Viral MicroRNAs Repress the Cholesterol Pathway, and 25-Hydroxycholesterol Inhibits Infection

Abstract

From various screens, we found that Kaposi's sarcoma-associated herpesvirus (KSHV) viral microRNAs (miRNAs) target several enzymes in the mevalonate/cholesterol pathway. 3-Hydroxy-3-methylglutaryl-coenzyme A (CoA) synthase 1 (HMGCS1), 3-hydroxy-3-methylglutaryl-CoA reductase (HMGCR [a rate-limiting step in the mevalonate pathway]), and farnesyl-diphosphate farnesyltransferase 1 (FDFT1 [a committed step in the cholesterol branch]) are repressed by multiple KSHV miRNAs. Transfection of viral miRNA mimics in primary endothelial cells (human umbilical vein endothelial cells [HUVECs]) is sufficient to reduce intracellular cholesterol levels; however, small interfering RNAs (siRNAs) targeting only HMGCS1 did not reduce cholesterol levels. This suggests that multiple targets are needed to perturb this tightly regulated pathway. We also report here that cholesterol levels were decreased in de novo-infected HUVECs after 7 days. This reduction is at least partially due to viral miRNAs, since the mutant form of KSHV lacking 10 of the 12 miRNA genes had increased cholesterol compared to wild-type infections. We hypothesized that KSHV is downregulating cholesterol to suppress the antiviral response by a modified form of cholesterol, 25-hydroxycholesterol (25HC). We found that the cholesterol 25-hydroxylase (CH25H) gene, which is responsible for generating 25HC, had increased expression in de novo-infected HUVECs but was strongly suppressed in long-term latently infected cell lines. We found that 25HC inhibits KSHV infection when added exogenously prior to de novo infection. In conclusion, we found that multiple KSHV viral miRNAs target enzymes in the mevalonate pathway to modulate cholesterol in infected cells during latency. This repression of cholesterol levels could potentially be beneficial to viral infection by decreasing the levels of 25HC.IMPORTANCE A subset of viruses express unique microRNAs (miRNAs), which act like cellular miRNAs to generally repress host gene expression. A cancer virus, Kaposi's sarcoma-associated herpesvirus (KSHV, or human herpesvirus 8 [HHV-8]), encodes multiple miRNAs that repress gene expression of multiple enzymes that are important for cholesterol synthesis. In cells with these viral miRNAs or with natural infection, cholesterol levels are reduced, indicating these viral miRNAs decrease cholesterol levels. A modified form of cholesterol, 25-hydroxycholesterol, is generated directly from cholesterol. Addition of 25-hydroxycholesterol to primary cells inhibited KSHV infection of cells, suggesting that viral miRNAs may decrease cholesterol levels to decrease the concentration of 25-hydroxycholesterol and to promote infection. These results suggest a new virus-host relationship and indicate a previously unidentified viral strategy to lower cholesterol levels.

Keywords: Kaposi's sarcoma-associated herpesvirus; cholesterol; human herpesviruses; microRNA.

FIG 1

Schematic diagram of the mevalonate pathway with viral miRNA targets. Individual miRNAs that repress gene expression are shown.

FIG 2

KSHV viral miRNAs target several enzymes in the mevalonate pathway. (A) HUVECs were transfected with either 30 nM siRNA or miRNA mimics. Total protein lysates were harvested at 48 h posttransfection (hpt) for immunoblotting with HMGCS1 and actin. combi, combination of 3 miRNA mimics transfected (n = 5). (B) HUVECs were transfected with KSHV viral miRNA mimics, and HMGCR gene expression was measured using RT-qPCR (n = 3). (C) Luciferase (Luc) reporter assay with full-length 3′ UTR of HMGCR cloned into a reporter plasmid (Renilla luciferase) and cotransfected with miRNA mimics in HEK-293 cells. Luciferase signal was normalized to an internal luciferase control (firefly luciferase), luciferase empty vector control, and negative-control miRNA (miR Neg) (n = 4). (D) Predicted miRNA target sites in the HMGCR 3′ UTR were identified using miRanda software. (E) HUVECs were transfected with KSHV viral miRNA mimics, and total protein lysates were harvested at 48 hpt for immunoblotting with anti-FDFT1 and antiactin (n = 3). (F) Luciferase reporter assay with full-length 3′ UTR of FDFT1 was performed as described above (n = 3). (G) Predicted viral miRNA target sites in FDFT1 3′ UTR and coding DNA sequence (CDS) were identified using miRanda software. For graphs, each data point represents a biological replicate, with error bars shown as means ± standard deviation (SD). Student’s t test was performed to assess statistical significance: *, P < 0.05; **, P < 0.01; ***, P < 0.001; ****, P < 0.0001.

FIG 3

KSHV latent infection perturbs cellular cholesterol levels. (A) HUVECs were transfected with either 30 nM siRNA or miRNA mimics. The graph shows data points for experiments normalized to negative control (siCtrl, miR Neg) (n = 3). (B and C) Total (B) and free (C) cholesterol assays on HUVECs infected with BCBL1-derived virus. Cholesterol samples were extracted and assayed as described above. Data points are normalized to the uninfected control (Mock). As a positive control, HUVECs were treated with 2 mM MBCD (cholesterol inhibitor) for 2 h prior to harvest (n = 4). (D and E) Total (D) and free (E) cholesterol assays on iSLK cell lines infected with either wild-type KSHV or mutant virus lacking the miRNA cluster (ΔmiR KSHV). Cells were harvested and assayed as described above (n = 5 to 6). Statistical significance: n.s., not significant; *, P < 0.05; **, P < 0.01; ***, P < 0.001; ****, P < 0.0001.

FIG 4

CH25H and 25HC during KSHV infection. (A) CH25H gene expression measured by RT-qPCR assay from de novo-infected HUVECs, from the B cell line MC116, and from iSLK cells infected with either wild-type or ΔmiR mutant KSHV. As an uninfected control for iSLK, an SLK cell line was assayed (n = 3). (B) HUVECs were transfected with a KSHV viral miRNA mimics, and CH25H gene expression was measured using RT-qPCR (n = 3). (C and D) HUVECs were pretreated with 25HC or vehicle only (ethanol) at 2 h prior to infection with BCBL1-derived virus supernatant. mRNA samples were harvested at 2 dpi. LANA (n = 5) and RTA (n = 4) mRNA expression was measured using the RT-qPCR assay and normalized to β-actin. (E) HUVEC pretreatment and infection as described above. At indicated time points, cells were washed and trypsinized to remove virions adhering to cell surface. DNA was extracted, and LANA DNA was measured using qPCR and normalized to human DNA (n = 4). **, P < 0.01.

FIG 5

25HC’s effects on viability and IL-6 expression. (A) Micrographs of HUVECs pretreated with 25HC and infected as described in the legend to Fig. 4. (B) HUVECs were treated with 25HC and infected with KSHV, with cell viability measured by WST-1 assays (n = 3). (C) RNA samples used in Fig. 4C and D were also used to measure IL-6 mRNA expression (n = 3). Veh, vehicle. *, P < 0.05.