Interactions of Pleckstrin Homology Domains with Membranes: Adding Back the Bilayer via High-Throughput Molecular Dynamics

Abstract

A molecular simulation pipeline for determining the mode of interaction of pleckstrin homology (PH) domains with phosphatidylinositol phosphate (PIP)-containing lipid bilayers is presented. We evaluate our methodology for the GRP1 PH domain via comparison with structural and biophysical data. Coarse-grained simulations yield a 2D density landscape for PH/membrane interactions alongside residue contact profiles. Predictions of the membrane localization and interactions of 13 PH domains reveal canonical, non-canonical, and dual PIP-binding sites on the proteins. Thus, the PH domains associate with the PIP molecules in the membrane via a highly positively charged loop. Some PH domains exhibit modes of interaction with PIP-containing membranes additional to this canonical binding mode. All 13 PH domains cause a degree of local clustering of PIP molecules upon binding to the membrane. This provides a global picture of PH domain interactions with membranes. The high-throughput approach could be extended to other families of peripheral membrane proteins.

Graphical abstract

Figure 1

The PH Domain/Bilayer Simulation Pipeline (A) Snapshot of a selected simulation demonstrating the localization of the GRP1 PH domain to the lipid bilayer. The GRP1 PH domain is shown in yellow. PIP₃ molecules are shown in green/red/bronze, and the POPC and POPS lipids are shown as silver lines (phosphorus atoms, blue). See also Figure S1. (B) Normalized density map of the GRP1 PH domain (zz component of rotational matrix versus distance). (C) Normalized average number of contacts between the GRP1 PH domain protein and PIPs shown for the 25 × 1 μs CG-MD simulations and for the 2 × 1 μs AT-MD simulations (see also Figure S1). The light blue colors represent the experimental contacts observed in the crystal structure. For normalization, the number of contacts of a residue with a lipid type was divided by the largest number of contacts that the same lipid type made with any residue in the protein. This means that the residue with the most frequent contacts will have the value of 1 and the residue with no contacts with a lipid type will have the value of 0. The position of the β1 and β2 strands is shown by blue and green arrows, respectively. Contacts were defined using cut-off distances of 0.7 and 0.4 nm, respectively for CG-MD and AT-MD simulations. The same analysis for the atomistic simulations of the PLC-δ1 PH and the β-spectrin PH domains is shown in Figure S2.

Figure 2

Normalized Density Maps for the 12 PH Domains, Other Than that of GRP1 For the density map of GRP1, see Figure 1C. The normalized density maps are shown as the zz component of the rotational matrix versus the z component of the distance between centers of mass of the protein and the bilayer. See also Figure S3 for convergence analysis and Figure S1 for the analysis of the orientation of the mutated form of the DAPP1 PH domain relative to the bilayer.

Figure 3

PH/PIP Complexes Alignment of the PH/PIP complexes derived from our simulation approach (with PH domains in yellow and PIP molecules in cyan/red/bronze/silver) with the corresponding crystal structures (PH domains and PIP both in blue). Note that PIPs in the simulation snapshots are located at approximately the same sites on the PH domains as in the crystal structures. These complexes were obtained from the maxima in the density maps shown in Figure 2. See also Figure S7.

Figure 4

Normalized Average Number of Contacts between the PH Domains and PIPs Contacts were calculated using the whole ensemble (25 × 1 μs CG-MD simulations). For normalization, the number of contacts of a residue with a lipid type was divided by the largest number of contacts that the same lipid type made with any residue in the PH domain. The positions of the β1 to β6 stands are shown by blue, green, black, purple, orange, and pink arrows, respectively. See also Figures S5 and S6.

Figure 5

Binding of PIP Molecules to Both Canonical and Non-canonical Sites on the ASAP1 PH Domain (A–C) A simulation snapshot and the crystal structure are compared in (A) (the same format as in Figure 3 for other PH domains). (B) A snapshot of the PH/PIP₂ complex derived from our CG simulations and then converted to an atomistic model, with the PH domain in yellow and the two bound PIP₂ molecules (in cyan/red/bronze). (C) The crystal structure (PDB: 5C79) with the PH domain in blue and the two bound dibutyryl PIP molecules (in cyan/red/bronze/silver). See also Figure S2.

Figure 6

Conservation of the Interactions with PIP Lipids (A–C) Sequence alignment of the PH domains used in this study (A). Red indicates a high number of contacts, whereas white indicate no contacts. Structures of the GRP1 PH domain color-coded based on the number of contact with PIP₂ (B) or PIP₃ (C) (both averaged over 25 × 1 μs CG-MD simulations of the GRP1). Blue indicates no contacts, and red a high number of contacts. See also Figure S6.