Molecular chaperones of the Hsp110 family act as nucleotide exchange factors of Hsp70s

Abstract

Hsp70 molecular chaperones function in protein folding in a manner dependent on regulation by co-chaperones. Hsp40s increase the low intrinsic ATPase activity of Hsp70, and nucleotide exchange factors (NEFs) remove ADP after ATP hydrolysis, enabling a new Hsp70 interaction cycle with non-native protein substrate. Here, we show that members of the Hsp70-related Hsp110 family cooperate with Hsp70 in protein folding in the eukaryotic cytosol. Mammalian Hsp110 and the yeast homologues Sse1p/2p catalyze efficient nucleotide exchange on Hsp70 and its orthologue in Saccharomyces cerevisiae, Ssa1p, respectively. Moreover, Sse1p has the same effect on Ssb1p, a ribosome-associated isoform of Hsp70 in yeast. Mutational analysis revealed that the N-terminal ATPase domain and the ultimate C-terminus of Sse1p are required for nucleotide exchange activity. The Hsp110 homologues significantly increase the rate and yield of Hsp70-mediated re-folding of thermally denatured firefly luciferase in vitro. Similarly, deletion of SSE1 causes a firefly luciferase folding defect in yeast cells under heat stress in vivo. Our data indicate that Hsp110 proteins are important components of the eukaryotic Hsp70 machinery of protein folding.

Figure 1

Hsp110 accelerates nucleotide exchange on Hsp70. (A) Accelerated dissociation of MABA-ADP from Ssa1p as monitored by stopped-flow fluorescence spectroscopy. Equimolar amounts of MABA-ADP and the indicated Hsp70 homologue were preincubated to form a complex, which was then mixed with an excess of ADP either in presence or absence of Sse1p. (B) Comparison of the efficiencies of nucleotide exchange in the presence of Sse1p and the canonical NEF, Fes1p. When applied at the same concentration (0.5 μM), Sse1p accelerates nucleotide release more efficiently than Fes1p. (C) Accelerated dissociation of MABA-ADP from Ssb1p. (D) The effect of human Hsp110 on the displacement of MABA-ADP from human Hsp70. (E) Release of MABA-ADP from Ssa1p by Sse2p. (F) Ssa1p does not trigger displacement of MABA-ADP from Sse1p. In all panels, effector-triggered and spontaneous dissociation is indicated by open and closed circles, respectively. Fes1p-triggered dissociation is indicated by closed squares. The molar ratio of effector to Hsp70 was 1:2 in all experiments.

Figure 2

Dependence of nucleotide dissociation rate constant on NEF concentration. (A) Time course of displacement of MABA-ADP from Ssa1p–MABA-ADP complexes in the presence of increasing concentrations (0–6 μM) of Sse1p or (B) the canonical NEF Fes1p. For clarity, only the first second of traces has been shown. In both cases, higher concentrations of NEF lead to faster nucleotide exchange. (C) Observed dissociation rate constants were plotted versus NEF concentration. Each data point represents the mean of three measurements. The maximal nucleotide dissociation constant was estimated to be 114 s⁻¹ for Sse1p and 29 s⁻¹ for Fes1p.

Figure 3

Mutational analysis of Sse1p function. (A) Schematic representation of a set of Sse1p constructs assayed for their ability to accelerate nucleotide exchange on Ssa1p and Ssb1p. (B, C) Nucleotide exchange activity of the Sse1p constructs on Ssa1p and Ssb1p, respectively. Sse1p variants and Ssa1p or Ssb1p were mixed at a molar ratio of 5:1. In the bar graphs, the average nucleotide exchange activity of wt Sse1p was set to 1. The ATP binding mutant G233D retained only about 5% of wt activity, that is, k_off is slightly above the spontaneous release rate.

Figure 4

Hsp110 accelerates substrate release from Hsp70. (A) Hsp110 accelerates displacement of fluorescent dye-labeled peptide (D-NR) from nucleotide free Hsp70–D-NR complex in an ATP-dependent manner. Hsp70–D-NR was mixed with the indicated combination of unlabeled peptide (NR), Hsp110 (110), and ATP, and release of D-NR was monitored by stopped-flow fluorimetry. Components shown in parentheses indicate content of stopped-flow syringes, and ‘+' indicates the mixing event. (B) Acceleration of D-NR release from nucleotide free Hsp70–D-NR complex triggered by the NEF HspBP1. (C) Hsp110-mediated acceleration of D-NR release from an ADP–Hsp70–D-NR complex in an ATP-dependent manner. Preformed ADP–Hsp70–D-NR complex was mixed with the indicated components and analyzed as in (A). (D) Bar graph representation of the peptide (D-NR) release half times from Hsp70–D-NR and ADP–Hsp70–D-NR complexes under the conditions tested.

Figure 5

Hsp110 and Hsp70 mediate luciferase refolding in an Hsp40-dependent manner. (A) Luciferase refolding after preincubation with Hsc70. Firefly luciferase was heat-denatured at 42°C in the presence of Hsc70. Refolding was performed at 30°C in the presence of either Hsp110, Hsp40, or both, and ATP. In total, 100% activity corresponds to the enzyme activity of native luciferase in refolding buffer. (B) Luciferase refolding after preincubation with Hsp110 or Hsc70. Here, luciferase was denatured at 42°C in presence of Hsp110 or Hsc70 and folded at 30°C by adding ATP and different combinations of Hsc70, Hsp110, and Hsp40. Folding yields were similar irrespective of the order of Hsc70 and Hsp110 addition, indicating that the prevention of aggregation activity of Hsp110 is not a critical determinant for efficient protein refolding by the Hsp70–Hsp110 system. (C) Luciferase refolding by Ssa1p, Sse1p, and Ydj1p (yeast Hsp70/Hsp110/Hsp40). Luciferase was denatured in the presence of Ssa1p as described in (A). (D) Refolding of chemically denatured luciferase by Hsp70/Hsp110/Hsp40. (E) Hsp110 concentration dependence of luciferase refolding by the Hsp70/Hsp110/Hsp40 system. The concentrations of all other components were unchanged.

Figure 6

De novo folding of luciferase under thermal stress conditions is dependent on Sse1p levels. (A) Luciferase activity measurements in wt yeast, an SSE1 deletion strain (sse1Δ), and an SSE1 overexpression strain (SSE1↑). Equal numbers of cells were transferred into media that induces luciferase synthesis and grown at 37°C. Aliquots of cells were taken at the indicated time points after induction, and luciferase activity was measured in vivo. SLA was determined 6 h postinduction, revealing that deletion and overexpression of SSE1 reduced the SLA to 27 and 54% of wt levels, respectively. (B) Luciferase protein levels are similar in analyzed yeast strains. Aliquots of cells from (A) were lysed at the indicated time points, and luciferase protein levels were analyzed via SDS–PAGE and Western blotting.

Figure 7

Hypothetical model of cooperative protein folding by Hsp70 and Hsp110. Sequence signatures in an unfolded multidomain protein are recognized by either Hsp70 or Hsp110. Concerted release of Hsp70 and Hsp110 triggers efficient folding of domain A (i.e., a structural unit that folds cooperatively), and subsequent release of Hsp70 triggers folding of domain B.