ABSTRACT
eIF4A is a DEAD-box RNA-dependent ATPase thought to unwind RNA secondary structure in the 5′-untranslated regions (UTRs) of mRNAs to promote their recruitment to the eukaryotic translation pre-initiation complex (PIC). We show that the PIC stimulates the ATPase of eIF4A, indicating that the factor acts in association with initiating ribosomal complexes rather than exclusively on isolated mRNAs. ATP hydrolysis by eIF4A accelerates the rate of recruitment for all mRNAs tested, regardless of their degree of secondary structure, indicating that the factor plays important roles beyond unwinding mRNA structure. Structures in the 5′-UTR and 3′ of the start codon synergistically inhibit mRNA recruitment, in a manner relieved by eIF4A, suggesting that the factor resolves global mRNA structure rather than just secondary structures in the 5′-UTR. We suggest that eIF4A breaks the many weak interactions formed within an mRNA that occlude the 5′-UTR and facilitates engagement of the 5′-UTR with the PIC.
INTRODUCTION
The goal of translation initiation is to assemble the ribosomal initiation complex containing the methionyl initiator tRNA (Met-tRNAi) at the translation start site on an mRNA. The process begins when the small (40S) subunit of the ribosome binds eIF1, eIF1A, eIF2, GTP, Met-tRNAi, eIF3, and eIF5, to assemble the 43S PIC (Dever et al., 2016). eIF1 and eIF1A bind near the P site and in the A site of the 40S subunit, respectively, and promote binding of the ternary complex (TC) comprising eIF2, GTP, and Met-tRNAi. eIF5 is the GTPase-activating protein (GAP) for eIF2 and promotes GTP hydrolysis (Das et al., 1997, 2001; Paulin et al., 2001); however, irreversible release of the inorganic phosphate is inhibited at this stage of the pathway (Algire et al., 2005). The heteromultimeric factor eIF3 has multiple interactions with the PIC and is involved in nearly every step of translation initiation (Aitken and Lorsch, 2012; Valásek, 2012).
The 43S PIC is assembled in an “open” conformation (Fekete et al., 2007; Llacer et al., 2015; Maag et al., 2005, 2006; Passmore et al., 2007; Pestova et al., 1998) that can bind an mRNA in a process called mRNA recruitment. eIF3 and a set of mRNA recruitment factors – eIF4A, eIF4E, eIF4G, and eIF4B – facilitate this step (Mitchell et al., 2011). After initial mRNA loading, the PIC remains in an open conformation and scans the 5′- untranslated region (UTR) of the mRNA for the start codon, usually an AUG (Hinnebusch, 2014). Recognition of the start codon by the tRNAi triggers a series of key steps – eviction of eIF1, movement of the C-terminal tail of eIF1A out of the P site, and subsequent release of the previously-hydrolyzed inorganic phosphate by eIF2 – ultimately shifting the PIC from an “open” to a “closed” conformation (Dever et al., 2016; Hussain et al., 2014; Llacer et al., 2015). The 48S PIC thus formed is committed to the selected start codon and joining with the large (60S) subunit of the ribosome to form the final 80S initiation complex (Acker et al., 2009; Dever et al., 2016).
Whereas a combination of genetic, biochemical, and structural approaches have illuminated the molecular details of PIC formation and start-codon selection, the intermediate events of mRNA recruitment remain poorly understood (Aitken and Lorsch, 2012). We recently demonstrated that the absence of either eIF4A, eIF4B, eIF3, or eIF4G together with eIF4E, greatly reduces the extent, the rate or both for mRNA recruitment to the PIC in a S. cerevisiae in vitro reconstituted translation initiation system (Mitchell et al., 2010). Structural and biochemical work indicates that eIF3 binds on the solvent side of the 40S but its five core subunits have multiple interactions with other components of the PIC including distinct interactions with the mRNA near the entry and exit channels of the ribosome (Aitken et al., 2016; Llacer et al., 2015). Also, yeast eIF4B binds directly to the 40S ribosomal subunit, modulates the conformation of the ribosome near the mRNA entry channel (Walker et al., 2013), and has a functional interaction with eIF4A (Andreou and Klostermeier, 2014; Harms et al., 2014; Park et al., 2013; Walker et al., 2013). In contrast, eIF4A has not been shown to bind stably to the PIC but forms a heterotrimeric complex with eIF4G and eIF4E, collectively referred to as eIF4F, which interacts with the mRNA.
mRNA can form stable secondary structures via local base-pairing of complementary sequences but also has a natural tendency to form global structures, created by a combination of entangled or compacted conformations inherent to polymers longer than their persistence lengths (Chen et al., 2012) and the sum of many, possibly dynamic, individual base-pairing and other interactions between both neighboring and distant parts of the molecule (Halder and Bhattacharyya, 2013). Hairpin structures in the 5′-UTR are generally inhibitory to translation initiation and the prevailing model of mRNA recruitment suggests that eIF4A – localized to the 5′-end via the eIF4G–eIF4E–5′-m7G-cap chain of interactions – unwinds these hairpins to allow PIC attachment (Merrick, 2015; Pelletier and Sonenberg, 1985; Ray et al., 1985; Svitkin et al., 2001; Yoder-Hill et al., 1993).
eIF4A is a DEAD-box ATP-dependent RNA helicase (Andreou and Klostermeier, 2013a; Linder et al., 1989; Schreier et al., 1977). It cooperatively binds RNA and ATP with no apparent RNA sequence specificity, and is thought to disrupt structures by local strand separation, possibly due to bending of the RNA duplex (Henn et al., 2012; Linder and Jankowsky, 2011). Subsequent ATP hydrolysis causes a decrease in affinity of eIF4A for the mRNA, thus recycling eIF4A from an eIF4A•ATP•RNA ternary complex (Andreou and Klostermeier, 2013a; Jankowsky, 2011; Liu et al., 2008; Lorsch and Herschlag, 1998a, 1998b). Several studies demonstrated that eIF4A is able to disrupt short RNA duplexes (Rajagopal et al., 2012; Ray et al., 1985; Rogers et al., 1999) and more recent work suggests that eIF4A can unwind a large hairpin when the RNA is stretched between two tethers (Garcia-Garcia et al., 2015). Also, sensitivity to inhibition of translation by a dominant negative mutant of eIF4A is correlated with the degree of secondary structure in the 5′- UTR, supporting a role for eIF4A in removing structures from the 5′-end of mRNAs (Svitkin et al., 2001).
Nonetheless, eIF4A is a notoriously slow enzyme (Garcia-Garcia et al., 2015; Lorsch and Herschlag, 1998b; Rajagopal et al., 2012; Rogers et al., 1999) and it is difficult to envision how it supports in vivo rates of translation initiation in the regime of ~10 min-1 (Palmiter, 1975). In fact, several more potent helicases appear to promote translation by resolving stable structural elements (Parsyan et al., 2011), raising the possibility that eIF4A instead performs a distinct role during initiation on all mRNAs (Gao et al., 2016). A study employing ribosome profiling to compare the in vivo effects of inactivating eIF4A versus Ded1p – a considerably more robust DEAD-box RNA helicase – demonstrated that translation of many mRNAs with 5′-UTRs possessing high degrees of structure is highly dependent on Ded1 but relatively few mRNAs are similarly hyper-dependent on eIF4A, despite comparable requirements for the two helicases in maintaining global translation initiation. Consistent with this, analysis of reporter mRNAs harboring inhibitory hairpin structures indicated that yeast eIF4A is either ineffective or dispensable in the presence of Ded1 in resolving stable, local secondary structures in the 5′-UTR (Sen et al., 2015). In a separate study, minor decreases in the normally high cellular levels of eIF4A also resulted in depressed global rates of translation (Firczuk et al., 2013), providing additional evidence that eIF4A may be important for translation of all mRNAs and must be present in excess of other components of the translational apparatus. Consistent with the idea that it acts generally rather than by disrupting specific secondary structures in 5′-UTRs, eIF4A has been shown to promote translation of an mRNA possessing a short (8 nucleotide (nt)) 5′-UTR (Blum et al., 1992) and a viral mRNA with a low degree of structure in its 5′-UTR (Altman et al., 1990), and to stimulate 48S formation on mRNAs with little secondary structure in their 5′-UTRs (Pestova and Kolupaeva, 2002). How the helicase and ATPase activities of eIF4A, alone or as a part of eIF4F, contribute to its role in promoting initiation on diverse mRNAs remains unclear.
