Principles of microRNA-target recognition

Abstract

MicroRNAs (miRNAs) are short non-coding RNAs that regulate gene expression in plants and animals. Although their biological importance has become clear, how they recognize and regulate target genes remains less well understood. Here, we systematically evaluate the minimal requirements for functional miRNA-target duplexes in vivo and distinguish classes of target sites with different functional properties. Target sites can be grouped into two broad categories. 5' dominant sites have sufficient complementarity to the miRNA 5' end to function with little or no support from pairing to the miRNA 3' end. Indeed, sites with 3' pairing below the random noise level are functional given a strong 5' end. In contrast, 3' compensatory sites have insufficient 5' pairing and require strong 3' pairing for function. We present examples and genome-wide statistical support to show that both classes of sites are used in biologically relevant genes. We provide evidence that an average miRNA has approximately 100 target sites, indicating that miRNAs regulate a large fraction of protein-coding genes and that miRNA 3' ends are key determinants of target specificity within miRNA families.

Figure 1. Complementarity to the miRNA 5′ End Is Important for Target Site Function In Vivo

(A) In vivo assay for target site regulation in the wing imaginal disc. The EGFP reporter is expressed in all cells (green). Cells expressing the miRNA under ptcGal4 control are shown in red. Functional target sites allow strong GFP repression by the miRNA (middle). Non-functional target sites do not (right). Yellow boxes indicate the disc region shown in (B) and later figures. (B) Regulation of individual target sites by miR-7. Numbers in the upper left of each image indicate the mismatched nucleotide in the target site. Positions important for regulation are shown in red, dispensable positions in green. Regulation by the miRNA is completely abolished in only a few cases. (C) Summary of the magnitude of reporter gene repression for the series in (B) and for a second set involving miR-278 and a target site resembling the miR-9 site in Lyra [26]. Positions important for regulation are shown in red, dispensable positions in green. Error bars are based on measurements of 3–5 individual discs.

Figure 2. The Minimal miRNA Target Site

(A) In vivo tests of the function of target sites with 6mer, 5mer, and 4mer seeds complementary to the first eight nucleotides of the miRNA. Sites were designed to have optimal support from 3′ pairing. The first 4mer seed site shows that extensive complementarity to the miRNA 3′ region is not sufficient for regulation in vivo. (B) Regulation of 8mer, 7mer, and 6mer seed sites lacking complementarity to the miRNA 3′ end. The test UTR contained one site (first column) or two identical sites (second column).

Figure 3. Effects of G:U Base-Pairs and Bulges

(A) Regulation of sites with 8mer, 7mer, or 6mer seeds (rows) containing zero, one, two, or three G:U base-pairs in the seed region (columns). (B) Regulation of sites with bulges in the target sequence or in the miRNA.

Figure 4. Three Classes of miRNA Target Sites

Model of canonical (left), seed (middle) and 3′ compensatory (right) target sites. The upper diagram illustrates the mode of pairing between target site (upper line) and miRNA (lower line, color). Next down in each column are diagrams of the pattern of 3′ UTR conservation. The vertical black bars show stretches of at least six nucleotides that are conserved in several drosophilid genomes. Target sites for miR-7, miR-4, and miR-10 are shown as colored horizontal bars beneath the UTR. Sites for other miRNAs are shown as black bars. Furthest down in each column the predicted structure of the duplex between the miRNA and its target site is shown; canonical base-pairs are marked with filled circles, G:U base-pairs with open circles. The sequence alignments show nucleotide conservation of these target sites in the different drosophilid species Nucleotides predicted to pair to the miRNA are shown in bold; nucleotides predicted to be unpaired are grey. Red asterisks indicate 100% sequence conservation; grey asterisks indicate conservation of base-pairing to the miRNA including G:U pairs. The additional sequence alignment for the miR-10 target site in Scr in Tribolium castanaeum, Anopheles gambiae, and Bombyx mori strengthens this prediction. Note that the reduced quality of 3′ compensation in these species is compensated by the presence of a better quality 7mer seed. A. ga, Anopheles gambiae; B. mo, B. mori; D. an, D. ananassae; D. me, D. melanogaster; D. ps, D. pseudoobscura; D. si, D. simulans; D. vi, D. virilis; D. ya, D. yakuba; T. ca, T. castanaeum.

