Analysis of the interaction of primate retroviruses with the human RNA interference machinery

Abstract

The question of whether retroviruses, including human immunodeficiency virus type 1 (HIV-1), interact with the cellular RNA interference machinery has been controversial. Here, we present data showing that neither HIV-1 nor human T-cell leukemia virus type 1 (HTLV-1) expresses significant levels of either small interfering RNAs or microRNAs in persistently infected T cells. We also demonstrate that the retroviral nuclear transcription factors HIV-1 Tat and HTLV-1 Tax, as well as the Tas transactivator encoded by primate foamy virus, fail to inhibit RNA interference in human cells. Moreover, the stable expression of physiological levels of HIV-1 Tat did not globally inhibit microRNA production or expression in infected human cells. Together, these data argue that HIV-1 and HTLV-1 neither induce the production of viral small interfering RNAs or microRNAs nor repress the cellular RNA interference machinery in infected cells.

FIG. 1.

MT-2 and ACH-2 cells express readily detectable levels of viral mRNAs. Total RNA samples were prepared from the HTLV-1-infected MT-2 cell line and the HIV-1-infected ACH-2 cell line, in the latter case either before or after PMA induction. Northern blot analyses were performed using random-primed probes specific for the viral LTRs. All predicted viral mRNAs, including genome-length transcripts, were detected in both MT-2 cells (A) and ACH-2 cells (B). Two exposures are provided for the ACH-2 mRNA Northern blot, to allow the visualization of the level of viral mRNAs produced in both the presence and absence of PMA. The lower panels show photographs of ethidium bromide stains of rRNA bands from the gels used for these Northern blot analyses and represent loading controls.

FIG. 2.

Summary of the identities of small RNAs recovered from MT-2 or ACH-2 cells. RNAs of 18 to 24 nt in size were cDNA cloned from MT-2 and ACH-2 cells using standard procedures. Totals of 698 MT-2- and 625 ACH-2-derived cDNAs were sequenced and identified by reference to GenBank and miRBase. No small RNAs of viral origin were recovered. ncRNAs, noncoding RNAs.

FIG. 3.

HIV-1-infected PBMCs fail to express detectable levels of the proposed vsiRNA#1 siRNA. (A) Structure of a hypothetical HIV-1 RNA stem-loop proposed by Bennasser et al. (3). (B) The sequence of the proposed Bennasser stem-loop as found in HIV-1 isolate NL4-3. Differences in sequence are indicated in gray. (C) PBMCs were infected with the NL4-3 laboratory strain of HIV-1 or the primary QH0515 isolate and then cultured for 6 days to allow the virus to spread through the culture. At this point, p24 ELISA assays indicated a viral load of 78 ng/ml of p24 in the NL4-3-infected cultures and 76 ng/ml in the QH0515 culture. Total RNA was isolated from the infected cells and uninfected control PBMCs and analyzed by Northern blotting for expression of the proposed 5′ and 3′ arms of the vsiRNA#1 siRNA, using synthetic probes complementary to the NL4-3 genomic sequence. Synthetic forms of these proposed HIV-1 siRNAs were loaded onto the blot as positive controls at a level equivalent to ∼300 copies per PBMC. The blot was then stripped and rehybridized using the HIV-1 LTR-specific probe described in the Fig. 1 legend. The cellular U6 RNA was used as a loading control.

FIG. 4.

Retroviral transcriptional transactivators fail to inhibit RNAi in human cells. 293T cells were cotransfected with vectors expressing HA-tagged forms of the cellular proteins TRIM5α and β-arrestin. The cells were also cotransfected with pSuper-based expression plasmids that produce shRNAs specific for TRIM-5α (+) or with pSuper as a control (−) and with a vector expressing the indicated wild-type or mutant retroviral transcription factors or with the parental pBC12/CMV as a control (Neg). At 48 h posttransfection, the cells were harvested and lysed and equal amounts of the cellular extracts were used for a Western blot analysis using an HA-specific monoclonal antibody (A). Panel B shows the results of analysis of the same cell extracts but with the amounts of samples loaded normalized to yield equivalent signal intensities, as indicated below the panel.

FIG. 5.

HIV-1 Tat and PFV Tas do not inhibit RNAi mediated by an shRNA. HeLa cells were cotransfected with plasmids expressing Fluc and Rluc together with either pSuper or a pSuper-based plasmid expressing an Fluc-specific shRNA (shFireflyLuc). The HeLa cells were also cotransfected with the indicated levels of a plasmid expressing either a 101-aa form of HIV-1 Tat (pcTat101) (A to C) or PFV Tas (pcTas) (D to F). Panels A and D show the relative levels of Fluc protein expression seen in the absence (Pos) or presence of the pSuper/shFluc expression plasmid. These data are normalized to the level of Fluc expression seen in the absence of both pSuper/shFluc and pcTat101 or pcTas, which was set at 100%. Panels B and E show the raw Rluc expression data derived from the same cultures analyzed in panels A and D. Finally, panels C and F show the Fluc activity data from panels A and D after normalization to the internal control Rluc data presented in panels B and E. The positive control again represents HeLa cells transfected with the Fluc and Rluc expression vectors in the absence of both pSuper/shFluc and pcTat101 or pcTas. The averages and standard deviations of the results of three independent experiments are indicated. RLU, relative light units.

FIG. 6.

The HIV-1 Tat protein does not globally affect cellular miRNA expression. (A) Northern blot analysis of endogenous miR-16 expression in uninduced or PMA-induced ACH-2 cells. Unind, uninduced cells; +PMA, PMA-induced cells. (B) Northern blot analysis of endogenous miR-16 and miR-17-5p expression in 293T cells stably transduced with an HIV-1-based vector, pNL-BLR, that expresses normal levels of HIV-1 Tat, as well as the blr drug resistance gene. The transduced, Tat-expressing cells were cultured for 21 days after selection to allow any pre-existing cellular miRNAs to turn over. 293T cells transduced with the Tat-defective pNL-SIN-CMV-BLR lentiviral vector served as controls. The pre-miRNA forms of miR-16 and miR-17-5p were not detected in either the pNL-BLR- or pNL-SIN-CMV-BLR-transduced 293T cells (data not shown), implying efficient Dicer processing of pre-miRNAs in both the presence and absence of Tat. (C) Northern blot analysis similar to that described for panel B, except that this panel compared cellular miRNA expression in wild-type CEM T cells with that seen in a transduced CEM cell line (CEM/TART) that stably expresses HIV-1 Tat and Rev. Ethidium bromide staining of the gels used in these analyses (lower panels) was performed to confirm equal loading.