Here – using an in vitro translation initiation system reconstituted from purified S. cerevisiae components – we examined the role of eIF4A and eIF4F in mRNA recruitment to the PIC. We monitored the kinetics of eIF4A ATPase activity in the context of mRNA recruitment and asked how that activity is utilized for the recruitment of mRNAs possessing various degrees of structure, ranging from the natural (structured) RPL41A mRNA to short model mRNAs comprised mostly of CAA repeats expected to lack significant structure (hereafter called “unstructured”) (Sobczak et al., 2010; Zuker, 2003) beyond fluctuations in polymer conformation or transient interactions (Chen et al., 2012). We show that the PIC stimulates the ATPase activity of eIF4A both on its own and as a component of eIF4F. We further show that eIF4A increases the rate of recruitment of all mRNAs tested, ranging from the natural RPL41A mRNA to short unstructured messages. Structures in the 5′-UTR and on the 3′ side of the start codon synergistically inhibit mRNA recruitment in a manner relieved by eIF4A. We propose that eIF4A, alone or as a part of eIF4F, facilitates mRNA recruitment and PIC attachment by relaxing global mRNA structure rather than resolving specific secondary structures in the 5′-UTR. In addition, our data indicate the factor engages with the PIC, consistent with the possibility that it facilitates loading of mRNAs into the 40S subunit’s entry channel by remodeling the PIC itself or by funneling the message directly onto the ribosome.
RESULTS
ATP hydrolysis by eIF4A is required for recruitment of mRNAs, regardless of their degree of structure
To better understand how eIF4A-catalyzed ATP hydrolysis is related to the removal of RNA structure and mRNA recruitment, we compared the kinetics of recruitment of the natural mRNA RPL41A (possessing structural complexity throughout its length) with a 50 (nt) model mRNA made up of CAA repeats and an AUG codon at positions 24-26 (CAA 50-mer) (Aitken et al., 2016). The latter mRNA is expected to have little, if any, secondary or tertiary structure (Sobczak et al., 2010; Zuker, 2003).
mRNA recruitment experiments were performed as described previously, using an in vitro-reconstituted S. cerevisiae translation initiation system (Mitchell et al., 2010; Walker et al., 2013). Briefly, PICs containing 40S, TC, eIF1, eIF1A, eIF5, and eIF3 were formed in the presence of saturating levels of eIFs 4A, 4B, 4E, and 4G (see “30 nM PIC” in Methods). Reactions were initiated by simultaneous addition of ATP and an mRNA labeled with a [32P]-7-methylguanosine (m7G) cap, enabling mRNA recruitment to the PICs and formation of 48S complexes. Reaction timepoints were acquired by mixing an aliquot with a 25-fold excess of a non-radioactive (“cold”) capped mRNA identical to the labeled one in the reaction, effectively stopping further recruitment of radiolabeled mRNA. The rate of dissociation of recruited mRNAs from the PIC in the presence of the cold chase mRNA was negligible for all mRNAs in the study (data not shown). Free mRNA and 48S complexes were resolved via gel electrophoresis on a native 4% THEM polyacrylamide gel (Acker et al., 2007; Mitchell et al., 2010) (see Materials and Methods).
We first compared the kinetics of recruitment for RPL41A with CAA 50-mer in the presence and absence of ATP (Figure 1). In the presence of saturating ATP, the rate of recruitment of RPL41A was 0.74 ± 0.01 min-1 with an endpoint in excess of 90%. In contrast, in the presence of ADP, and in reactions lacking either nucleotide or eIF4A, less than 20% of RPL41A mRNA was recruited after 6 hours, indicating a dramatically lower rate that could not be measured accurately due to the low reaction endpoint (Figure 1A,C). The CAA 50-mer was recruited in the absence of eIF4A and ATP at rates of about 0.90 min-1, likely due to lack of significant structure, reaching endpoints around 80%. Surprisingly, the addition of eIF4A and ATP stimulated the rate of recruitment of the CAA 50-mer by more than 4-fold (4.0 ± 0.6 min-1) and yielded an endpoint of 90% (Figure 1B,C).
To determine whether ATP hydrolysis is required for the stimulation we observed, we next measured the rate of recruitment with the non-hydrolyzable ATP analogs ADPCP and ADPNP, as well as with the slowly-hydrolyzable analog ATP-γ-S (Peck and Herschlag, 2003). Neither ADPCP nor ADPNP supported stimulation of the recruitment of either mRNA by eIF4A, producing rates that were comparable to the observed rates measured in the absence of nucleotide or eIF4A (Figure 1; compare grey and blue curves to red and purple). In the presence of ATP-γ-S, recruitment of RPL41A and CAA 50-mer was 39-fold (0.019 ± 0.001 min-1) and nearly 2-fold (2.3 ± 0.2 min-1) slower, respectively, than in the presence of ATP; however, both mRNAs achieved endpoints of approximately 80%, consistent with previous observations that eIF4A is capable of utilizing ATP-γ-S (Peck and Herschlag, 2003). Taken together, these results suggest that ATP hydrolysis by eIF4A is required to stimulate the recruitment of mRNAs to the PIC regardless of their degree of structure.
The ATPase activities of eIF4A and eIF4F are increased by the PIC
We next asked if the presence of the PIC might influence the activity of eIF4A or eIF4F. We monitored the ATPase activity of eIF4A in the in vitro reconstituted translation initiation system using an enzyme-coupled ATPase assay in which pyruvate kinase and lactate dehydrogenase are used to regenerate ATP from ADP and, in the process, oxidize NADH to NAD+, producing a change in absorbance at 340 nm (Bradley and De La Cruz, 2012; Kiianitsa et al., 2003); (Figure 2 – figure supplement 1A; see Materials and Methods). Reactions with varying concentrations of mRNA were assembled in a 384-well plate and initiated by addition of saturating ATP (5 mM). NADH absorbance at 340 nm was recorded every 20 seconds using a microplate reader. By titrating mRNA, we determined the maximal velocity of ATP hydrolysis (Vmax), as well as the concentration of mRNA needed to achieve the half-maximal velocity (). For eIF4A alone (5 μM) the Vmax was 2.4 ± 0.2 μM/min (or a kcat of 0.48 ± 0.04 min-1) (Figure 2A; Figure 2 – figure supplement 1B), comparable to a previous measurement of kcat of 0.20 ± 0.05 min-1 (Rajagopal et al., 2012). Also, congruent with previous findings (Hilbert et al., 2011; Oberer et al., 2005; Rajagopal et al., 2012), the addition of co-purified full length eIF4G1 and eIF4E (eIF4G•4E) to eIF4A, forming the eIF4F complex, resulted in a 6.5-fold increase in the Vmax at saturating mRNA levels (Figure 2A; compare “4A alone” to “4A•4G•4E alone”).
The addition of the PIC to these reactions (See “0.5 μM PIC” in Methods) increased the observed Vmax an additional 3-fold over the Vmax with eIF4F alone (Figure 2A; compare “4A•4G•4E alone” to “+”). Leaving out the 40S subunit resulted in a 2-fold decrease of Vmax as compared to the value observed in the presence of an intact PIC (Figure 2A), suggesting that the 40S, alone or in association with one or more components of the PIC stimulates the ATPase activity. We observed similar values for in the presence of a complete PIC (260 ± 40 μM) and when all components except the 40S were present (270 ± 70 μM). In contrast, the with eIF4A and eIF4F alone were 80 ± 10 μM and 100 ± 10 μM, respectively (Figure 2A; Figure 2 – Supplement 1B). Because values of Vmax are, by definition, obtained at saturating concentrations of mRNA (Figure 2A), the stimulation observed by the PIC is not attributable to rRNA or tRNAi.
Because the 5′-cap promotes mRNA recruitment (Kumar et al., 2016; Mitchell et al., 2010), we also measured the Vmax and with uncapped RPL41A. In the presence of the PIC, the Vmax was comparable and the was approximately 2-fold lower than the values measured with capped RPL41A. For eIF4F alone, in the absence of the PIC, congruent with previous findings (Rajagopal et al., 2012), the Vmax (21.3 ± 0.1 μM/min) and the (150 ± 24 μM) were both modestly higher with uncapped RPL41A than with capped. The absence of a cap on the mRNA did not affect the enhancement of the maximal rate of ATP hydrolysis by the PIC at saturating concentrations of mRNA (Figure 2 – figure supplement 1C).
The rate of eIF4A-catalyzed ATP hydrolysis saturates at levels of eIF4A in excess of the PIC
In vivo eIF4A is in excess of all other components of the translational machinery and the rate of translation is sensitive to minor changes in eIF4A concentration (Firczuk et al., 2013; von der Haar and McCarthy, 2002). In vitro, the maximal rate of mRNA recruitment is observed when eIF4A is in excess of the PIC, mRNA, and other initiation factors (Mitchell et al., 2010; Walker et al., 2013). To determine how the eIF4A:PIC ratio affects the stimulation of eIF4A by the PIC, we titrated eIF4A in the presence of saturating capped RPL41A mRNA and ATP. The rate of ATP hydrolysis observed in the presence of the PIC was divided by the rate observed with the same concentration of eIF4A alone (i.e. normalized) (Figure 2B). Titrating eIF4A to increase the eIF4A:PIC ratio, resulted in a larger enhancement of the normalized rate of ATP hydrolysis, plateauing at a concentration of eIF4A in 10-fold excess of the PIC (5 μM eIF4A), consistent with the requirement of excess eIF4A for mRNA recruitment, both in vivo and in vitro. It is possible that this concentration of eIF4A is necessary to saturate the PIC due either to a relatively weak interaction or to the presence of multiple binding sites for the factor on the mRNA and/or the PIC. The degree of ATPase stimulation by the PIC modestly decreased when eIF4A was in excess over the PIC by 24-fold (12 μM eIF4A) possibly because all available PICs were saturated by eIF4A (Figure 2B) and could not provide as much of a rate increase when normalized to the rate of eIF4A alone at that concentration.