Figure 5. Target Specificity of miRNA Family Members

(A) Diagrams of 3′ UTR conservation in six drosophilid genomes (horizontal black bars) and the location of predicted miRNA target sites. Above is the 3′ UTR of the myogenic transcription factor bagpipe (bap) showing the predicted target site for the Brd box miRNA family, miR-4 and miR-79 (black box below the UTR). Alignment of miR-4 and miR-79 illustrates that they share a similar seed sequence (except that mir-4 has one extra 5′ base) but have little 3′ end similarity. Below are the conserved sequences in the3′ UTRs of the pro-apoptotic genes grim and sickle. Predicted target sites for the K Box miRNAs miR-11, miR-2b, and miR-6 are shown below the UTR. Alignment of miR-11, miR-2b, and miR-6 illustrates that they share the same family motif but have little similarity in their 3′ ends. (B) The bagpipe (bap) 3′ UTR reporter gene is regulated by miR-4 and miR-79. Alignments of the two miRNAs to the predicted target site show good 8mer seed matches (left). Overexpression of miR-4 or miR-79 under ptcGal4 control downregulated the bagpipe 3′ UTR reporter (right). (C) Left: Alignment of K box miRNAs with the single predicted site in the grim 3′ UTR and regulation by overexpression of miR-2 (top), but not by miR-6 (middle) or miR-11 (bottom). Right: Alignment of K box miRNAs with the two predicted sites in the sickle 3′ UTR. Regulation by overexpression of miR-2 was strong (top), regulation by miR-6 was weaker (middle), and miR-11 had little effect (bottom). (D) Effect of clones of cells lacking dicer-1 on expression of UTR reporters for predicted miRNA-regulated genes. Mutant cells were marked by the absence of β-Gal expression (red). EGFP expression is shown in green. Both channels are shown separately below in black and white. Mutant clones are indicated by yellow arrows. Expression of a uniformly transcribed reporter construct lacking miRNA target sites was unaffected in dicer-1 mutant cells (first column). The UTR reporter for the bantam miRNA target hid was upregulated in the mutant cells (second column). The bagpipe (bap) UTR reporter was upregulated in dicer-1 clones (third column). The grim (fourth column) and sickle (fifth column) UTR reporters were upregulated.

Figure 6. Computational Analysis of Target Site Occurrence

(A) Genome-wide occurrence of conserved 5′ seed matches. Histogram showing the ratio of 5′ seed matches for a set of 49 5′ non-redundant miRNAs and the average of their ten completely shuffled variants for different seed types (black bars). A ratio of one (red line) indicates no difference between the miRNA and its shuffled variants. The same ratio for mutated miRNAs and their shuffled variants shows no signal (white bars). The inset depicts shuffling of the entire miRNA sequence (wavy purple line). (B) Target site conservation between D. melanogaster and D. pseudoobscura. Histogram showing the average conservation of the 3′ UTR sequence (16 nt) upstream of a conserved 8mer seed match that would pair to the miRNA 3′ end. All sites were binned according to their conservation, and the percentage of sites in each bin is shown for sites identified by 49 5′ non-redundant miRNA sequences (grey) and their shuffled control sequences (black, error bars indicate one standard deviation). (C) 3′ pairing preferences for miR-7 target sites. Histogram showing the distribution of 3′ pairing energies for miR-7 (red bars) and the average of 50 3′ shuffled variants (black bars) for all sites identified genome-wide by 6mer 5′ seed matches for miR-7. The inset illustrates shuffling of the 3′ end of miRNA sequence only (wavy purple line). Because the miRNA 5′ end was not altered, the identical set of target sites was compared for pairing to the 3′ end of real and shuffled miRNAs. (D) 3′ pairing preferences for miRNA target sites. Histograms showing the ratio of the top 1% 3′ pairing energies for the set of 58 3′ non-redundant miRNAs and their shuffled variants. The y-axis shows the number of miRNAs for each ratio. Real miRNAs are shown in red; mutant miRNAs are shown in black. Left are shown combined 8- and 7mer seed sites. Right are shown combined 5- and 6mer seed sites. For combined 8- and 7mer seeds, 1% corresponds to approximately ten sites per miRNA; for combined 6- and 5mer, to approximately 25 sites. The difference between the real and mutated miRNAs improves if fewer sites per miRNA are considered. (E) Non-random signal of 3′ pairing. Plot of the ratio of the number of target sites for the set of 58 3′ non-redundant miRNAs and their shuffled miRNA 3′ ends (y-axis) with 3′ pairing energies that exceed a given pairing cutoff (x-axis). 100% is the pairing energy for a sequence perfectly complementary to the 3′ end. As the required level of 3′ pairing energy increases, fewer miRNAs and their sites remain to contribute to the signal. Plots for the real miRNAs extended to considerably higher 3′ pairing energies than the mutants, but as site number decreases we observe anomalous effects on the ratios, so the curves were cut off when the number of remaining miRNAs fell below five.

Figure 7. Distribution of 3′ Pairing Energies for 8mer Seed Matches

Shown is the distribution (number of sites versus 3′ pairing) for 8mer seed matches identified genome-wide for 58 3′ non-redundant miRNAs (black) compared to a random control using 50 3′ shuffled miRNAs per real miRNA (grey). Note that the distribution for real miRNAs is broader at both the high and low end than the random control and has shoulders close to the peak. The red, blue, and green curves show the effect of subtracting background noise (random matches) from the real matches at three different levels, which reveals the real matches underlying these shoulders.