The 3' cap-independent translation element of Barley yellow dwarf virus binds eIF4F via the eIF4G subunit to initiate translation

Abstract

The 3' cap-independent translation element (BTE) of Barley yellow dwarf virus RNA confers efficient translation initiation at the 5' end via long-distance base pairing with the 5'-untranslated region (UTR). Here we provide evidence that the BTE functions by recruiting translation initiation factor eIF4F. We show that the BTE interacts specifically with the cap-binding initiation factor complexes eIF4F and eIFiso4F in a wheat germ extract (wge). In wge depleted of cap-interacting factors, addition of eIF4F (and to a lesser extent, eIFiso4F) allowed efficient translation of an uncapped reporter construct (BLucB) containing the BTE in its 3' UTR. Translation of BLucB required much lower levels of eIF4F or eIFiso4F than did a capped, nonviral mRNA. Both full-length eIF4G and the carboxy-terminal half of eIF4G lacking the eIF4E binding site stimulated translation to 70% of the level obtained with eIF4F, indicating a minor role for the cap-binding protein, eIF4E. In wge inhibited by either BTE in trans or cap analog, eIF4G alone restored translation nearly as much as eIF4F, while addition of eIF4E alone had no effect. The BTE bound eIF4G (Kd = 177 nm) and eIF4F (Kd = 37 nm) with high affinity, but very weakly to eIF4E. These interactions correlate with the ability of the factors to facilitate BTE-mediated translation. These results and previous observations are consistent with a model in which eIF4F is delivered to the 5' UTR by the BTE, and they show that eIF4G, but not eIF4E, plays a major role in this novel mechanism of cap-independent translation.

FIGURE 1.

Identification of BTE-interacting proteins from wheat germ extract. (A) Secondary structure of BTE105 RNA (right) and the stem–loop in the 5′UTR (SL-D) to which it base pairs (indicated by dashed lines) (Guo et al. 2001). In mutant BTEBF (inset), the BamHI₄₈₃₇ site (nucleotide 4837) is disrupted by insertion of a GAUC duplication that abolishes BTE function. (B) BTE-interacting proteins (BTEIPs) from wheat germ extract (wge) identified using biotin-labeled RNAs as bait and magnetic streptavidin beads to pull down the BTEIPs. Proteins were separated by 5% PAGE and silver stained. (Lane 1) Molecular weight markers of the indicated kDa at left; (lane 2) total wge protein; (lanes 3–6) unbound proteins obtained after indicated number of low-salt washes of bead-bound BTE RNA. RNA bait (lanes 7–11) show proteins that remained bound to the indicated RNA after washes. STNV TED consists of nucleotides 621–741 of STNV RNA. (Lane 12) Recombinant eIFiso4E and eIFiso4G. Dots to the left of lane 7 indicate BTE105-interacting proteins that comigrate with eIFiso4E and eIFiso4G. Expected Mobilities of eIF4G (> 200 kDa) and eIF4E (26 kDa) are indicated by squares. Arrowhead indicates BTE RNA. (C) Western blots using antibodies to known initiation factors on proteins pulled down by the indicated RNAs. Proteins were separated by SDS PAGE prior to blotting on PVDF membrane. Each panel represents a different gel and blot. Washes indicate proteins not bound to the indicated RNA. No pure eIF4B was used as positive control (first lane), but efficacy of antisera was evident by detection of eIF4B in the low-salt wash. Cleavage products of the labile eIF4G are visible. (D) Western blots against wheat germ extract proteins eluted from biotinylated, nonviral (166 nt vector-derived) RNA complexes. (bound) Proteins interacting with vector sequence (none detected in these Western blots). Unbound proteins obtained in washes (lanes 1–3) as indicated.

FIGURE 2.

UV cross-linking between BTE RNAs and cap-binding proteins in wheat germ extracts. [³²P]-labeled BTE105 or BTEBF RNAs were UV cross-linked to wheat germ extract proteins, RNase-treated, and immunoprecipitated with either preimmune antisera (PI) or antiserum to eIF4F (4F) or eIFiso4F (i4F). RNA–protein mixtures were then run on a 12.5% SDS–polyacrylamide gel and visualized by autoradiography. Mobilities of pure factors on the same gel are indicated at left.

FIGURE 3.

