Distance constraints between microRNA target sites dictate efficacy and cooperativity

Abstract

MicroRNAs (miRNAs) have the potential to regulate the expression of thousands of genes, but the mechanisms that determine whether a gene is targeted or not are poorly understood. We studied the genomic distribution of distances between pairs of identical miRNA seeds and found a propensity for moderate distances greater than about 13 nt between seed starts. Experimental data show that optimal down-regulation is obtained when two seed sites are separated by between 13 and 35 nt. By analyzing the distance between seed sites of endogenous miRNAs and transfected small interfering RNAs (siRNAs), we also find that cooperative targeting of sites with a separation in the optimal range can explain some of the siRNA off-target effects that have been reported in the literature.

Figure 1.

Pairs of identical miRNA seeds have a distance-dependent conservation pattern. (a) Pairs of miRNA hexamer seeds are underrepresented for distances of 13 nt or less. We counted the number of times the pairs of conserved miRNA hexamer seed sites were separated by a given number of nucleotides and compared the relative occurrences with the corresponding occurrences for random controls (see the Materials and methods section). Very close pairs of identical miRNA seeds occur much less frequently than the random controls do. (b) To determine the significance of the underrepresentation, we ran a randomization experiment that compared the relative occurrences of pairs of conserved miRNA seeds closer than a given distance threshold with the corresponding occurrences for random controls (see the Materials and methods section). The graph shows for increasing distance cutoffs, the average of the relative miRNA occurrences divided by the relative random occurrences (black; primary y-axis) and the estimated P-values (gray; secondary y-axis). The underrepresentation of miRNA seeds holds up to a distance of 12 nt after which the P-values increase rapidly. (c) The smoothed distance distribution indicates that miRNA seed sites are overrepresented for distances between 16 and 20 nt. We computed the moving averages of the miRNA and random distance distributions from (a) (moving average window size 5). In the resulting distribution, the largest deviations from random, except for the underrepresentation of miRNAs at distances less than 13 nt are the overrepresentation of miRNAs for distances between 16 and 20 nt. The graph in the upper right corner shows an excerpt of the distance distribution in a linear scale on the x-axis. (d) Pairs of heptamers are more likely to be conserved together when the distance is less than 130. The graph shows the distribution of distances between two consecutive non-overlapping occurrences of conserved miRNA heptamers (gray solid line), and the corresponding average distribution for simulated random conservation (black solid line). The real conservation distribution differs from the random distribution for distances between 10 and 130. Outside this range, the real conservation distribution approaches the random distribution (graph in upper right corner). The graph is smoothed by using a moving average with a window size of 5; see Supplementary Figure 5 for the original distribution.

Figure 2.

The distance between seed sites affects target down-regulation. We cloned different let-7 target site configurations into the 3′ UTR of Renilla luciferase reporter constructs, transfected the constructs along with an anti-let-7a 2′O-methyl RNA into HeLa cells [(b) and (e)] and a let-7 mimic in HEK293 cells [(c) and (f)], and measured the change in luciferase expression compared to irrelevant controls. (a) Schematic depiction of target sites with distances of 9, 13, 17, 21, 24, 35, and 70 between seed starts. (b) Ratio of increased expression in HeLa; and (c) percentage knockdown in HEK293 normalized to a control without a seed site for targets shown in (a). Asterisks (*) mark values that are significantly different from that of the seed sites with distance of 17 [Student's t-test, confidence level 0.05; (b) P-values for single, 9, 13, 21, 24, 35, 70, and none were 1E-5, 2E-4, 0.01, 0.8, 0.1, 0.3, 0.002, and 1E-8; (c) P-values for single, 9, 13, 35, 70, and none were 2E-4, 3E-5, 0.02, 0.5, 0.01, and 5E-8 (c)]. (d) Schematic depiction of one target site that has three optimally spaced seeds and another that has 50 nt between two optimally spaced pairs. (e) Ratio of increased expression in HeLa and (F) percentage knockdown in HEK293 normalized to control without a seed site for targets shown in (d). In (b), (c), (e), and (f), columns are the average of at least three independent experiments carried out in triplicate; error bars are standard deviations.

Figure 3.

Polycistronic miRNAs from the MCM7 intron show no collaborative effect on the predicted endogenous target BMPR2, but produce 30% down-regulation when targets are moved closer. (a) Schematic representation of the 3′ UTR of BMPR2 and the predicted targets of mir-106b, mir-93, and mir-25 from the MCM7 intron. (b) The percentage knockdown of the wild-type mir-106b-25 polycistron (mir-106b-25 wt) and a modified polycistron containing irrelevant controls (mir-106b-25 irr) on a Renilla luciferase reporter harboring 1.2 kb of the endogenous target (BMPR2 3′UTR) and the modified target (BMPR2-Super). Columns are the average of three independent experiments carried out in duplicate; error bars depict standard deviations.

Figure 4.

Short interfering RNA seed sites are located farther from miRNA seed sites in off-targeted genes than in other genes containing siRNA seed sites. The graphs show the smoothed (sliding window of size 5) distance distribution for the distance between siRNA hexamer seed sites and the closest non-overlapping miRNA hexamer seed site in off-targeted 3′ UTRs (black) and other 3′ UTRs that contain siRNA seed sites (gray). The graph in the upper right corner shows an excerpt of the distance distribution in a linear scale on the x-axis. The miRNA seeds are the seeds from the highly conserved miRNAs defined by Lewis et al. (20).

Figure 5.

Short interfering RNA seed sites are located farther from seed sites of expressed miRNAs in off-targeted genes than in reference genes, and are more often located at an optimal distance to expressed miRNAs in off-targeted genes than in reference genes. The miRNA seeds are those previously reported to be expressed in HeLa cells (41). See the legend of Figure 4 for additional information.