Alzheimer's disease (AD) is one of the most common neurodegenerative diseases at the present time. The disease is characterized by the formation of neurofibrillary tangles and plaques in the brain, leading to neuronal dysfunction, neuronal loss and finally death. The main component of the plaques is the amyloid-β peptide (Aβ), a 39–43 amino acids long hydrophobic peptide generated by the cleavage of the amyloid precursor, which accumulates in the form of soluble and non-soluble aggregates.

The connection between Apolipoprotein E (ApoE) and AD is well established [1],[2]. Structurally, ApoE is a 299 residues protein with an N-terminal domain involved in binding to heparin, low density lipoprotein receptors (LDLR) and LDLR-related proteins [3],[4]. The C-terminal domain has been related to heparin and lipid binding [5],[6]. Three main isoforms have been described for human ApoE, i.e. ApoE2, ApoE3 and ApoE4. The standard variant is ApoE3, while ApoE2 is defective for receptor binding, causing APOE ε2/ε2 homozygotic individuals to have a higher predisposition to diseases related to high amounts of cholesterol and triglycerides [3],[7]. For ApoE4, the receptor binding affinity remains unaffected, but APOE ε4/ε4 homozygotic individuals have higher risk for coronary heart disease and a significantly greater risk for developing AD.[1],[8] Around 80% of all AD cases are related to the genetic variance at the ApoE locus [9],[10].

The only difference between the ApoE isoforms is found in residues 112 and 158, where Cys112/Cys158 corresponds to ApoE2, Cys112/Arg158 to ApoE3, and Arg112/Arg158 to ApoE4. The presence of cysteines at these positions confers oligomerization properties to ApoE. Indeed, ApoE2 and ApoE3 are able to form disulfide-linked homo- and hetero-oligomers due to the presence of “respectively” two and one Cys residue. ApoE4 lacks the possibility of strong disulfide linking; however, it is unclear whether weaker interactions could promote the oligomerization of ApoE4. The Cys/Arg substitution in ApoE4 also has molecular impact in terms of intra-protein polar contacts: the orientation of Arg61 is different in ApoE4 compared to ApoE3; the orientation of Arg61 towards the C-terminal domain (See Figure 1A) facilitates a salt bridge between Arg61 and Glu255. The electrostatic interaction between Arg61 and Glu255 promotes an N- and C-domain interaction that packs the structure tighter, which seems crucial for the interaction of ApoE4 with triglyceride-rich lipoproteins. The interaction between Arg61 and Glu255 is absent in ApoE3 leading to a more open structure and a preferential binding of phospholipid-rich high-density lipoproteins [11],[12]. Chemical and thermal denaturation experiments have shown that the most unstable structure belongs to ApoE4, which displays a partially unfolded intermediate (molten globule) containing some β structure that may be related to the fact that ApoE4 enhances the deposition of Aβ [13],[14].

Although different mechanisms have been proposed to explain the physiological and pathological relationship between ApoE and the Aβ peptide, the details of the interaction between ApoE and Aβ at a molecular level are unknown. Such detailed knowledge is however important for the understanding of the pathological mechanisms of AD, and may also help to identify potential therapeutic target sites where the interaction between ApoE4 and Aβ can be blocked.

In the present study we are using molecular docking simulations based on global minimum energy to investigate the interaction process of Aβ with the N-terminal domain of the different ApoE isoforms in order to determine potential Aβ peptide binding sites in ApoE. In the next step, molecular dynamics (MD) calculations are undertaken to explore the conformational dynamics of ApoE under Aβ interaction and evaluate the stability of each of the ApoE-Aβ complexes. From the analysis and the statistics of the electrostatic interactions of the three ApoE isoforms, we present a model explaining the role of the Aβ-ApoE interaction and its relevance for AD.

Molecular dockings followed by MD simulations were used to study the interaction of Aβ with the different isoforms of ApoE. In order to study the Aβ peptide binding site on the N-terminal domains of the three ApoE truncated isoforms we used the Aβ(1–40) peptide as ligand, employing an SDS-induced α-helix solution structure previously determined by NMR spectroscopy [15]. Indeed, such helical fold in the Aβ monomeric state (non-aggregated) has been shown to be the most populated one in highly hydrophobic environments [16]. On the other hand, the structures of the three ApoE truncated isoforms were taken from lipid-free structure determinations by X-ray crystallography [11],[17],[18], which correspond only to the N-terminal domain (144 residues including the LDLR domanin of ApoE). Water molecules in the pdb files were removed prior to docking and energy minimizations were carried out to refine the structures.

All 3D models of the ApoE-Aβ complexes were found to be quite different. Although the Aβ(1–40) peptide assembles between the first and fourth ApoE helix for all ApoE isoforms, the orientation of the peptide was found to depend on the ApoE variant (Figure 1B; see Figure S1 for comparison of the 10 lowest energy solutions for each isoform). For ApoE2 and ApoE4, the C-terminus of the peptide faces the N-terminus of the protein, though the assembly is different. For ApoE3, the peptide is turned around, and the N-terminus of the peptide faces the N-terminus of the protein. Early studies indicated that ApoE interaction with Aβ fibrils is partially dependent on ionic interactions [19]. Thus, the single change of Cys158 in ApoE2 to Arg158 in ApoE3 changes the distribution of ionic residues influencing the assembly of Aβ (1–40), while the double change of Cys112 and Cys158 to Arg112 and Arg158 in ApoE4 distributes the ionic residues in an ApoE2-like way.