The PIC and eIF4G•4E stimulate eIF4A via distinct mechanisms
Having observed that the PIC increases the rate of eIF4A-catalyzed ATP hydrolysis at saturating levels of ATP and mRNA, we next investigated the effects of the PIC and eIF4G•4E on the ATP-dependence of the reaction. As before, we measured ATPase activity in the presence and absence of the PIC but here performed experiments with saturating capped RPL41A mRNA (0.5 μM) and instead varied the ATP concentration to determine the maximal velocity of ATP hydrolysis at saturating ATP levels (Vmax) and the concentration of ATP required to achieve half-maximal velocity () (Figure 2C). In the absence of the PIC and other initiation factors, eIF4A alone hydrolyzed ATP at a maximal velocity of 2.9 ± 0.4 μM/min and had a of 2500 ± 400 μM. The presence of eIF4G•4E – forming eIF4F – resulted in a 4-fold increase in the Vmax (11.9 ± 0.6 μM/min) and a 10-fold decrease in (250 ± 10 μM). Adding the PIC to eIF4F increased the Vmax an additional 4-fold but had no significant impact on (Figure 2C, “4A alone,” “4A•4G•4E alone,” “+”). Omitting the 40S subunits from reactions containing eIF4F and all other PIC components decreased the Vmax by a factor of 2 underscoring the importance of the 40S subunit in promoting ATPase activity (Figure 2C, compare “-40S” to “+”). The absence of the 40S subunit also resulted in a 2-fold decrease in the . In contrast, adding only the 40S and TC to eIF4F did not provide a significant increase in the rate of ATPase as compared with eIF4F alone (Figure 2 – Figure Supplement 1D, “TC, 40S, 4A•4G•4E”), suggesting that the 40S is not able to directly stimulate eIF4F and requires other PIC components. Also, the omission of eIF4A from a reaction containing all other components resulted in ≥ 67-fold decrease in the rate of ATPase (to the limit of detection of the assay), ruling out any significant ATPase contamination in either the PIC components or other initiation factors (Figure 2C, “-4A”).
We next asked if the PIC could stimulate eIF4A ATPase directly, in the absence of eIF4G•4E. Addition of the PIC to eIF4A, in the absence of eIF4G•4E, resulted in a 6-fold increase in Vmax over eIF4A alone (Figure 2C, “4A alone” vs. “-4G, −4E”) and a that was ~1.5-fold lower than that with eIF4A alone. eIF4G is thought to juxtapose the two eIF4A RecA-like domains to enhance ATP binding and catalysis (Hilbert et al., 2011; Oberer et al., 2005; Schütz et al., 2008), potentially explaining eIF4F’s significantly lower than that of eIF4A alone. Our findings that eIF4G•4E increased the Vmax by 4-fold and decreased the by 10-fold, as compared to eIF4A alone (Figure 2C “4A alone”, “4A•4G•4E alone”), whereas the PIC increased the Vmax with only a small decrease in the (Figure 2C “4A alone”, “-4G•4E”) may be due to distinct mechanisms of eIF4A stimulation. Taken together, our data suggest that the PIC enhances ATP hydrolysis without a major effect on ATP binding, while eIF4G•4E stimulates both ATP binding and hydrolysis.
eIF3 and other components of the PIC are required for full stimulation of eIF4A
To further dissect the functional interactions among eIF4A, eIF4G•4E, and the PIC, we next measured Vmax and in the absence of each of the PIC components. Leaving out tRNAi or eIF2 decreased the Vmax by ~2-fold – similar to the reduction observed in the absence of 40S subunits – and also conferred a 1.5-fold reduction in as compared to when all components were present (Figure 2C; compare “+” to “-2”, and “-tRNAi”). The absence of eIF1 or eIF1A, which both stimulate binding of the TC to the 40S subunit (Hinnebusch, 2014), also resulted in ~1.3-fold reductions in Vmax. Leaving out eIF3 decreased the Vmax by approximately 2.5-fold and by approximately 2-fold. In contrast, eIF3 did not significantly influence Vmax or in the presence of eIF4F alone (Figure 2 – figure supplement 1D, compare “eIF4A•4G•4E alone” to “3, 4A•4G•4E”), indicating that its effect is exerted only in the presence of other PIC components. Taken together, the PIC stimulation of eIF4A that we observe depends on the presence of the majority of PIC constituents. The changes in could be due to conformational differences in eIF4A in the absence of PIC components or changes in the rate-limiting step for ATP hydrolysis (Fersht, 1999).
S. cerevisiae eIF3 is comprised of 5 core subunits and is involved in numerous steps of translation initiation, including mRNA recruitment. Previous reports demonstrated that yeast eIF3 is essential for mRNA recruitment both in vitro (Mitchell et al., 2010) and in vivo (Jivotovskaya et al., 2006), and that it stabilizes TC binding and promotes PIC interactions with the mRNA at both the mRNA entry and exit channels of the 40S subunit (Aitken et al., 2016). In particular, the eIF3 subunits g and i have been implicated in scanning and AUG recognition in vivo (Cuchalová et al., 2010) and are required for recruitment of RPL41A mRNA in vitro (Aitken et al., 2016; Valásek, 2012). Both subunits are thought to be located near the mRNA entry channel of the ribosome, at either the solvent or intersubunit face of the 40S subunit (Aylett et al., 2015; des Georges et al., 2015; Llacer et al., 2015). In the presence of PICs formed with the heterotrimer of eIF3 subunits a, b, and c – but lacking the g and i subunits – eIF4F had Vmax and values of 20 ± 2 μM/min and 170 ± 12 μM, respectively, which were similar to those observed in the absence of the entire eIF3 (Figure 2C, “-3” vs. “-3g, −3i”). Thus, although the heterotrimeric eIF3a,b,c subcomplex binds to the PIC under our experimental conditions (Aitken et al., 2016), it does not stimulate eIF4F’s ATPase activity, indicating an important role for the eIF3 i and g subunits in this function.
Having found that the PIC can stimulate eIF4A ATPase activity in the absence of eIF4G•4E (Figure 2C), we next asked which PIC components are critical for this independent stimulatory mechanism. Eliminating the 40S subunit, eIF2, eIF3, or the g and i subunits of eIF3 in the absence of eIF4G•4E abrogated all stimulation of ATPase activity, yielding Vmax values the same as observed with eIF4A alone (~3 μM/min-1) (Figure 2D). The values were also similar to the values observed with eIF4A alone or when just eIF4G•4E was missing from the PIC (~1600 μM, Figure 2D). Taken together, these data suggest that stimulation of the ATPase activity of eIF4A, in the absence of eIF4G•4E, requires multiple components of the PIC. In the presence of eIF4G•4E, the combined absence of the 40S subunit and either eIF2 or eIF3 yielded and Vmax values that were comparable to those obtained in the presence of the 40S subunit when only eIF2 or eIF3 were left out of the reaction, as well as to reactions in which just the 40S subunit was omitted (Figure 2D compare “-2, −40S” and “-3, −40S” to Figure 2C “-40S,” “-2” and “-3”), suggesting that the stimulatory effects of eIF2, eIF3 and the 40S subunit are interdependent and largely reflect the 40S-bound conformations of the factors. It may be noteworthy, however, that the omission of eIF3 or its g and i subunits consistently has a slightly larger effect on the Vmax of ATP hydrolysis in the presence of eIF4G•4E and other components of the PIC than does omission of the 40S subunit or eIF2 (Figure 2C, compare “-3” and “-3g, −3i” to “-40S” and “-2”; Figure 2D, compare “-3, −40S” to “-2, −40S”). This observation suggests that eIF3 might provide a small amount of stimulation of eIF4F’s ATPase in the absence of a fully assembled PIC, but in a manner that depends on one or more additional factors.
