 5 independent individual samples (B). Shown are expression levels of 8,441 and 4,758 genes, respectively, expressed above background on at least one of the microarrays in a given experiment and represented by at least two independent sequence reads in RNA-Seq (see Methods for details). (C and D) Person correlation coefficients (r) from comparisons between RNA-Seq and microarray measurements based on each microarray separately and on average expression from all possible microarray combinations for two pooled and 5 individual samples, respectively (see Additional file 1: Table S3 for details).

Figure 2

Correlation between protein and mRNA expression levels measured by Affymetrix arrays and RNA-Seq. Protein expression was measured in four individual samples with technical replicates. mRNA expression was measured by microarrays and RNA-Seq in two pooled samples (A, B, and E), and by microarrays in 5 individual samples (D). Shown are expression intensities of 520 (A and B) and 306 (D and E) genes expressed above background on all microarrays in a given experiment and represented by at least twenty independent sequence reads in RNA-Seq. (Cand F) Person correlation coefficients (r) from comparisons between RNA-Seq and protein measurements (blue) and between microarray and protein measurements (red) for two pooled samples and 5 individual samples, respectively. For RNA-Seq data, the correlations were based on each sequencing experiment separately and on average expression from all possible experiment combinations. For microarrays, the correlations were based on expression values from each microarray separately and on average expression from all possible microarray combinations (see Additional file 1: Table S4 for details).

Figure 3

Distribution of expression signals within genes for the three methodologies. The histograms show total signal density for 6424, 13582, and 1577 genes with detectable expression estimated by microarrays, RNA-Seq, or proteomics, respectively. In order to account for length differences among genes, for each gene we normalized the distances between the middle positions of the detected expression measurements (array probes, sequence reads, or peptides) and the 5' end of the gene by the gene length.