High potency silencing by single-stranded boranophosphate siRNA

Abstract

In RNA interference (RNAi), double-stranded short interfering RNA (ds-siRNA) inhibits expression from complementary mRNAs. Recently, it was demonstrated that short, single-stranded antisense RNA (ss-siRNA) can also induce RNAi. While ss-siRNA may offer several advantages in both clinical and research applications, its overall poor activity compared with ds-siRNA has prevented its widespread use. In contrast to the poor gene silencing activity of native ss-siRNA, we found that the silencing activity of boranophosphate-modified ss-siRNA is comparable with that of unmodified ds-siRNA. Boranophosphate ss-siRNA has excellent maximum silencing activity and is highly effective at low concentrations. The silencing activity of boranophosphate ss-siRNA is also durable, with significant silencing up to 1 week after transfection. Thus, we have demonstrated that boranophosphate-modified ss-siRNA can silence gene expression as well as native ds-siRNA, suggesting that boranophosphate-modified ss-siRNAs should be investigated as a potential new class of therapeutic agents.

Figure 1

Sequence and structure of interfering RNA. (A) Structure of native (left) and boranophosphate (Sp isomer, right) ribonucleic acid backbone linkages. (B) Native and modified siRNA species. Modified nucleotides are shown in boldface. For control siRNAs, the inverted sequence is underlined. Arrows indicate the linkage opposite the expected target cleavage site. A, antisense strand; S, sense strand; b, boranophosphate; n, native; a, adenosine; c, cytidine; u, uridine; 3, adenosine, cytidine and uridine.

Figure 2

Position specific effects of boranophosphate modifications on silencing activity of ss-siRNAs. (A) Percent inhibition of EGFP fluorescence in cells treated with native or boranophosphate EGFP1 siRNA at 25 nM. To account for variations in transfection efficiency, the results of each individual experiment were normalized to results for native siRNA-treated cells in that experiment. Error bars represent the standard error. (B) Percent inhibition of EGFP fluorescence in cells treated with native or boranophosphate modified EGFP2 siRNA at 12.5 nM. Error bars represent the standard error. ds-siRNA is represented by closed bars. ss-siRNAs are represented by gray bars. A, antisense strand; S, sense strand; b, boranophosphate; n, native; a, adenosine; c, cytidine; u, uridine; 3, adenosine, cytidine and uridine; cont, inverted control sequence.

Figure 3

Effect of boranophosphate modification on silencing dose response of ss-siRNAs. Silencing of EGFP fluorescence in cells treated with native or boranophosphate EGFP1 siRNA over a range of concentrations. (A) The activity of each siRNA at 50 nM is normalized to an arbitrary value of 100. (B) Raw dose response data. Error bars represent the standard error. AⁿSⁿ is represented by closed circles, Aⁿ by open circles, ${\text{A}}_{\text{c}}^{\text{b}}$ by closed triangles and ${\text{A}}_{\text{ac}}^{\text{b}}$ by open triangles. A, antisense strand; S, sense strand; b, boranophosphate; n, native; a, adenosine; c, cytidine.

Figure 4

Effect of BP modification on the duration of ss-siRNA silencing. Percent inhibition of EGFP fluorescence over time in cells treated with native ds-siRNA or native/BP ss-siRNA (all EGFP1 sequence) at 25 nM. To examine the relative change in activity over time, the degree of silencing at 1 day after transfection for each siRNA was set at an arbitrary value of 100. Error bars represent the standard error. AⁿSⁿ is represented by closed circles, Aⁿ by open circles, ${\text{A}}_{\text{c}}^{\text{b}}$ by closed triangles and ${\text{A}}_{\text{ac}}^{\text{b}}$ by open triangles. A, antisense strand; S, sense strand; b, boranophosphate; n, native; a, adenosine; c, cytidine.

Figure 5

Effect of single-stranded BP siRNA on EGFP mRNA and protein levels. (A) Northern blot of total cytoplasmic RNA from mock transfected cells (M) or cells transfected with EGFP1 siRNA. (B) Percent reduction in mRNA (closed bars) and protein (gray bars) levels as determined by northern and FACS analysis. Samples of cells from the same population were used for both analyses. EGFP mRNA levels were normalized to β-actin expression. A, antisense strand; S, sense strand; n, native; b, boranophosphate; a, adenosine; c, cytidine; cont, EGFP1 control sequence.

Figure 6

Silencing by boranophosphate ss-siRNA is Ago2-dependent. (A) Cells we mock-transfected with Oligofectamine alone (mock) or transfected with control ds-siRNA (control) or ds-siRNA targeted to Ago2 (Ago2). Ago2 mRNA levels were measured by quantitative RT–PCR and normalized to GAPDH mRNA levels. (B) Cells were transfected with control ds-siRNA (closed bars) or ds-siRNA targeted to Ago2 (gray bars). Twenty-four hours later, cells were retransfected with control ds-siRNA, EGFP1 native ds-siRNA (AⁿSⁿ) or EGFP1 BP ss-siRNA (${\text{A}}_{\text{ac}}^{\text{b}}$). EGFP fluorescence was measured by flow cytometry. Data were normalized with silencing by anti-EGPF siRNAs after initial transfection with control siRNA set at an arbitrary value of 100. Error bars represent standard error.

Figure 7

Nuclease stability of native and boranophosphate RNA. ss-ssRNAs were incubated with RNase A for the times indicated and then assessed for degradation by agarose gel electrophoresis. b, boranophosphate; n, native; A, adenosine; C, cytidine; U, uridine; 3, adenosine, cytidine and uridine.