A virus-encoded inhibitor that blocks RNA interference in mammalian cells

Abstract

Nodamura virus (NoV) is a small RNA virus that is infectious for insect and mammalian hosts. We have developed a highly sensitive assay of RNA interference (RNAi) in mammalian cells that shows that the NoV B2 protein functions as an inhibitor of RNAi triggered by either short hairpin RNAs or small interfering RNAs. In the cell, NoV B2 binds to pre-Dicer substrate RNA and RNA-induced silencing complex (RISC)-processed RNAs and inhibits the Dicer cleavage reaction and, potentially, one or more post-Dicer activities. In vitro, NoV B2 inhibits Dicer-mediated RNA cleavage in the absence of any other host factors and specifically binds double-stranded RNAs corresponding in structure to Dicer substrates and products. Its abilities to bind to Dicer precursor and post-Dicer RISC-processed RNAs suggest a mechanism of inhibition that is unique among known viral inhibitors of RNAi.

FIG. 1.

Assay for RNAi in mammalian cells. 293T cells were cotransfected with plasmids encoding eGFP and shRNAs, and the reduction in eGFP levels was determined. Diagram of the destabilized eGFP construct used as a reporter for RNAi activity (top panel). Histogram showing the intensity of eGFP fluorescence in the presence of an shRNA targeting eGFP (anti-eGFP HP) or an irrelevant shRNA (irrel. HP) (middle panel). The fold reduction in the geometric mean fluorescent intensity is plotted as a ratio of eGFP levels from cells expressing an irrelevant shRNA versus an anti-eGFP shRNA (bottom panel).

FIG. 2.

NoV B2 inhibits RNAi and the Dicer cleavage reaction in a dose-dependent fashion in mammalian cells. (A) This assay was performed in an identical fashion to that in Fig. 1, except in the presence or absence of NoV B2. Histogram showing the intensity of eGFP in the presence of various anti-eGFP shRNA construct/NoV B2 construct ratios (top panel). The fold reduction in geometric mean fluorescent intensity of eGFP is plotted as in Fig. 1, in the presence (NoV B2) or absence (vector) of NoV B2 (bottom panel). (B) Northern blot showing the mRNA levels of eGFP when cotransfected with anti-eGFP shRNA or an irrelevant shRNA in the presence (B2) or absence (Vec) of multiple concentrations of NoV B2. (C) Northern blot showing levels of the pre-Dicer precursor shRNA and the post-Dicer siRNA. RNA was harvested from a portion of the cells analyzed in panel A, blotted, and probed with radioactive oligonucleotides that correspond to the target sites of siRNAs produced from anti-eGFP shRNA or irrelevant anti-Luc shRNA. Locations of bands corresponding to shRNA and siRNA are indicated with cartoons on the right side (top panel). Distances of migration of various-sized oligonucleotides are indicated on left side (top panel). An ethidium bromide-stained gel of low-molecular-weight RNA is shown as a loading control (middle panel). The amount of phosphorimaging-quantified signal is plotted as a ratio of shRNA (HP) to siRNA (bottom panel).

FIG. 3.

NoV B2 inhibits RNAi induced by siRNAs. This assay was performed similar to those in Fig. 1 and 2A, except siRNAs were cotransfected instead of shRNAs. Histogram showing the intensity of eGFP in the presence of either 50 nM or 10 nM anti-eGFP siRNA or irrelevant siRNA (top panel). The fold reduction in geometric mean fluorescent intensity of eGFP is plotted as in Fig. 1 and 2 in the presence (NoV B2) or absence (vector) of NoV B2 (bottom panel).

FIG. 4.

Stable expression of NoV B2. (A) Immunofluoresence microscopy showing cytoplasmic localization of GFP-B2. (B) Northern blot analysis of small RNAs recognized by anti-Let-7-D probe. The gray arrow indicates the migration of the pre-miRNA (predicted ∼87-nt, pre-Let7-D). Lanes include parental cell line (P) or cells that express GFP-B2 clones 4, 6, and 9 (cl. 4, cl. 6, and cl. 9). Size markers and ethidium bromide loading controls are similar to those in Fig. 2. (C) Northern blot analysis with probe that recognizes the antisense strand of the anti-luciferase shRNA. Parental (P) cells or stable clones expressing GFPB2 (cl. 4, cl. 6, and cl. 9) were transfected with a plasmid that expresses anti-luciferase shRNA, lysates were harvested, and Northern blot analysis was conducted. Cartoons and arrows indicate the 49-nt shRNA and ∼20-nt antisense RNA. (D) Northern blot analysis of RNA precipitated with GFP-B2. Cells expressing high levels of GFP-B2 were transfected with anti-luciferase shRNA, and lysates were immunoprecipitated with antibody that recognizes GFP-B2 oreither of two negative controls (neg. 1 and 2) and blotted with probe that recognizes either the antisense (left panel) or sense (right panel) strand of the shRNA. Cartoons and arrows indicate the 49-nt shRNA and ∼20-nt antisense (black) or sense (gray) strand RNAs. (E and F) Cells expressing high levels of GFP (G) or GFP-B2 (B) were transfected with anti-luciferase shRNA (+), and lysates were immunoprecipitated with antibody that recognizes GFP. (E) Western blot of immunoprecipitates showing levels of protein precipitated. *, faster-migrating band that is likely a degradation product. (F) Northern blot showing shRNA and ∼20-nt processed RNAs (indicated with cartoons on right). RNA was obtained from immunoprecipitated protein complexes (I.P.) or from 10% of the cells used to generate lysate used for the immunoprecipitation reaction (input). Note: as expected, only transfected input (G+ and B+) and the immunoprecipitated GFP-B2 (B+) lanes displayed significant reactivity with the probe.

FIG. 5.

NoV B2 binds specifically to dsRNA and inhibits the Dicer cleavage reaction in vitro. (A) Gel shift of a 36-mer, perfectly base-paired, double-stranded RNA hairpin probe, showing the concentration dependence (left panel) and in the presence of various competitors (right panel). Purified GST-NoV B2 or GST was mixed with in vitro-transcribed radiolabeled RNA, and complexes were resolved on a 4% native acrylamide gel and visualized by autoradiography. (B) Gel shift of in vitro-transcribed pre-Let7-D and pre-Mir-21 pre-miRNA probes. Experimental conditions were identical to those for panel A, except the indicated probes were used. (C) Gel shift of a labeled siRNA probe. Lysates from cells expressing GFP or GFP-B2 were incubated with probe in the presence or absence of anti-eGFP antibody. The gray arrow indicates complexes supershifted to the well. (D) In vitro Dicer cleavage reaction of the same probe used for panel A (top panel). Purified human Dicer was incubated with RNA probes used in panel A in the presence or absence of purified GST-NoV B2 or GST. The amount of signal is plotted as a ratio of 80-nt substrate to ∼21- and ∼36-nt product, relative to the reaction without any inhibitor (bottom panel). (E) In vitro Dicer cleavage reaction of a pre-miRNA. In vitro-transcribed pre-miRNA (pre-Let7-D) was incubated with purified Dicer. The predicted ∼87-nucleotide (pre-Let7-D) substrate and ∼21-nucleotide product are indicated.