Effect of added factors on translation in cap-binding factor-depleted wheat germ extract. Wheat germ extract (wge) was passed over a m⁷GTP-Sepaharose column to remove cap-binding protein complexes prior to in vitro translation. Indicated amounts of recombinant eIF4F (A) or eIFiso4F (B) were added to extracts prior to programming with 20 nM uncapped BLucB or capped vector with a 68-nt poly(A) tail (capVLucV(A)₆₈) mRNA. The reaction mixtures were incubated for 1 h at 25°C and firefly luciferase activity was measured in relative light units. (C) Direct comparison of effects of eIFiso4F and eIF4F on BLucB translation. The data shown are averages of at least two experiments. Percent translation indicates relative light units normalized to the readings obtained with 54 nM eIF4F (4F). (D) Comparison of stimulation of translation by recombinant eIF4F containing his-tagged eIF4E used throughout this work (4F) with eIF4F containing native eIF4E (4F-wt).

FIGURE 4.

Effect of added eIF4F and its individual subunits on translation in factor-depleted extracts. (A) Wge depleted of cap-binding complex (50 μL) (as in Fig. 3) was supplemented with indicated amounts of eIF4F or its subunits (eIF4E, eIF4G) and programmed with BLucB mRNA (20 nM). (B) Depleted wge (50 μL) was supplemented with indicated factors and programmed with BLucB, capped BLucBBF mRNA (cap-BLucBBF), and capped reporter RNA containing vector-derived UTRs and a 68-nt poly(A) tail [capVLucV(A)₆₈] (final concentration 20 nM). The level of translation was expressed as a percentage of relative light units (RLU) obtained from luciferase translated in each extract supplemented with eIF4F. In the presence of eIF4F (defined as 100% for each mRNA), luciferase expression for capVLucV(A)₆₈ was 3000 RLU, while capBLucBBF, and uncapped BLucB RNAs yielded between 5000 and 6000 RLU. (C) Depleted wge (50 μL) was supplemented with indicated factors and programmed with BLucB (20 nM). The 86-kDa truncation mutant of eIF4G, lacking the eIF4E recognition site is indicated as 4G86. The 1:1 mixture of eIF4E and 4G86 is indicated as 4F86. The level of translation is expressed as the percentage of luciferase produced in the extract supplemented with eIF4F. The data are averages of triplicates from at least two experiments, and error bars represent standard error.

FIGURE 5.

Restoration of BTE-dependent translation by eIF4F in wheat germ extract inhibited by addition of BTE or cap analog. BTE105 RNA (A) or m⁷GpppG (B) and indicated factors were added to wheat germ extract, which was next programmed with BLucB RNA. The level of translation is expressed as a percentage of luciferase produced in the uninhibited extract (control). The data shown are averages of triplicates from at least two experiments and error bars represent standard error.

FIGURE 6.

Binding of the BTE to initiation factors. (A) Binding curves to calculate apparent equilibrium dissociation constants (Kd) of eIF4F and its subunits for BTE RNA. [α-³²P]-labeled BTE (0.4 nM) was mixed with indicated amounts of factors. Both protein-bound and unbound RNAs were measured in a double membrane filter-binding assay as described in Materials and Methods. Each point represents an average from at least three independent experiments. Data were fitted using GraphPad software and Kd values were calculated from equations of the best-fitted curves. (B) Filter binding of eIF4F (50 nM) to [α-³²P]-labeled BTE, BTEBF, a 200-nt vector-derived RNA, and a 100-nt fragment of 18S rRNA. Binding of α-³²P-labeled RNAs to nitrocellulose in the absence of eIF4F is shown in the bar indicated as none. Final concentration of all RNAs was 0.4 nM. The data are averages from at least two independent experiments performed in triplicate. Error bars indicate standard error. (C) Binding of bovine serum albumin (BSA), eIFiso4F, and eIF4F to [α-³²P]-labeled BTE (0.4 nM) was performed as described in B.

FIGURE 7.

Proposed model for 3′ BTE-mediated recruitment of translational machinery to viral mRNA. For simplicity, only the factors relevant to this report are shown. eIF4F (4G + 4E) binds the BTE structure in the 3′ UTR. The BTE and eIF4E bind eIF4G directly, while eIF4E and unidentified pulled-down proteins (indicated by question mark) may or may not bind the BTE directly. Long-distance base-pairing (parallel lines connecting a stem–loop in the BTE with the stem–loop adjacent to the AUG) juxtaposes the BTE-bound factors near the 5′ end. This delivers eIF4F and possibly other factors to the 43S ribosomal complex at the 5′ end (dashed arrow). eIF4G and possibly other factors interact with the ribosome to facilitate ribosomal scanning (horizontal arrow). See text for details. Reproduced with permission from Miller et al. (2007); ©2007 the Biochemical Society.