The PIC stimulates ATP hydrolysis by eIF4F in the presence of limiting amounts of either a structured natural mRNA or a short unstructured model mRNA
Our initial observation that eIF4A stimulates the recruitment of both the natural RPL41A mRNA and the unstructured CAA 50-mer model mRNA was made under conditions of limiting mRNA, whereas our experiments investigating the stimulation of eIF4A ATPase by the PIC and other initiation factors were performed at saturating mRNA levels and higher factor concentrations to ensure PIC formation even in the absence of multiple components. To confirm that the PIC stimulation of eIF4A’s ATPase activity is maintained at limiting mRNA levels, we monitored ATP hydrolysis by eIF4A (in the context of the eIF4F complex) in the presence or absence of the PIC (30nM PIC, when present, the same conditions as in Figure 1), using limiting (15 nM) capped RPL41A or capped CAA 50-mer. As under saturating mRNA conditions, addition of the PIC increased the Vmax approximately 4-fold in the presence of both the natural RPL41A and the unstructured CAA 50-mer mRNAs, as compared to eIF4F alone (Figure 2E). Thus, the PIC stimulates eIF4A activity under conditions where eIF4A promotes PIC recruitment of both native and unstructured model mRNAs. Also, the was ~3-fold higher than observed with saturating mRNA and 0.5 μM PIC (compare Figure 2E and 2C, blue bars). Considering that eIF4A binds RNA and ATP cooperatively (Lorsch and Herschlag, 1998b), perhaps the mRNA was sub-saturating for eIF4A binding at the lower concentration (15 nM) employed in the current experiments (Figure 2E), which imposed a requirement for higher ATP concentrations to saturate ATP binding.
In contrast to the other PIC components, we did not observe an effect on the Vmax of eIF4A ATPase by omitting eIF5. Similarly, leaving out eIF4B, in the presence or absence of the PIC, had no effect on Vmax for ATP hydrolysis (Figure 2C, E; Figure 2 – figure supplement 1D). However, addition of eIF4B in the presence of either eIF4F alone or with eIF4F and the complete PIC, decreased the by 1.5-fold and 2.5-fold, respectively, as compared to the corresponding condition in the absence of eIF4B (Figure 2C; Figure 2 – figure supplement 1D) consistent with the idea that eIF4B acts as a coupling factor or a co-factor for eIF4A (Andreou and Klostermeier, 2014; Mitchell et al., 2010; Özeş et al., 2011). Although eIF4B has no effect on the Vmax for ATP hydrolysis in our system, the factor strongly stimulates mRNA recruitment to the PIC in vitro (Mitchell et al., 2010), demonstrating that it is active. It also reduces the K1/2 for eIF4A in mRNA recruitment assays, indicating a functional coupling between the two factors exists in the in vitro system (Walker et al., 2013). Therefore, the lack of an effect of eIF4B on the ATPase activity of eIF4A in the system does not appear to represent a functional inadequacy.
eIF4A relieves the inhibition of recruitment created by the global structures of mRNAs, rather than structures confined to the 5′-UTR
Our finding that eIF4A-dependent ATP hydrolysis increases the rate of recruitment of a natural mRNA as well as a short, unstructured 50 nucleotide model mRNA prompted us to investigate which features of an mRNA influence the efficiency of its recruitment to the PIC and the dependence on eIF4A. To this end, we created a library of in vitro transcribed and individually purified mRNAs spanning a range of structures and lengths. This library contains model mRNAs made almost entirely of CAA repeats, containing or lacking a 9 base pair (bp) hairpin in the 5′-UTR, and/or a natural RPL41A mRNA sequence downstream of the AUG in place of CAA repeats (Figure 3A; Supplementary Methods). We measured the recruitment kinetics for each mRNA as a function of eIF4A (as described above; see “mRNA Recruitment Assay” in Methods) and determined the maximal rate (kmax) and concentration of eIF4A required to achieve the half-maximal rate () (Figure 3 – figure supplement 1).
Using an eIF4A concentration determined to be at, or close to, saturation for all ten mRNAs (5 μM, as determined in Figure 3 – figure supplement 1), we observed recruitment endpoints between 85%-95% with all mRNAs tested (Figure 3B, black bars). In the absence of eIF4A, however, the extent of recruitment varied widely among the mRNAs. Less than 10% of RPL41A mRNA was recruited in reactions lacking eIF4A (Figure 3B, RNA 10, red bar), consistent with the low levels of RPL41A recruitment we observed in the absence of ATP (Figure 1A), with a kmax of 1.3 ± 0.1 min-1 (Figure 3C) and of 3.7 ± 1.0 μM (Figure 3 – figure supplement 1B,E). In the absence of eIF4A, time courses with RPL41A mRNA could not be accurately fit to a single-exponential kinetic model due to low reaction endpoints. However, comparison of estimated initial rates (no eIF4A, 0.22 ± 0.07 min-1; saturating eIF4A, 41 ± 1 min-1) of recruitment of RPL41A revealed that recruitment proceeds two orders of magnitude more rapidly in the presence of saturating levels of eIF4A versus in the absence of eIF4A (Figure 3D).
Consistent with our observation that the unstructured CAA 50-mer mRNA is efficiently recruited even in the absence of ATP, we observed 74 ± 1 % recruitment of this mRNA in the absence of eIF4A (Figure 3A-B, RNA 1, red bar). Nonetheless, the addition of saturating eIF4A increased the extent of recruitment to 87 ± 1 % (Figure 3A-B, RNA 1, black bar) consistent with our observation that the addition of ATP slightly elevates the extent of recruitment of this mRNA above the levels observed in the absence of ATP (Figure 1B). Beyond this modest stimulation of recruitment extent, saturating eIF4A accelerated the rate of CAA 50-mer recruitment, yielding a kmax of 6.2 ± 1.0 min-1 (Figure 3C), a more than 7-fold increase (Figure 3D) as compared to the rate of CAA 50-mer recruitment in the absence of eIF4A (0.9 ± 0.1 min-1). Relative to RPL41A mRNA, this acceleration is achieved at lower levels of eIF4A ( of 0.70 ± 0.2 μM vs. 3.7 ± 1.0 μM with RPL41A; Figure 3 – figure supplement 1B,E).
To compare the CAA 50-mer with a longer mRNA, we increased the total mRNA length to 250 nucleotides (250-mer) by adding 200 nucleotides of CAA repeats downstream of the AUG (Figure 3A, RNA 2). In the absence of eIF4A, we observed 66 ± 10 % extent of recruitment, comparable to that seen for the CAA 50-mer in the absence of eIF4A (Figure 3B, red bars, RNA 1 vs. 2). The kmax was 3.3 ± 0.4 min-1, approximately 2-fold lower than that for the CAA 50-mer, whereas the values were indistinguishable for the two mRNAs (Figure 3 – figure supplement 1E). Importantly, eIF4A strongly stimulated the rate of recruitment of this mRNA, in this case by 13-fold (Figure 3D). Similar results were obtained for two additional CAA-repeat 250-mers with the AUG situated 67 or 150 nucleotides from the 5′-end (Figure 3A, RNAs 3 and 4). These mRNAs had extents of recruitment of 60-70% in the absence of eIF4A, which increased to >90% in the presence of saturating eIF4A (Figure 3B, RNAs 3-4, red vs. black bars). Furthermore, the kmax for mRNA recruitment in the presence of eIF4A (Figure 3C, RNAs 3-4) were 22- and 7-fold greater than the observed rates in the absence of eIF4A (Figure 3D, RNAs 3-4). The kmax values and degree of stimulation by eIF4A varied by ≤2-fold among RNAs 1-4. The reason for these differences is not clear, but does not seem to correlate with overall mRNA length or number of nucleotides 5′ or 3′ to the AUG. Thus, all four unstructured CAA-repeat mRNAs that we studied can be recruited by the PIC at appreciable levels independently of eIF4A, but eIF4A stimulates their rates of recruitment by roughly an order of magnitude.
To probe the effects of defined, stable secondary structures on the functioning of eIF4A in mRNA recruitment, we examined 250-mer mRNAs comprising CAA repeats throughout the sequence except for a single 21-nt insertion predicted to form an 9 bp hairpin of −10 kcal/mol stability (Zuker, 2003), situated in the 5′-UTR either proximal or distal to the 5′-cap (Figure 3A, RNAs 5-6, Key; Supplementary Methods). Both cap-proximal and cap-distal insertion of this 21-nt sequence into the 5′-UTR of a luciferase reporter conferred strong inhibition of reporter mRNA translation in yeast cells (Sen et al., 2016). We confirmed the presence and location of the single hairpin in RNAs 5 and 6 and absence of significant secondary structure in RNA 4 by incubating RNAs 4-6 at 26°C with a 3′-5′ RNA exonuclease, ExoT, specific for single-stranded RNA (Figure 3 – figure supplement 2); (Deutscher et al., 1984; Zeng and Cullen, 2004).
