Dynamic regulation of miRNA expression in ordered stages of cellular development

Abstract

Short RNA expression in several distinct stages of T-lymphocyte development was comprehensively profiled. The total number of microRNAs (miRNAs) expressed per cell at different stages of development varies over nearly an order of magnitude in parallel with changes in total cellular RNA content, suggesting that global miRNA levels are coregulated with the translational capacity of the cell. However, individual miRNAs were dynamically regulated during T-cell development, with at least one miRNA or miRNA family overrepresented at each developmental stage. miRNA regulation in this developmental pathway is characterized by analog rather than switch-like behavior, with temporal enrichments at distinct stages of development observed against a background of constant, basal expression of the miRNA. Enrichments of these miRNAs are temporally correlated with depletions of the transcript levels of targets containing seed matches to the specific miRNAs, and may have specific functional consequences. miR-181a, which is specifically enriched at the CD4(+)CD8(+) (DP) stage of thymocyte development, can repress the expression of Bcl-2, CD69, and the T-cell receptor, all of which are coordinately involved in positive selection.

Figure 1.

Measurements of total RNA content per cell, miRNAs per cell, and miRNAs per total RNA content. Values were derived from cell counts, total RNA quantification, and measurement of the concentration of individual miRNAs in each cell type normalized to a recovery control. The calculated miRNA pool represents an estimate based on the average of constants relating miRNA copy number to cloning frequency. Additional data is in SOM7–9. We were not able to obtain enough DN1 cells to perform miRNA quantitation analysis.

Figure 2.

miRNA expression is dynamically regulated during thymocyte development. Rooted trees were generated from miRNA and mRNA expression data derived from each thymocyte population. (A) Relationship of cells determined by Spearman correlation of miRNA profiles. (B) Relationship of cells determined by Spearman correlation of mRNA profiles (Hoffmann et al. 2003). Values at branch points in A and B denote multiscale bootstrapping significance values. (C) Heat map representing relative expression of the 21 miRNAs that were identified as enriched or depleted during thymocyte development by the χ² test. (Asterisks) Statistically significant enrichment or depletion. (D) qRT–PCR analysis of pri-miR-142 in thymocyte populations. (E) qRT–PCR analysis of ADAR family members in thymocyte populations.

Figure 3.

Genomic signatures in response to changes in miRNA family member dxpression. (A) Cumulative distribution plots of relative expression of transcripts with 3′ UTR elements harboring matches to position 2–8 of the seed region of the miR-181 family versus sets of control heptamers at each stage of thymocyte development. (B) χ² analysis of aggregate expression of miRNA family members. (Arrows) Significant (p < 0.05) enrichment (up) or depletion (down) of transcripts containing seed-match heptamers relative to a cohort of sets of transcripts containing control heptamers with similar (±10) occurrence; (asterisks) statistically significant enrichment or depletion of the indicated miRNA family. (C) Enrichment and depletion of transcripts containing heptamer seed matches relative to control sequences in relation to ranked relative miRNA expression in the six cell populations examined. Results for the 20 significantly changed miRNA families shown in B are presented. (D) Temporal analysis of enrichments and depletions during thymocyte development relative to stage of maximum miRNA family aggregate expression. Significance of these enrichments when compared with 1000 randomizations of the data set is shown.

Figure 4.

Repression of predicted miR-181a target UTRs in a reporter assay. The 3′ UTR elements of several genes identified by the Targetscan 3.0 server (Lewis et al. 2005) as potential miR-181a targets were tested in a dual-luciferase assay. An alignment of the conserved seed matches is indicated for each predicted target. Graphs indicate expression of the construct in HeLa cells transfected with a control siRNA duplex versus a miR-181a duplex normalized to the effect of each siRNA on a control UTR in a dual luciferase assay. UTR fragment length and miR-181a target sites are indicated. Results are representative of a minimum of three independent experiments performed in triplicate. Error bars represent one SD.

Figure 5.

Dysregulation of CD69 and the TCR in Dicer-deficient DP thymocytes. CD69 (A) and TCR (B) staining on electronically gated DP thymocytes from lck-cre⁺ and control Dicer^f/f mice. Derepression was normalized via median fluorescence intensity (bar graphs). (C) CD69 levels on GFP^hi and GFP^neg Dicer^f/f DP thymocytes transfected with a miR-181a or control siRNA. (D) As in C, examining lck-cre⁺ Dicer^f/f DP thymocytes. Median fluorescence intensities for each parameter are provided in SOM16. Results are representative of a minimum of three individual experiments.