Antiviral immunity via RIG-I-mediated recognition of RNA bearing 5'-diphosphates

Abstract

Mammalian cells possess mechanisms to detect and defend themselves from invading viruses. In the cytosol, the RIG-I-like receptors (RLRs), RIG-I (retinoic acid-inducible gene I; encoded by DDX58) and MDA5 (melanoma differentiation-associated gene 5; encoded by IFIH1) sense atypical RNAs associated with virus infection. Detection triggers a signalling cascade via the adaptor MAVS that culminates in the production of type I interferons (IFN-α and β; hereafter IFN), which are key antiviral cytokines. RIG-I and MDA5 are activated by distinct viral RNA structures and much evidence indicates that RIG-I responds to RNAs bearing a triphosphate (ppp) moiety in conjunction with a blunt-ended, base-paired region at the 5'-end (reviewed in refs 1, 2, 3). Here we show that RIG-I also mediates antiviral responses to RNAs bearing 5'-diphosphates (5'pp). Genomes from mammalian reoviruses with 5'pp termini, 5'pp-RNA isolated from yeast L-A virus, and base-paired 5'pp-RNAs made by in vitro transcription or chemical synthesis, all bind to RIG-I and serve as RIG-I agonists. Furthermore, a RIG-I-dependent response to 5'pp-RNA is essential for controlling reovirus infection in cultured cells and in mice. Thus, the minimal determinant for RIG-I recognition is a base-paired RNA with 5'pp. Such RNAs are found in some viruses but not in uninfected cells, indicating that recognition of 5'pp-RNA, like that of 5'ppp-RNA, acts as a powerful means of self/non-self discrimination by the innate immune system.

Fig. 1. RNA from reovirus and L-A virus requires 5′-phosphates to induce a RIG-I-dependent response.

(a-d) RNA samples were tested in an IFN-β promoter reporter assay in HEK293 cells: (a) RNA from reoT3D- or IAV-infected cells +/−CIP, (b) reoT3D vRNA +/−CIP, (c) reoT1L genome segments, and (d) reoT3D segments +/− CIP. For (b) and (d), RNA integrity was verified by gel electrophoresis. (e) IFN-α levels from transfected DCs. (f-h) IFN-α levels (f) or relative expression (RE) of ifit1 (g-h) from control (MDA5^+/−), RIG-I^−/−, MDA5^−/− or RIG-I/MDA5^−/− MEFs transfected with reo vRNA (f,h) or isolated reoT1L L segments (g) +/− CIP. Water and ppp-IVT-RNA^99nts are controls. For (e-h), cells were treated with ribavirin to block virus replication. (i) Total L-A RNA (genome and transcript), L-A genomes and L-A transcripts were analysed as in (a). (j) Total L-A RNA was analysed as in (e). (k-l) Total L-A RNA +/− shrimp alkaline phosphatase (SAP) was analysed as in (a) or transfected into MDA5^−/− DCs and analysed as in (g). Water, ppp-IVT-RNA^99nts, poly(dA:dT) and cyclic-di-GMP were included as controls. All experiments were performed at least twice. For PCR and IFN-α data, the mean (±s.d.) of triplicate technical replicates is shown (* = not detected).

Fig. 2. RIG-I associates with 5′-diphosphate-bearing viral RNAs.

(a) Left, Experimental procedure. Right, IFN-β promoter reporter assay of RNA from RIG-I-precipitates. (b-c) (b, left) Experimental procedure using the following input RNA: reoT1L or reoT3D vRNA, reoT3D S or L segments, RNA isolated from reoT1L-infected cells, or total L-A RNA. (b, left) IFN-β promoter reporter assay or (b, right) ifnb1 expression from IFN-pre-treated MDA5^−/− DCs (c) following transfection of RNA from RIG-I-precipitates treated +/−CIP. For PCR data, the mean (±s.d) of triplicate technical replicates is shown. All experiments were performed at least twice.

Fig. 3. De novo generated base-paired 5′-diphosphate RNA triggers RIG-I.

(a) Experimental procedure used to generate 5′pp-IVT-RNA^25nts. (b-c) IFN-β promoter reporter assay of IVT-RNA^25nts+/−AS (b) and pp-IVT-RNA^25nts+AS +/−CIP (c). (d-g) IFN-α levels (d,f,g) or ifit1 expression (e) from DCs (d) MEFs (e,g) or human PBMCs (f) transfected with indicated RNAs. Water, poly(dA:dT) or cyclic-di-GMP were included as controls (*not detected). For (f), the value obtained for 800ng/ml of [ppp-RNA^24nts+AS] was set to 100%. Mean values (+s.d.) from four donors are shown (***P<0.0001). (h) AlphaScreen of RIG-I and synthetic RNA ligands (±s.d.). Units are proportional to RIG-I-ligand complex concentration. One experiment of two is shown.

Fig. 4. RIG-I is required for control of reovirus infection.

(a-c) ifit1 (a) or reovirus gene segment S4 genome expression ([b-c], right panel) and copy number per μg of RNA ([b-c], left panel) in reoT3D infected DCs (a-b) or control (RIG-I^+/−) MDA5^−/−, RIG-I^−/−, and MDA5/RIG-I^−/− MEFs. Mean of triplicate biological replicates (±s.d.) is shown. Cyclic-di-GMP was included as a control. **P≤0.01 (unpaired t-test). (d-e) Abundance of reovirus gene segment S4 determined as in (b) from intestine (d) and MLN (e) of mice following peroral infection with reovirus strain T3SA+. Data were pooled from two experiments. Each symbol represents an individual mouse. Line represents the mean of each group. *P<0.03 and **P<0.008 (unpaired t-test).