To our surprise, in the absence of eIF4A, neither the cap-proximal nor the cap-distal hairpins significantly influenced the extent of recruitment, achieving endpoints between 70% and 80%, comparable to the unstructured CAA 50-mer and 250-mer RNAs (Figure 3B, RNAs 5-6 vs. 1-4). The maximal rates in the presence of eIF4A for both hairpin-containing mRNAs (RNAs 5-6) were ~2-fold lower than for the CAA 250-mers lacking the hairpin (RNAs 1-4) but ~2- 3-fold higher than the kmax for RPL41A (Figure 3C, RNAs 5-6 vs. 10). We could not accurately measure the for RNAs 5 and 6 but the lower limit was between 60-200 μM (Fersht, 1999). Saturating eIF4A stimulated the rate of recruitment for both cap-proximal and cap-distal hairpin mRNAs but, surprisingly, to a lesser degree than in the absence of the hairpin: between 3- and 4-fold as opposed to 7-fold for RNA 4 (Figure 3D). Thus, at odds with the expectation that stable structures in the 5′-UTR would impose strong obstacles to mRNA recruitment to the PIC, we found that addition of a cap-proximal or cap-distal hairpin in the 5′-UTR of an otherwise unstructured mRNA confers little or no inhibition of the extent of recruitment and only a modest reduction in the rate, in the presence or absence of eIF4A. Moreover, the observation that these hairpins in the 5′-UTR actually decrease the enhancement of the rate of mRNA recruitment provided by eIF4A relative to what we observed with the unstructured mRNA (Figure 3D, RNAs 5-6 vs. 4) is not readily consistent with the idea that the factor’s predominant function is to unwind stable secondary structures in the 5′-UTRs of mRNAs. If this were the case, one might have expected larger rate enhancements for mRNAs with stable structures in their 5′-UTRs than for mRNAs containing little inherent structure, the opposite of what we actually observe. It is possible that eIF4A is not efficient at unwinding such stable structures, which results in a lower kmax and a lower degree of stimulation.
To probe further the effects of RNA structural complexity on mRNA recruitment and eIF4A function, we examined a chimeric mRNA comprising CAA-repeats in the 5′-UTR and the natural sequence (with associated structural complexity) from RPL41A 3′ of the AUG start codon (Figure 3A, RNA 7). In the absence of eIF4A, this mRNA was recruited to the PIC with an observed rate of 0.06 ± 0.01 min-1, which is significantly slower than for RNAs 1-6 (~0.2- 0.9 min-1), but faster than the rate for full-length RPL41A mRNA, which could not be determined due to its low endpoint of recruitment (Figure 3 – supplement 1B,E RNAs 1-6, 10 vs. 7). In contrast, in the presence of saturating eIF4A the kmax for RNA 7 was comparable to the kmax values observed with RNAs 2, 3, 5 and 6 and within 2-fold of the values for RNAs 1 and 4. Thus, addition of saturating eIF4A conferred a 60-fold increase in the rate of recruitment for RNA 7, which is a greater degree of stimulation than observed with RNAs 1-6 (Figure 3D), indicating that eIF4A can efficiently resolve inhibition of mRNA recruitment mediated by RNA sequences on the 3′ side of the start codon that are not predicted to form stable secondary structures with the 5′-UTR (Zuker, 2003). In addition, the for RNA 7 was 1.8 ± 0.9 μM, approximately midway between the unstructured model mRNAs (RNAs 1-4; Figure 3 – supplement 1E; values of 0.7-1.0 μM) and RPL41A (3.7 ± 1.0 μM), suggesting that structure on the 3′ side of the start codon increases the concentration of eIF4A required to maximally stimulate recruitment.
The cap-proximal and cap-distal hairpins were strongly inhibitory to mRNA recruitment in the absence of eIF4A when inserted into the unstructured 5′-UTR of the chimeric mRNA harboring RPL41A sequence 3′ of the AUG codon, conferring very low reaction endpoints (≤ 20%; Figure 3B, RNAs 8-9, red bars) and rates (Figure 3 – figure supplement 1E, , RNAs 8-9). The presence of saturating eIF4A increased recruitment of both of these mRNAs to ~80% (Figure 3B, RNAs 8-9, black vs. red bars) and also increased their kmax values by approximately 10-fold (Figure 3D, RNAs 8-9); however, the rate stimulation by eIF4A was notably less than the 60-fold and ~190-fold increases observed for the chimeric mRNA lacking a hairpin (RNA 7) and native RPL41A (RNA 10), respectively (Figure 3D, RNAs 8-9 vs. 7,10). Consequently, the maximal rates achieved in the presence of eIF4A for mRNAs 8-9 remain well below those observed for mRNA 7 and RPL41A mRNA (Figure 3C, RNAs 8-9 vs. 7 and 10). Notably, the hairpin insertions conferred the predicted strong inhibition of PIC recruitment in the context of the chimeric mRNA containing native RPL41A sequences, but not in an otherwise unstructured mRNA.
Comparing kmax values for RNA 4 to RNAs 5-9 shows that the combined effects of structures in the 5′-UTR and 3′ to the AUG (RNAs 8 and 9) is considerably more than the additive effects of either structural element alone (Figure 3C, RNAs 5-7; Figure 3 – supplement 1E); structures in the 5′-UTR (RNAs 5 and 6) or 3′ to the start codon (RNA 7) on their own have 2-3-fold effects on kmax relative to the unstructured RNA 4, whereas combining them (RNAs 8 and 9) produces a ≥30-fold effect. These data indicate that structures in both regions synergistically inhibit the rate of mRNA recruitment. This synergy is also reflected in the dramatically reduced recruitment endpoints of RNAs 8-9 seen in the absence of eIF4A (Figure 3A,B, red bars; RNAs 4-7 vs. 8-9). The fact that eIF4A restores recruitment of these RNAs (Figure 3B, RNAs 8-9, black bars), albeit at relatively low recruitment rates, indicates that eIF4A can eventually resolve the synergistic inhibition produced by structures in the 5′ and 3′ segments of these messages. It is noteworthy, however, that eIF4A gives considerably larger rate enhancements for the mRNAs harboring only native RPL41A sequences (RNAs 7 and 10) than those burdened with synthetic hairpins (RNAs 5-6 and 8-9), suggesting that eIF4A is better able to resolve the complex array of relatively less stable structures in RPL41A compared to a highly stable local structure in the 5′-UTR.
The 5′-7-methylguanosine cap imposes an eIF4A requirement for structured and unstructured mRNAs
Because eIF4A-dependent ATP hydrolysis is enhanced by eIF4G•4E in our experiments, we next inquired how the 5′-cap influences the requirement for, and activity of, eIF4A in mRNA recruitment. We have previously shown that the 5′-cap enforces the requirement for several eIFs, including eIF4A, in mRNA recruitment (Mitchell et al., 2010). More recent work in the mammalian system provided evidence that the 5′-cap-eIF4E-eIF4G-eIF3-40S network of interactions is required to promote mRNA recruitment via threading of the 5′-end into the 40S entry channel (Kumar et al., 2016). As before, we monitored the kinetics of mRNA recruitment (30 nM PIC conditions) at various concentrations of eIF4A with capped or uncapped versions of mRNAs described above, including RNA 1 (CAA 50-mer), RNA 4 (CAA 250- mer), and RNA 7 (unstructured 5′-UTR with RPL41A sequence 3′ of the AUG; Figure 4 and Figure 4 – figure supplement 1). As summarized in Figure 4B, the kmax observed with saturating eIF4A was comparable with or without the 5′-cap for RNAs 1 and 7, and was 1.5-fold lower with the cap than without it for RNA 4. In contrast, in the absence of eIF4A, the rates of recruitment for uncapped versions of the unstructured model mRNAs 1 and 4 were 3.7- and 2.5- fold higher, respectively, than the rates of the corresponding 5′-capped mRNAs (Figure 4). This effect was even more pronounced for RNA 7, containing natural mRNA sequence 3′ of the AUG, which was recruited 15-fold faster when uncapped versus capped in the absence of eIF4A. It is also noteworthy that the rate enhancement provided by eIF4A (Figure 4B, ) is larger in all cases for the capped mRNAs than the uncapped mRNAs, reaching an order of magnitude difference for RNA7, and this effect is due almost entirely to the reduced rate in the absence of eIF4A for the capped versus uncapped mRNAs. Taken together, our data indicate that even for short mRNAs with low structural complexity, the 5′-cap inhibits recruitment in the absence of eIF4A, consistent with our previous observations with a natural mRNA and our proposal that the cap serves, in part, to enforce use of the canonical mRNA recruitment pathway (Mitchell et al., 2010).
DISCUSSION
Fifteen years ago it was suggested that the substrate for eIF4A – in vivo – is likely single stranded RNA (Rogers et al., 2002). Since then, high resolution crystal structures, genetics, and biochemical studies provided critical insights into its mechanism of catalysis, alone and in the context of eIF4F (Harms et al., 2014; Hilbert et al., 2011; Lindqvist et al., 2008; Merrick, 2015; Oberer et al., 2005; Schütz et al., 2008). More recently, Next Generation Sequencing (i.e. ribosome profiling) allowed holistic examination of the effects of eIF4A on global translation (Sen et al., 2015) and biochemical techniques gave clues as to how eIF4A and eIF4F may interact with the rest of the recruitment machinery (Gao et al., 2016; Garcia-Garcia et al., 2015; Kumar et al., 2016). However, the exact role and mechanism of eIF4A in mRNA recruitment to the PIC remain open questions.
