Correlation of microRNA levels during hypoxia with predicted target mRNAs through genome-wide microarray analysis

Abstract

Background: Low levels of oxygen in tissues, seen in situations such as chronic lung disease, necrotic tumors, and high altitude exposures, initiate a signaling pathway that results in active transcription of genes possessing a hypoxia response element (HRE). The aim of this study was to investigate whether a change in miRNA expression following hypoxia could account for changes in the cellular transcriptome based on currently available miRNA target prediction tools.

Methods: To identify changes induced by hypoxia, we conducted mRNA- and miRNA-array-based experiments in HT29 cells, and performed comparative analysis of the resulting data sets based on multiple target prediction algorithms. To date, few studies have investigated an environmental perturbation for effects on genome-wide miRNA levels, or their consequent influence on mRNA output.

Results: Comparison of miRNAs with predicted mRNA targets indicated a lower level of concordance than expected. We did, however, find preliminary evidence of combinatorial regulation of mRNA expression by miRNA.

Conclusion: Target prediction programs and expression profiling techniques do not yet adequately represent the complexity of miRNA-mediated gene repression, and new methods may be required to better elucidate these pathways. Our data suggest the physiologic impact of miRNAs on cellular transcription results from a multifaceted network of miRNA and mRNA relationships, working together in an interconnected system and in context of hundreds of RNA species. The methods described here for comparative analysis of cellular miRNA and mRNA will be useful for understanding genome wide regulatory responsiveness and refining miRNA predictive algorithms.

Figure 1

Differentially expressed mRNAs. Comparison of changes in HT29 mRNA levels under hypoxic vs. normoxic conditions. Unique genes that were differentially expressed 1.5 fold or greater are shown on the log-scale scatter plot. Upper cloud indicates transcripts at increased levels under hypoxic conditions and lower cloud indicates those decreased under hypoxic conditions.

Figure 2

Bicluster of microRNA expression. Hierarchical clustering was carried out using correlation distance as the distance metric and average linkage between clusters to perform the analysis. This is a non-supervised method to illustrate potential relationships between the miRNA expression profiles from different samples. Hierarchical clustering was carried out for all samples and miRNA. The top of the figure indicates relationships between the various samples. The left-hand side shows the relationships between the miRNA identified on the right-hand side. The color of each cell reflects fold-change of the observed hybridization intensity relative to average hybridization intensity across all samples. Saturated green cells represent decrease in hybridization intensity, whereas saturated red cells represent an increase.

Figure 3

Correlation of miRNAs with at least one target site in miRanda-predicted target mRNA. In each panel, the reference distribution of t-statistics from all probes of the mRNA expression arrays is given by a dotted line. These are compared with the distribution of t-statistics for those probes that are predicted targets of given miRNAs, shown as a solid line. 'N' represents the number of transcripts in the reference sample (dotted line), and therefore is the same in each plot. Sample size (n) is the number of genes predicted to have target(s) of given microRNA(s) (solid line), and therefore changes from plot to plot. Note that n depends on the number of predicted target probes contained within the dataset, either combined among all miRNAs, or specific to an individual miRNA. The plotted distributions are Gaussian kernel density estimates (loosely, smoothed histograms), and the indicated bandwidth is in terms of the standard deviation of the smoothing kernel. The x-axis in each figure reflects the t-statistics for the comparison between groups (dotted line represents random distribution). The y-axis represents the density of observations at a given t-statistic value. a. Combined t-statistics for all significantly changed miRNAs with 1 site in the 3'UTR of predicted target miRNAs. b. Combined t-statistics for a set of non-significant miRNAs with 1 predicted target site. c. Representative significantly changed miRNA compared to all of its predicted targets. d. Representative non-significantly changed miRNA compared to all of its predicted targets.

Figure 4

Correlation of miRNAs with at least one target site in PicTar-predicted target mRNA. a. Combined t-statistics for all significantly changed miRNAs with 1 site in the 3'UTR of predicted target mRNAs. b. Combined t-statistics for a set of non-significant miRNAs with 1 predicted target site. c. Representative significantly changed miRNA compared to all of its predicted targets. d. Representative non-significantly changed miRNA compared to all of its predicted targets.

Figure 5

Correlation of miRNAs with at least one target site in TargetScanS (with total context score)-predicted target mRNA. a. Combined t-statistics for significantly changed miRNAs (top 15%) with 1 site in the 3'UTR of predicted target mRNAs. b. Combined t-statistics for a set of non-significant miRNAs with 1 predicted target site. c. Representative significantly changed miRNA compared to top 15% of its predicted targets. d. Representative non-significantly changed miRNA compared to top 15% of its predicted targets.

Figure 6

Correlation of miRNAs with at least one target site in miRanda(miRBase)-predicted target mRNA. a. Combined t-statistics for all significantly changed miRNAs with 1 site in the 3'UTR of predicted target mRNAs. b. Combined t-statistics for a set of non-significant miRNAs with 1 predicted target site. c. Representative significantly changed miRNA compared to all of its predicted targets. d. Representative non-significantly changed miRNA compared to all of its predicted targets.

Figure 7

Correlation of miRNAs with at least 3 target sites in miRanda-predicted target mRNA. Same as Figure 3, except that probes identified as targets of a miRNA are required to have at least three target sites in the 3'UTR region according to the miRanda(microrna.org) target prediction software. Arrows indicate deviation from the reference graph.

Figure 8

Correlation of specific genes with predicted groups of miRNAs (miRanda, microrna.org). The expression levels in hypoxia and normoxia of each gene specific miRNA group were plotted. Significant deviation of the regression line (solid) from the line of equality (dotted line) indicates co-regulation of the group. Panel a shows histogram of the p-values for miRNA groups of all coding genes represented in the study for miRanda. Frequency on y-axis refers to the number of genes involved. Panels b-d depict CFTR, KIAA2026, and C16orf73 as examples of mRNA regulation by gene-specific miRNA groups. The red dots indicate gene-specific miRNAs for each given gene; this includes 9 miRNAs predicted by miRanda(microrna.org) for CFTR, 28 each for KIAA2026 and C16orf73.

Figure 9

Correlation of specific genes with predicted groups of miRNAs (PicTar). The expression levels in hypoxia and normoxia of each gene specific miRNA group were plotted. Significant deviation of the regression line (solid) from the line of equality (dotted line) indicates co-regulation of the group. Panel a shows histogram of the p-values for miRNA groups of all coding genes represented in the study for PicTar. Frequency on y-axis refers to the number of genes involved. Panels b-d depict CFTR, NRBF2, and GALNT3 as examples of mRNA regulation by gene-specific miRNA groups. The red dots indicate gene specific miRNAs for each given gene.

Figure 10

Correlation of specific genes with predicted groups of miRNAs (TargetScanS). Panel a shows histogram of the p-values for miRNA groups of all coding genes represented in the study for TargetScanS. Frequency on y-axis refers to the number of genes involved. Panels b-d depict CFTR, KIAA1468, and ARID4B as examples of mRNA regulation by gene-specific miRNA groups. The red dots indicate gene specific miRNAs for each given gene.

Figure 11

Correlation of specific genes with predicted groups of miRNAs (miRanda/miRBase). Panel a shows histogram of the p-values for miRNA groups of all coding genes represented in the study for miRanda/miRBase. Frequency on y-axis refers to the number of genes involved. Panels b-d depict CFTR, NRBF2, and LARP1 as examples of mRNA regulation by gene-specific miRNA groups. The red dots indicate gene specific miRNAs for each given gene.