Unfolding simulations reveal the mechanism of extreme unfolding cooperativity in the kinetically stable alpha-lytic protease

Abstract

Kinetically stable proteins, those whose stability is derived from their slow unfolding kinetics and not thermodynamics, are examples of evolution's best attempts at suppressing unfolding. Especially in highly proteolytic environments, both partially and fully unfolded proteins face potential inactivation through degradation and/or aggregation, hence, slowing unfolding can greatly extend a protein's functional lifetime. The prokaryotic serine protease alpha-lytic protease (alphaLP) has done just that, as its unfolding is both very slow (t(1/2) approximately 1 year) and so cooperative that partial unfolding is negligible, providing a functional advantage over its thermodynamically stable homologs, such as trypsin. Previous studies have identified regions of the domain interface as critical to alphaLP unfolding, though a complete description of the unfolding pathway is missing. In order to identify the alphaLP unfolding pathway and the mechanism for its extreme cooperativity, we performed high temperature molecular dynamics unfolding simulations of both alphaLP and trypsin. The simulated alphaLP unfolding pathway produces a robust transition state ensemble consistent with prior biochemical experiments and clearly shows that unfolding proceeds through a preferential disruption of the domain interface. Through a novel method of calculating unfolding cooperativity, we show that alphaLP unfolds extremely cooperatively while trypsin unfolds gradually. Finally, by examining the behavior of both domain interfaces, we propose a model for the differential unfolding cooperativity of alphaLP and trypsin involving three key regions that differ between the kinetically stable and thermodynamically stable classes of serine proteases.

Figure 1. The structure of αLP.

The molecule is colored dark blue at the N-terminus progressing to red at the C-terminus. Important structural regions for this work are labeled, including the active site (the catalytic triad of H57, D102, and S195 are represented in ball-and-stick), the N-terminal β-strand (β1, blue), the cis-proline turn (CPT, teal), the Domain Bridge (green), and the C-terminal β-hairpin (CβH, yellow).

Figure 2. αLP unfolds significantly and reproducibly at high temperature but is stable at 298K.

(a) At 500K, αLP unfolds quickly and fully in the five 8.1 ns unfolding simulations while it remains native-like at 298K as measured by Cα RMSD (black, 298K; red, 500K1; green, 500K2; blue, 500K3; orange, 500K4; purple, 500K5). (b,c,d) Colors used are the same as in (a). 500K1 and 500K3 were chosen due to the relatively large difference in their unfolding times. (b) Cα RMSD for the first 4 ns of 298K, 500K1, and 500K3 indicates unfolding occurs early at high temperature. (c) The NPSASA for the first 4 ns of 500K1, 500K3, and 298K is shown. After a short thermal equilibration, both 500K1 and 500K3 reach values ∼5000 Ų and level off until exposing much more non-polar surface at 1.3 and 1.8 ns, respectively. At 298K, very little increase is seen in NPSASA. (d) ALF measures short-term fluctuations in structure and is an indicator of conformational flexibility of the molecule's current state. For both 500K1 and 500K3, conformational flexibility is low and then suddenly rises concurrently with NPSASA. ALF is low and stable at 298K. For all but (d), the data is smoothed with a 0.019 ns running average.

Figure 3. Selected structures from the 500K1 simulation illustrate the αLP unfolding pathway.

Time in the simulation and Cα RMSD to the crystal structure are indicated.

Figure 4. Conformational clustering effectively defines the exit from the native state.

3-D representation of conformational clustering of 500K1 generated by multi-dimensional scaling of the all-versus-all Cα RMSD. Each sphere is a conformation from every 10 ps of 500K1 and is connected by sticks to the preceding and following conformation. The earliest conformations are colored blue and the latest, red. E1, E2, and E3 represent the first through third eigenvectors from the multi-dimensional scaling. The exit from the native cluster is identified by the arrow and is at 1.41 ns.

Figure 5. Property-based landscapes clearly separate native from non-native conformations.

(a) The unfolding landscape is generated from all five unfolding simulations using native contacts and NPSASA as order parameters. 1-D histograms of native contacts and NPSASA are found to the right and above the landscape, respectively. The landscape was generated by taking the negative natural logarithm of the 2-D histogram with white being unobserved in the simulations, dark red the least populated, and progressing to dark blue as the most populated. The native state is in the upper left corner. A less populated region (indicated by the arrow) centered around 450 native contacts and 5900 Ų separates native-like conformations from non-native conformations and represents the TSE. (inset) Zoomed-in view of TSE region, with trace of 500K1 overlaid. 500K1 crosses the TSE barrier only once and in less than 10 ps, between 1.41 and 1.42 ns; other simulations exhibit similar behavior. (b) Principal components analysis was used to reduced ten conformational properties to two dimensions (see Methods for list of properties). Coloring is the same as in (a). The native state is the well-populated region at the bottom of the figure and is separated from the non-native state by a barrier near −2.7 in PC1 (indicated by the arrow). Note that significant spread in PC2 is only seen after the TSE, as many more conformations are accessible in the unfolded state.

Figure 6. The structure of the αLP TSE.

Deviations from native in the αLP TSE are restricted to several regions, mostly in the domain interface. Stereo view of the average Cα RMSD at each residue in the PCA landscape TSE from the crystal structure mapped onto the crystal structure. Both the thickness of the cartoon and the color indicate the deviation from native, with thicker representations meaning larger deviations.

Figure 7. Contacts at the domain interface are preferentially broken at the unfolding transition.

(a) The fraction of intra-domain (black), inter-domain (blue), native intra-domain (gray), and native inter-domain (red) are shown for the first 3 ns of 500K1. Inter-domain contacts experience a sharp drop at the native cluster exit (dashed vertical line, 1.41 ns) and continue to decline. Intra-domain contacts are lost more gradually. Shortly after unfolding, ∼90% of native inter-domain contacts are lost permanently. (b) The fraction of native domain bridge-domain bridge (black) and native domain bridge-other (gray) contacts for the first 3 ns of 500K1. Both decline sharply at the native cluster exit (dashed vertical line) and do not return to native-like values. For both (a) and (b), the data is smoothed with a 0.019 ns running average.

Figure 8. αLP unfolds significantly more cooperatively than trypsin.

Cooperativity is measured by counting the number of sampled conformations <3 Å Cα RMSD (two-fit Cα RMSD, see Methods) from the conformation at each time point. (a) Cooperativity for the first 4 ns of 500K1. Starting flat and steeply dropping indicates a very cooperative unfolding transition for αLP. (b) Cooperativity for the first 4 ns of 500K2T (trypsin). Trypsin unfolds much less cooperatively than αLP, as seen by the gradual rise early in the simulation and the gradual and noisy decline starting at 1.4 ns. (a) and (b) Vertical dashed line indicates position of the native cluster exit in each simulation.

Figure 9. Solvation of the domain interface during unfolding differs significantly between αLP and trypsin.

(a) - (d) Residues colored light red are solvent-exposed at the TSE, light green residues become exposed within 600 ps of the TSE, and light blue residues are still buried 600 ps past the TSE. (a) and (c) αLP, (b) and (d) trypsin. (a) and (b) All buried domain interface residues, (c) and (d) the subset of (a) and (b) where the position is conserved and found at the domain interfaces of both prokaryotic and metazoan proteases. Notably, many fewer buried residues of the αLP domain interface are solvated at the TSE compared to trypsin, even after eliminating the non-conserved positions.