Our data demonstrate that ATP hydrolysis by eIF4A stimulates the recruitment of both natural RPL41A mRNA, containing only a 24 nt 5′-UTR, and a 50 nt model mRNA that is expected to have little secondary or tertiary structure. We also report that the PIC stimulates the ATPase activity of eIF4A, suggesting that eIF4A, eIF4F, or both interact with the PIC to promote mRNA recruitment, in a manner requiring the i and g subunits of eIF3. We further observed that eIF4A accelerates recruitment of structured as well as unstructured mRNAs, and this acceleration does not correlate with the amount of secondary structure in the 5′-UTR. Instead, the requirement for eIF4A is most pronounced for mRNAs containing structural complexity throughout their sequence. We propose that eIF4A functions to relax the global structures of mRNAs – generated by the ensemble of many, often transient, base pairs and other stabilizing interactions between neighboring and distant parts of the mRNA – to facilitate interaction between the PIC and the 5′-UTR of the message. In addition, the observation that eIF4A accelerates the rate of recruitment of a short, unstructured model mRNA suggests that it may also act to load unwound segments of mRNA into the entry channel of the PIC, either by directly handing them off into the channel or by remodeling the PIC itself. We found that the presence of the cap structure confers a strong requirement for eIF4A for rapid recruitment even for unstructured mRNAs, which is consistent with a recent proposal (Kumar et al., 2016) that cap-eIF4E interaction favors mRNA recruitment via threading of the 5′-end into the 40S entry channel in a manner dependent on eIF4A, eIF4G, and eIF3.
The PIC stimulates eIF4A and eIF4F ATPase activity
In the prevailing model of mRNA recruitment, eIF4F is localized to the 5′-end of the mRNA via the eIF4E-cap interaction, where it collaborates with eIF4B to unwind the mRNA. Consistent with this model, eIF4G and eIF4B were the only proteins known to stimulate eIF4A activity in translation initiation (Hinnebusch, 2014; Mitchell et al., 2011). And yet, given the natural propensity of an mRNA to form structure it is difficult to envision how an mRNA could be unwound by eIF4F and eIF4B, released into the cytoplasm and then bound by the PIC without the mRNA reforming its structure. Moreover, recent work has demonstrated that yeast eIF4B binds the ribosome itself (Walker et al., 2013) and previous evidence suggested that mammalian eIF4B interacts with rRNA (Methot et al., 1996), thus blurring the lines between the PIC and the activated mRNP composed of mRNA, eIF4F and eIF4B. In another proposed model, eIF4F and eIF4B could interact with the PIC, forming a “holo-PIC” (Aitken and Lorsch, 2012) that relaxes the mRNA and attaches to it synchronously. Some support for a model in which eIF4F interacts with the PIC to promote mRNA recruitment came from hydroxyl radical footprinting experiments that indicate eIF4G binds to the 40S subunit near the eukaryotic expansion segment 6 of the 18S rRNA (Yu et al., 2011). In addition, in mammals (but not S. cerevisiae) eIF4G interacts with eIF3, which could serve to bring the eIF4F complex onto the PIC (des Georges et al., 2015). Our observation that the PIC stimulates the ATPase activity of eIF4A, both in the context of the eIF4F complex and in the absence of eIF4G•4E, indicates that eIF4A and eIF4F interact with the PIC, and is consistent with the holo-PIC model.
Our studies of eIF4A ATPase activity demonstrated that nearly all core components of the PIC are necessary for full acceleration of ATP hydrolysis, suggesting that the intact PIC is required for fully productive interaction with eIF4A and eIF4F (Figure 2). The absence of eIFs 2 or 3, or the 40S subunit significantly decreased the rate of ATP hydrolysis, and the presence of the 40S subunit and TC alone gave no stimulation of ATP hydrolysis beyond that afforded by eIF4F. An eIF3 subcomplex comprised of subunits a, b, and c but lacking subunits g and i, resulted in a similar rate decrease as when eIF3 was omitted entirely from the reaction. The g and i subunits of eIF3 have been implicated in mRNA recruitment and scanning (Aitken et al., 2016; Cuchalová et al., 2010; Valásek, 2012), and structural data suggest that they are located near the mRNA entry channel of the 40S subunit, on either the solvent or intersubunit face (Aylett et al., 2015; des Georges et al., 2015; Llacer et al., 2015). The observation that these eIF3 subunits appear at distinct locations near the mRNA entry channel in complexes either containing or lacking mRNA has led to the speculation that they might participate in a large-scale rearrangement of the PIC important for either initial attachment to the mRNA or scanning along it (Llacer et al., 2015; Simonetti et al., 2016). Our observation that the eIF3 g and i subunits are required for full stimulation of eIF4A’s ATPase activity is consistent with the possibility that eIF4A is located near the mRNA entry channel, where it can promote mRNA loading onto the PIC (Spirin, 2009).
The mechanism through which the PIC components stimulate eIF4A’s ATPase activity is not yet clear. Similar to eIF4G•4E, the PIC (in the absence of eIF4G•4E) increases the Vmax for ATP hydrolysis by eIF4A. Unlike eIF4G•4E, however, the PIC does not significantly decrease eIF4A’s Km for ATP, suggesting the mechanisms of stimulation are distinct. eIF4G acts as a “soft clamp” that holds the two RecA-like domains of eIF4A in close proximity to each other, in a conformation poised for ATP binding and hydrolysis (Hilbert et al., 2011; Oberer et al., 2005; Schütz et al., 2008). It seems possible that the interaction with one or more components of the PIC also alters the conformation of eIF4A to stimulate its ATPase activity, albeit in a manner distinct from eIF4G•4E that does not enhance binding of ATP. The fact that the PIC stimulates the activity of eIF4A in the absence of eIF4G•4E indicates that the effect does not have to be mediated through interaction with eIF4G•4E, although it is plausible that the mode of stimulation is different for eIF4A on its own and when it is part of the eIF4F complex.
eIF4A promotes recruitment of all mRNAs regardless of their degree of structure
A number of observations have suggested that the function of eIF4A is to unwind structures in the 5′-UTRs of mRNAs. In vitro, eIF4A can unwind model RNA duplexes (Andreou and Klostermeier, 2013b; Blum et al., 1992; Grifo et al., 1983; Lorsch and Herschlag, 1998b; Ray et al., 1985; Rogers et al., 1999, 2001; Seal et al., 1983), albeit at a rate slower than necessary to support the rate of translation initiation in vivo (Palmiter, 1975). The factor is required in reconstituted translation systems for 48S PIC formation (Benne and Hershey, 1978; Pestova and Kolupaeva, 2002; Schreier and Staehelin, 1973), and in mammalian extracts the eIF4A-dependence of translation of different reporter mRNAs was correlated with their degree of 5′-UTR structure (Svitkin et al., 2001). On the other hand, eIF4A has also been shown to stimulate initiation in vitro on mRNAs with low degrees of 5′-UTR structure (Blum et al., 1992; Pestova and Kolupaeva, 2002), and ribosome profiling studies have shown that the vast majority of mRNAs in yeast display a similar, strong dependence on eIF4A for efficient translation, whereas mRNAs with long, structured 5′-UTRs generally exhibit a special dependence on the helicase Ded1 in addition to their general requirement for eIF4A (Sen et al., 2015). The latter results suggested that eIF4A functions in loading all mRNAs onto the PIC independent of their 5′-UTR structures. Our observation that eIF4A accelerates the recruitment not just of the natural RPL41A mRNA and model mRNAs containing secondary structures in their 5′-ends, but also of unstructured mRNAs comprising CAA repeats, supports this proposal.
It is possible that eIF4A, in addition to alleviating structure in mRNA (see below), also plays a role in directing the hand-off of single-stranded mRNA segments to the PIC. It could do this by directly transferring mRNA into the entry channel of the 40S subunit. Another possibility is that eIF4A may directly modulate the conformation of the PIC itself (Figure 5), for example by opening the mRNA entry channel. In fact, a recent report suggests that mammalian eIF4A may be involved in modulating the conformation of the ribosome (Sokabe and Fraser, 2017) and several examples of DEAD-box helicases rearranging ribonucleoprotein complexes exist (Henn et al., 2012; Jankowsky, 2011; Linder and Jankowsky, 2011) including mammalian eIF4AIII, which is critical in formation of Exon Junction Complexes (Andersen et al., 2006; Ballut et al., 2005), and Dhx29, which binds to and is thought to modulate the mammalian ribosome (Hashem et al., 2013; Pisareva et al., 2008). Moreover, the bacterial ribosome has been demonstrated to possess intrinsic helicase activity (Qu et al., 2011; Takyar et al., 2005) and the residues responsible for this activity are preserved in the eukaryotic ribosome. In fact, we recently demonstrated that the equivalent residues in Rps3 – which is near the 40S latch and interacts with eIF3 – stabilize the PIC:mRNA interaction (Dong et al., 2017). It is thus possible that ATP hydrolysis by eIF4A might contribute to modulating this region, thereby promoting PIC attachment and/or scanning. Both the possibilities that eIF4A directly loads mRNA segments onto the PIC and that it modulates the conformation of the complex are consistent with our observation that the PIC stimulates the ATPase activity of eIF4A.
