Weak seed-pairing stability and high target-site abundance decrease the proficiency of lsy-6 and other microRNAs

Abstract

Most metazoan microRNAs (miRNAs) target many genes for repression, but the nematode lsy-6 miRNA is much less proficient. Here we show that the low proficiency of lsy-6 can be recapitulated in HeLa cells and that miR-23, a mammalian miRNA, also has low proficiency in these cells. Reporter results and array data indicate two properties of these miRNAs that impart low proficiency: their weak predicted seed-pairing stability (SPS) and their high target-site abundance (TA). These two properties also explain differential propensities of small interfering RNAs (siRNAs) to repress unintended targets. Using these insights, we expand the TargetScan tool for quantitatively predicting miRNA regulation (and siRNA off-targeting) to model differential miRNA (and siRNA) proficiencies, thereby improving prediction performance. We propose that siRNAs designed to have both weaker SPS and higher TA will have fewer off-targets without compromised on-target activity.

Figure 1

Increasing SPS while decreasing TA imparted typical targeting proficiency to lsy-6 and miR-23 miRNAs. (a) Sequences of miRNAs and target sites tested in reporter assays of this figure. Each miRNA was co-transfected with reporter plasmids as a duplex designed to represent the miRNA paired with its miRNA* strand (Supplementary Fig 1a). (b) Response of reporters with 3′UTRs of predicted lsy-6 targets following co-transfection with lsy-6. As a specificity control, the experiment was also performed using a non-cognate miRNA, miR-1 (grey bars). Geometric means are plotted relative to those of reporters in which the predicted target sites were mutated after also normalizing for the repression observed for miR-1 (grey bars). The mutant sites of this experiment were the cognate sites of Figure 2d. Error bars represent the third largest and third smallest values among 12 replicates from 4 independent experiments. Statistically significant differences in repression by the cognate miRNA compared to that by the non-cognate miRNA are indicated. (*p < 0.01, **p < 0.001, Wilcoxon rank-sum test). (c) Distribution of predicted SPSs for 7mer-m8 sites of 60 conserved nematode miRNA families (Supplementary Table 7). Values were rounded down to the next half-integer unit. (d) SPS distribution for 7mer-m8 sites of 87 conserved vertebrate miRNA families (Supplementary Table 7). (e) Distributions of predicted genome TA for 7mer-m8 3′UTR sites of 60 conserved nematode miRNA families (Supplementary Table 7). Values were rounded up to the next tenth of a unit. (f) Distributions of predicted genome TA for 7mer-m8 3′UTR sites of 87 conserved vertebrate miRNA families (Supplementary Table 7). (g) Response of reporters mutated such that their sites matched the miR-142 seed. The cognate miRNA was the miR-142lsy-6 chimera; non-cognate sites were lsy-6 sites. Otherwise, as in b. (h) As in g, except showing the response to miR-142 transfection. (i) Response of reporters with 3′UTRs of predicted miR-23 targets following co-transfection with miR-23a. Non-cognate sites were for miR-CGCG. Otherwise, as in b. (j) Response of reporters mutated such that their sites matched the seed of miR-CGCG, which was co-transfected as the cognate miRNA. Non-cognate sites were for miR-23. Otherwise, as in i.

Figure 2

Separating the effects of SPS and TA on miRNA targeting proficiency. (a) The relationship between predicted SPS and genomic TA for lsy-6 and the 59 other conserved nematode miRNAs (red squares), and all other heptamers (light blue, blue, dark blue, or purple squares indicating 0, 1, 2, or 3 CpG dinucleotides within the heptamer respectively). TA was defined as the total number of canonical 7–8-nucleotide sites (8mer, 7mer-m8, and 7mer-A1) in annotated 3′UTRs. SPS values were predicted using the respective 7mer-m8 sites. (b) The relationship between predicted SPS and TA in human 3′UTRs for miR-23 and the 86 other broadly conserved vertebrate miRNA families (red squares). Otherwise, as in a. (c) Sequences of miRNAs and target sites tested in reporter assays of this figure. (d) Response of reporters with 3′UTRs of predicted lsy-6 targets mutated such that their sites matched the seed of LTA-lsy-6, which was co-transfected as the cognate miRNA. Non-cognate sites were for lsy-6. Otherwise, as in Figure 1b. (e) 2,6-di-aminopurine (DAP or D)—uracil base pair. (f) Response of reporters used in d after co-transfecting D-LTA-lsy-6 as the cognate miRNA. Otherwise, as in d. (g) Response of reporters used in Figure 1i after co-transfecting D-miR-23a as the cognate miRNA, alongside results for miR-23a that was repeated in parallel. Otherwise, as in Figure 1i.

Figure 3

Impact of TA and SPS on sRNA targeting proficiency, as determined using array data.(a) Distribution of TA_HeLa and predicted SPS for the sRNAs from the 102 array datasets analyzed in this study (orange squares), and sRNAs from datasets that passed the motif-enrichment analysis (red squares). Otherwise, plotted as in Figure 2b. (b) Response of expressed mRNAs with a single 3′UTR site to the cognate sRNA, shown with respect to TA_HeLa and predicted SPS. Fold-change values are plotted according the key to the right of each plot, comparing mRNAs with a single site of the type indicated (and no additional sites to the cognate sRNA elsewhere in the mRNA) to those with no site to the cognate sRNA; note different scales for different plots. In areas of overlap, mean values are plotted. Correlation coefficients and P values are in Table 1. (c) Response of expressed mRNAs with a single ORF site to the cognate sRNA, shown with respect to TA_HeLa and predicted SPS. Otherwise, as in b. (d) Response of mRNAs with the indicated single sites when binning the cognate sRNA by TA_HeLa (top panel) or predicted SPS (bottom panel). The key indicates the data considered, with the first quartiles of the top panel comprising data for sRNAs with the lowest TA_HeLa and those of the bottom panel comprising data for sRNAs with the strongest predicted SPS. Error bars indicate 95% confidence intervals.

Figure 4

Predictive performance of the context+ model, which considers miRNA or siRNA proficiency in addition to site context. (a) Improved predictions for mRNAs with canonical 7–8-nucleotide 3′UTR sites. Predicted interactions between mRNAs and cognate sRNA were distributed into 10 equally populated bins based on total context scores generated using the model indicated (key), with the first bin comprising interactions with the most favorable scores. Plotted for each bin is the mean mRNA change on the arrays (error bars, 95% confidence intervals). (b) Prediction of responsive interactions involving mRNAs with only 3′UTR 6mer sites. Otherwise, as in a. (c) Prediction of responsive interactions involving mRNAs with at least one 8mer ORF site but no 3′UTR sites. Otherwise, as in a. (d) Impact of TA and SPS on siRNA-directed knock-down of the desired target. Efficacy in luciferase activity knock-down is plotted for 2,431 siRNAs transfected into H1299 cells. Efficacy is linearly scaled (key), with positive and negative controls having values of 0.900 and 0.354, respectively.