A 10 ns classical MD simulation including explicit water of the three ApoE isoforms together with the Aβ peptide was carried out on each of the lowest energy ApoE-Aβ models obtained by docking calculations as well as on each isolated species. Figure 1C shows the root-mean-square deviation (RMSD) of the MD simulation for the three ApoE isoforms in the presence and absence of the peptide. In their unbound form, no conformational transitions were detected for the ApoE isoforms, in agreement with previous results [20]. However, in presence of the peptide, different behaviors were observed between the isoforms. Despite the existence of interaction, no conformational transitions were detected for the ApoE2-Aβ or the ApoE3-Aβ complexes. However, the ApoE4-Aβ complex showed a large conformational transition indicated by a significant RMSD change of about 10 Å in the 10 ns timescale (Figure 1C).

In Figure 1D, four snapshots of the 10 ns MD simulation for the ApoE4-Aβ complex are presented. Focusing on ApoE4, during the first 0.3 ns, the third helix of ApoE4 started to unfold and a loop appeared between residues 112 and 92 which affected the whole third helix. This structural disturbance was caused by the onset of new electrostatic interactions rising from the interaction with the peptide. For the Aβ peptide, the first conformational change appeared in the Glu22-Asp23 region. At 1ns the second helix of ApoE4 showed a conformational change. In the snapshots of 5 ns, the first and fourth helices of ApoE4 were still stable, but at 10 ns a large conformational change had occurred, coinciding with a fully extended Aβ(1–40) peptide. At 10 ns, the hydrophobic groups inside the ApoE4 helices had become exposed to the solvent. The interruption of the stable salt bridge network by external electrostatic interactions (coming from the peptide) was thus transmitted from the dense helix region to the whole protein, causing a severe loss of α-helical structure.

Further investigation on the conformational change induced in ApoE4 by the complexation with Aβ was carried out through the analysis of the distances between charged residues. For this analysis, direct salt bridges have been assumed to be around 4.3 Å, whereas indirect or water-mediated salt bridges have been assumed to have a distance between 4.3 and 7.0 Å as reported by Dzubiella et al. [21]. In the most stable ApoE4-Aβ complex, the peptide interacted with helices I and IV of ApoE4. The Aβ residues responsible for these interactions were the negatively charged Asp1 and Asp23, which interacted with positively charged arginines in ApoE4 (Arg38 in helix I and Arg142 in helix IV respectively). The direct salt bridge between Aβ_Asp23 and ApoE4_Arg38 was very strong (Figure 2A), while the salt bridge between Aβ_Asp1 and ApoE4_Arg142 did not exist during most of the MD simulation, and only became more plausible at the end of the MD simulation (the distance for an indirect salt bridge being reached after circa 8 ns, Figure 2A). Focusing on helices I and II of the N-terminal domain of ApoE4, the distance between Arg38 and Asp35 changed during the 10 ns time window (see Figure 2B). A transition occurred from 10 to 2.5 Å in the 2 ns time window, which then went back to 10 Å (indicating the breaking of the Arg38-Asp35 salt bridge), and became stable at 7 ns. For comparison, the same distance is shown for the MD simulation of ApoE4 alone, where no change at all can be seen, as the distance was within the 4.3 and 7.0 Å range during the whole 10 ns (Figure 2B). The salt bridge between Asp35 and Arg32 was stable below 4.4 Å before 2 ns (Figure 2C). For ApoE4 in the absence of Aβ, the distance remained constant around the 7.0 Å threshold, making it difficult to determine the existence of an indirect salt bridge. For the ApoE4-Aβ complex, the direct salt bridge involving Arg32 and Glu66 (in helices I and II, respectively) was affected and showed a maximal fluctuation from 2.5 to 7.5 Å and then back to 2.5 Å in the 10 ns time window (Figure 2D). In the ApoE4 alone MD, this Arg32-Glu66 pair did not show any propensity to interact (the distance was over 7.0 Å during the whole 10 ns).

For helices II and III of the N-terminal domain of ApoE4, the transitions of the Arg61-Glu66, Arg61-Glu109 and Glu109-Arg112 salt bridges were monitored in the ApoE4-Aβ complex (see Figure 3). At 5 ns the distance between Glu66 and Arg61 from helix II dropped from about 10 to 3 Å, becoming stable and forming a direct salt bridge (see Figure 3A). However, for ApoE4 alone, this salt bridge was never formed. For the ApoE4-Aβ complex in the 5 ns interval, the direct salt bridge between Arg61 and Glu109 (helix III) broke down (the distance increased from about 3 to 12.5 Å, Figure 3B). In ApoE4 alone the distance for this pair was out of range during most of the MD simulation. However, the distance between Glu109 and Arg112 (both in helix III) remained relatively stable and below the salt bridge distance threshold (Figure 3C). In the ApoE4-Aβ complex, the Glu109-Arg112 salt bridge was direct (below 4.3 Å), whereas for ApoE4 alone, the salt bridge was more indirect or water mediated. The MD results for the Arg112-Asp110 pair (Figure 3D) were similar to those for the Arg112-Glu109 pair. In the complex, the distance for the electrostatic pair indicated a direct salt bridge, whereas for ApoE4 alone, this distance was closer to an indirect salt bridge (if any).

Electrostatic interactions between helix III and helix IV were more complex and insensitive to the interaction with the peptide, and the bridge network involving helices III and IV remained stable during the simulation (data not shown). In the ApoE4-Aβ complex, the interaction between Arg112 with Asp110 and Glu109 in helix III is connected to helix IV via the Asp110-Arg147 and Asp107-Arg151 ion pairs (see Figure 4). Also Asp107 in helix III and Asp151 in helix IV interacted with Arg147. Another inter-helical ion pair network existed between Arg103, Glu96 and Arg92 in helix III and Arg150, Arg153, Arg154 and Arg158 in helix IV (see Figure 4). Arg158 acted as a bridge for extending the electrostatic interaction between Glu96 and Arg92.