Global mRNA structure, not just structure in the 5′-UTR, inhibits mRNA recruitment
We observed that addition of native RPL41A mRNA sequences 3′ of the start codon inhibits recruitment of mRNA to the PIC, even if the 5′-UTR is made up of CAA repeats, and this inhibitory effect is ameliorated by eIF4A (Figure 3, compare RNA 4 to RNA 7). This result is surprising because in the canonical model eIF4A functions to resolve structures in the 5′-UTR. In combination, isolated hairpins in the 5′-UTR and structural complexity 3′ of the AUG codon synergistically inhibit mRNA recruitment (Figure 3, RNAs 8 and 9). Together, these results suggest that the global structure of the mRNA is a critical determinant of the efficiency of mRNA recruitment. We envision that the RPL41A sequences introduce an ensemble of relatively weak secondary or tertiary interactions that occlude the 5′-UTR and start codon and thus impede PIC attachment and AUG recognition, and that eIF4A can efficiently resolve these structural impediments. In addition, RNAs longer than their persistence length inherently fold back on themselves (Chen et al., 2012) and, by binding to single-stranded segments, eIF4A may serve to increase their persistence length, leading to untangling. It is intriguing that eIF4A was 15- to 20-fold more effective in overcoming the inhibitory effect of the RPL41A sequences versus the 5′-UTR hairpins in the RNAs containing one or the other inhibitory element (Figure 3C-D, RNAs 5-7). This could be explained by proposing that eIF4A is more efficient at resolving the relatively weak interactions that contribute to global mRNA structure compared to highly-stable local structures. Indeed, only a handful of native mRNAs are known to possess stable hairpin structures in yeast cells (Rouskin et al., 2014), yet eIF4A is essential for translation of virtually all mRNAs in vivo. Moreover, it was shown that Ded1 rather than eIF4A was required to overcome the inhibitory effects of hairpin insertions on reporter mRNA translation in vivo (Sen et al., 2015). Combined with these previous findings, our results support a model in which eIF4A acts to disrupt moderately stable, transient interactions throughout an mRNA that sequester the mRNA 5′-UTR or start codon within the global mRNA structure, whereas Ded1 is more effective in resolving stable, local secondary structures in the 5′-UTR or the initiation region of an mRNA.
Our proposal for eIF4A function is consistent with previous work suggesting that other DEAD-box helicases disrupt tertiary RNA interactions rather than unwinding stable hairpins (Pan et al., 2014) and previous reports that eIF4A is a very weak helicase when presented with stable RNA duplexes in vitro (Linder and Jankowsky, 2011; Rogers et al., 1999). Ded1 is a much stronger helicase than eIF4A or eIF4F in unwinding the same duplex substrates in vitro (Gao et al., 2016). Moreover, it was shown that eIF4A cannot substitute for Ded1, or the mammalian helicase Dhx29, to promote PIC scanning through highly stable hairpins inserted into model unstructured 5′-UTRs in a reconstituted mammalian system. Interestingly, Dhx29 could not substitute for eIF4A in facilitating 48S PIC assembly on native Beta-globin mRNA, supporting the notion of functional diversification of eIF4A versus Ded1 and Dhx29 in different aspects of initiation (Pisareva et al., 2008).
It is intriguing that inserting hairpins into the unstructured 5′-UTRs of our model mRNAs conferred strong inhibitory effects only when RPL41A sequences were present 3′ of the AUG codon (Figure 3B-C, RNAs 5-6 vs. 8-9), and that the hairpins dramatically increased the inhibition of mRNA recruitment beyond that produced by the RPL41A sequences alone. One possible explanation for this strong synergistic effect would be that the hairpins are stabilized by interactions of the unpaired bases in their loops with one or more short stretches of sequences within RPL41A. We can also envision that, in the absence of global structure conferred by the RPL41A sequences, the PIC can bypass the hairpins in the 5′-UTR and bind directly near the start codon, with the unstructured initiation region slotting into the 40S mRNA binding cleft. This slotting mechanism could be impeded by the presence of RPL41A sequences and attendant sequestration of the 5′-UTR within the global mRNA structure, requiring a switch to the scanning mechanism, with the mRNA 5′-end being fed into the entry channel pore (Kumar et al., 2016). The hairpin structures would strongly impede this threading mechanism and the relatively weak helicase activity of eIF4A could only partially overcome this impediment to PIC attachment and AUG recognition.
Perspectives
The work presented here addresses the apparent contradiction between the fact that eIF4A is an essential protein responsible for promoting the translation of virtually all mRNAs in vivo (Sen et al., 2015) and its status as one of the weaker RNA helicases known. It is curious that in the presence of related but more robust DEAD-box RNA helicases in the cell, eIF4A is an essential protein and that small changes in its concentration affect the rate of translation (Firczuk et al., 2013). Evolution is clearly capable of achieving more efficient helicase activity, thus the slow catalysis by eIF4A must be either sufficient or advantageous. Our data suggest that eIF4A contributes to mRNA recruitment not primarily by unwinding stable secondary structures in the 5′-UTR, at which it is relatively inefficient, but by resolving the overall mRNA structure, involving the large ensemble of different conformers stabilized by limited base-pairing and other individual interactions (Figure 5). The result of this structural “untangling” might be to facilitate identification of the 5′ end of the mRNA, or the AUG codon, by the PIC. In fact, our observation that the PIC stimulates eIF4A activity suggests that eIF4A or eIF4F might be part of a larger holoPIC complex that couples mRNA relaxation, initial mRNA loading, and possibly even scanning (the latter two processes are not resolved from one another in our assay).
If eIF4A does contribute to translation initiation as a component of the holoPIC, its presence in large excess of all other initiation factors and ribosomal subunits (Firczuk et al., 2013) remains a mystery. Perhaps excess eIF4A plays an additional role by binding to RNA unwound by eIF4F or by more potent helicases such as Ded1 (Firczuk et al., 2013; Gao et al., 2016), or that transiently become single-stranded owing to thermal fluctuations. The slow rate of ATP hydrolysis by eIF4A (kcat of ~0.5 min-1), considerably slower than the estimated rate of initiation in vivo (approximately 10 min-1)(Palmiter, 1975), might then prove advantageous by increasing the lifetime of eIF4A-mRNA interactions. Considering the >40-fold stimulation of eIF4A ATPase activity by the PIC together with eIF4G•4E observed here, we envision that scanning PICs would promote rapid ATP hydrolysis by such mRNA-bound eIF4A molecules encountered during scanning (Lindqvist et al., 2008), resulting in eIF4A dissociation from the 5′-UTR (Figure 5). This recurring PIC-eIF4A interaction might contribute to scanning processivity by ensuring that single-stranded mRNA is continuously presented at the PIC entry channel; the successive cycles of PIC-eIF4A interaction at the entry channel followed by eIF4A dissociation might also bias the directionality of scanning (Spirin, 2009) (Figure 5). If these mRNA-bound eIF4A•ATP complexes loaded sequentially onto eIF4G prior to ATP hydrolysis, release of mRNA into the entry channel, and dissociation of eIF4A•ADP from eIF4G, the model would be consistent with previous observations that an ATPase deficient mutant of eIF4A acts in a dominant-negative fashion to inhibit translation initiation in vitro (Pause et al., 1994), as the mutation would block dissociation of eIF4A molecules from the mRNA when they encounter eIF4G in the scanning PIC, and thereby impede progression through the 5′-UTR. This proposal is a variation on the model originally suggested by Sonenberg, Merrick, and colleagues, in which eIF4A molecules “recycle” through the eIF4F complex in order to promote mRNA recruitment and scanning (Yoder-Hill et al., 1993).
MATERIALS AND METHODS
Materials
ATP, GTP, CTP, and UTP (products 10585, 16800, 14121, 23160, respectively) were purchased from Affymetrix. [α-32P]-GTP was from PerkinElmer (product BLU006H250UC). ATP-γ-S, ADPCP, and ADPNP (products A1388, M7510, and A2647, respectively), S-adenosyl methionine (SAM) (product A7007), and the pyruvate kinase (900- 1400 units/mL)/lactate dehydrogenase (600-1000 units/mL) mix from rabbit muscle (product P0294) were from Sigma. NADH disodium salt was from Calbiochem (product 481913). Phosphoenolpyruvate potassium salt was purchased from Chem Impex International, Inc. (product 09711). RiboLock RNase inhibitor was from Thermo Fisher Scientific (product EO0381). The RNeasy RNA purification kit was purchased from Qiagen (product 74106). Exonuclease T was purchased from New England Biolabs (product M0265S). The Abnova Small RNA Marker was purchased from Abnova (product number R0007). SYBR Gold nucleic acid gel stain (product S11494) and Novex 15% TBE-Urea gels (product EC68852BOX) were purchased from Thermo Fisher Scientific. Corning 384-well plates were purchased from VWR (product 3544).
Reagent Preparation
Eukaryotic initiation factors – eIFs 1, 1A, 2, 3, 4A, 4B, 4E•4G, and 5 – as well as mRNA were prepared as described previously (Walker et al., 2013); see Supplementary Methods for more detail. tRNAi was charged with methionine as described previously (Walker and Fredrick, 2008). Following charging, Met-tRNAi was separated from contaminating ATP and other nucleotides (left over from the charging reaction) on a 5 mL General Electric (GE) desalting column equilibrated in 30 mM Sodium Acetate (NaOAc), pH 5.5. This step was essential in order to measure the ATP dependence of mRNA recruitment and to accurately control the concentration of ATP in experiments. The Met-tRNAi and free nucleotide peaks were confirmed with individual standards prepared identically to a charging reaction. Eluted Met-tRNAi was precipitated with 3 volumes of 100% ethanol at –20°C overnight, pelleted, and resuspended in 30 mM NaOAc, pH 5.5.
mRNA capping
mRNAs were capped as described previously (Aitken et al., 2016). Briefly, RNAs 2-10 at 5 μM were combined with 50 μM GTP, 0.67 μM [α-32P]-GTP, 100 μM S-adenosyl methionine (SAM), 1 U/μl RiboLock, and 0.15 μM D1/D12 vaccinia virus capping enzyme. RNA 1 was present at 50 μM in the reaction in the presence of 100 μM GTP, with all other conditions identical. Reactions were incubated at 37 °C for 90 minutes and purified using the RNeasy (Qiagen) RNA purification kit.
mRNA Recruitment Assay
In vitro mRNA recruitment assays were carried out as described previously with minor modifications (Aitken et al., 2016; Walker et al., 2013). All reactions were carried out at 26°C in “Recon” buffer containing 30 mM HEPES•KOH, pH 7.4, 100 mM KOAc, 3 mM Mg(OAc)2, and 2 mM DTT. 15 μl reactions contained final concentrations of 500 nM GDPNP•Mg2+, 300 nM eIF2, 300 nM Met-tRNAi, 1 μM eIF1, 1 μM eIF1A, 30 nM 40S ribosomal subunits, 300 nM eIF3, 5 μM eIF4A, 50 nM eIF4G•eIF4E, 300 nM eIF4B, and 1 U/μL Ribolock RNase inhibitor (Thermo). To form the ternary complex (TC), GDPNP and eIF2 were incubated for 10 minutes, Met-tRNAi was then added to the reaction and incubated an additional 7 minutes. The remainder of the components, except mRNA and ATP, were added to the TC and incubated for an additional 10 minutes to allow complex formation. Reactions were initiated with a mix containing final concentrations of 15 nM mRNA and ATP•Mg2+. Experiments varying the concentration of eIF4A were carried out in the presence of 5 mM ATP. Experiments varying ATP were carried out in the presence of 5 μM eIF4A. To take timepoints, 2 μl reaction aliquots were combined with 1 μl of 0.02% bromophenol blue and xylene cyanol dye in 40% sucrose containing a final concentration of a 25-fold excess of unlabeled mRNA (cold chase), identical to the labeled mRNA for that reaction. Two μl of the chased reaction were immediately loaded and resolved on a native 4% (37.5:1) polyacrylamide gel using a Hoefer SE260 Mighty Small II Deluxe Mini Vertical Electrophoresis Unit at a potential of 200 volts for 50 minutes. The electrophoresis unit was cooled to 22°C by a circulating water bath. Gels and running buffer contained 34 mM Tris Base, 57 mM HEPES, 1 mM EDTA, and 25 mM MgCl2 (“THEM”). Gels were exposed to a phosphor plate overnight at –20°C, the plates visualized on a GE Typhoon 9500 FLA, and the fraction of recruited mRNA bands (48S complex) versus the total signal in the lane was quantified using ImageQuant software. Data were plotted and fit using KaleidaGraph 4.5 software. Recruitment time courses were fit to a single exponential rate equation: y = A*(1-exp(-kobs*t)), where t is time, A is amplitude, and kobs is the observed rate constant. Observed rates were plotted against the concentration of the titrant and fit to a hyperbolic equation: y = b+((kmax*x)/(K1/2+x)) where x is the concentration of the titrant, kmax is the maximal observed rate of mRNA recruitment when the reaction is saturated by the factor titrated (e.g. eIF4A), K1/2 is the concentration of the factor required to achieve 1/2Vmax, and b is the rate in the absence of the titrated factor (i.e., the y-intercept).
NADH-coupled ATPase Assay
The NADH-coupled ATPase assay was adapted from previously described methods with some modifications (Bradley and De La Cruz, 2012; Kiianitsa et al., 2003). All ATPase experiments were carried out in 384-well Corning 3544 plates on a Tecan Infinite M1000PRO microplate reader at 26°C. Using a standard curve we determined that a 10 μL reaction with 1 mM NADH on a Corning 3544 microplate gives an absorbance of 1.23 Optical Density of 340 nm light (OD340) in the microplate reader. OD340 was measured every 20 seconds for 40 minutes, plotted vs. time for individual reactions, and fit to y = mx + b where m is the slope, x is time in minutes, and b is the y-intercept. Thus, m is OD340 of NADH/min. It follows that,
Note that the absolute value of m (| m |) was used because the slope is a negative value due to loss of absorbance over time. NADH consumed is stoichiometric with ATP regenerated thus, mM NADH/min = mM ATP/min.
“30 nM PIC:” 12 μl reactions (final volume) were at the same final concentrations as described above in the mRNA Recruitment Assay section: 500 nM GDPNP•Mg2+, 300 nM eIF2, 300 nM Met-tRNAi, 1 μM eIF1, 1 μM eIF1A, 30 nM 40S ribosomal subunits, 300 nM eIF3, 5 μM eIF4A, 50 nM eIF4G•eIF4E, 300 nM eIF4B, and 1 U/μL Ribolock RNase Inhibitor. PICs were formed at 2x of the final concentration in 1x Recon buffer, in the absence of mRNA and ATP. Subsequently, the PICs were combined with the Reporter Mix (added as a 10x stock of the final concentrations all in 1x Recon buffer) resulting in concentrations in the final reaction of 2.5 mM phosphoenolpyruvate, 1 mM NADH, and a 1/250 dilution of the pyruvate kinase (600-1,000 units/mL) and lactate dehydrogenase (900-1400 units/mL) mix (PK/LDH mix). Reactions were brought up to volume with 1x Recon buffer, such that when they were initiated by addition of mRNA (added as a 10x stock of the final concentration in 1 x Recon) and ATP•Mg2+ (added as a 4x stock of the final concentration in 1x Recon buffer) the total reaction volume was 12 μl. 10 μl of the reaction were then immediately transferred to the microplate for analysis by the Tecan plate reader and changes in absorbance of 340 nm light were monitored over time, taking readings every 20 seconds for 40 minutes. Because the assay measures the reaction velocity (i.e. slope of a straight line), the lag in time between initiating the reaction and start of the measurements by the plate reader has no effect on the results. Initiating the reactions using an injection, capable of monitoring rapid kinetics did not reveal any different results; i.e., there was no evidence of a “burst” phase in the initial part of the reaction. Increasing or decreasing the concentration of the PK/LDH mix by 3-fold did not influence the observed rate of ATP hydrolysis (Figure 2 – figure supplement 1A), indicating that the rate of NADH oxidation is not limited by PK/LDH activity. Also, when ATP, eIF4A, or PK/LDH was absent from the reaction, there was no change in absorbance at 340 nm over 1 hour.
“0.5 μM PIC:” Reactions were carried out identically as described in the “30 nM PIC” above except the concentrations in the final reaction were as follows: 1 mM GDPNP•Mg2+, 500 nM eIF2, 500 nM Met-tRNAi, 1 μM eIF1, 1 μM eIF1A, 500 nM 40S ribosomal subunits, 500 nM eIF3, 5 μM eIF4A, 500 nM eIF4G•4E, 500 nM eIF4B, 500 nM eIF5, 5 mM ATP•Mg2+, 500 nM mRNA, and 1 U/μl RiboLock RNase inhibitor.
Exonuclease T RNA Digest
In a 20 μl reaction 0.5 pmol/μl of RNA was incubated with 0.75 U/μl of RNase Exonuclease T in 1x NEB buffer 4 at 26°C for 18 hours. RNA (4 pmol total RNA per lane) was loaded and resolved on a Novex 15% Tris Borate EDTA Urea gel and stained with SYBR Gold nucleic acid gel stain, diluted 1/10,000, for 5 minutes and visualized on a General Electric Typhoon FLA 9500.
COMPETING INTERESTS
The authors declare no competing interests.
ACKNOWLEDGMENTS
The authors would like to acknowledge Tom Dever and Nicholas Guydosh for their thoughtful and critical suggestions. This work was supported by the Intramural Research Program (JRL and AGH) of the National Institutes of Health (NIH).