Identification of secondary structure elements in intermediate-resolution density maps

Abstract

An increasing number of structural studies of large macromolecular complexes, both in X-ray crystallography and cryo-electron microscopy, have resulted in intermediate-resolution (5-10 A) density maps. Despite being limited in resolution, significant structural and functional information may be extractable from these maps. To aid in the analysis and annotation of these complexes, we have developed SSEhunter, a tool for the quantitative detection of alpha helices and beta sheets. Based on density skeletonization, local geometry calculations, and a template-based search, SSEhunter has been tested and validated on a variety of simulated and authentic subnanometer-resolution density maps. The result is a robust, user-friendly approach that allows users to quickly visualize, assess, and annotate intermediate-resolution density maps. Beyond secondary structure element identification, the skeletonization algorithm in SSEhunter provides secondary structure topology, which is potentially useful in leading to structural models of individual molecular components directly from the density.

Figure 1

Flowchart for identification of secondary structure elements in SSEhunter. Three independent scoring algorithms, correlation with a prototypical α-helix (yellow density), pseudoatom geometry (orange spheres) and density skeletonization (red density), are combined to form a composite SSEhunter score which can be mapped back to individual pseudoatoms (blue to red spheres). Based on this score, a user can then annotate the secondary structure elements using SSEbuilder (cyan and green polygons).

Figure 2

Data representation in SSEhunter. During the identification of secondary structure elements, pseudoatoms are first generated to approximate the density distribution of the density map. The pseudoatom representation for the 8Å resolution simulated density map of 2BTV VP7 is shown in (A). These pseudoatoms are subsequently scored using several metrics based on their local environment. As examples, a pseudoatom in an α-helix (green, α) and its two closest neighboring pseudoatoms form nearly a straight line, while β-sheets contains multiple pseudoatoms with similar distances to each other (cyan, β). Skeletonization of the density then occurs and is shown in (B). The results of cross-correlation with a prototypical α-helix are shown in (C). Finally, the scores from skeletonization, cross-correlation and local geometry predicates are mapped back to individual pseudoatoms and colored based on their propensity to be α-helical (red) or β-sheet (blue) (D). The final annotation of VP7 is shown in (E), where α-helices are represented as green cylinders and β-sheets are shown as cyan planes.

Figure 3

Secondary structure element identification on simulated density maps at 8 Å resolution. Four model structures, bacteriorhodopsin (A, pdb id: 1C3W), triose phosphate isomerase (B, pdb id: 1TIM), insulin receptor tyrosine kinase domain (C, 1IRK) and a trimer of bluetongue virus capsid protein VP7 (D, 2BTV), were used for validation. Column 1 shows a ribbon diagram for each of the structures, while column 2 shows the 8Å resolution simulated density maps. In column 3, the results of secondary structure identification are shown, represented by green α-helices and cyan β-sheets. Comparison of the X-ray structure and identified secondary structure elements are shown in column 4. Deviations from the real structure are colored in red. Only one monomer of the 2BTV trimer was analyzed.

Figure 4

Resolution assessment of simulated data. Structural analysis of the four simulated test structures was carried out at 6, 8 and 10Å resolution. Shown in (A) is a monomer from 2BTV; (B) and (C) show simulated density at 6 and 10Å resolution with their resulting secondary structures determined by SSEhunter, respectively. Figure 2 contains the 8Å resolution data. Similar results were obtained with the other three structures at the equivalent resolutions.

Figure 5

Secondary structure element identification on authentic cryoEM density maps. The 6.8Å resolution RDV (EMDB ID: 1060) capsid proteins, P8 and P3, are shown in columns (A) and (B). The upper domain of a hexon subunit, containing both VP5 and VP26, from the 8Å resolution HSV-1 cryoEM density map is shown in column (C). A Gp5 monomer from the 9.5Å resolution structure of the P22 phage (EMDB ID: 1101) is shown in column (D). The results of SSEhunter (row 2) on the corresponding density maps (row 1) are shown where α-helices are represented as green cylinders and β-sheets as cyan polygons. The X-ray structures, fit to the cryoEM density using FOLDHUNTER, are shown superimposed on the SSEhunter results in row 3 (PDB IDs: 1UF2, 1NO7 and 1OHG). Discrepancies in identification are colored in red. In HSV-1 VP5, only the upper domain is shown as only this region has a corresponding high-resolution structure. No x-ray structure for GP5 of P22 is known, however the structural homolog, Gp5 from HK97, is shown in row 3, column (D).

Figure 6

SSEhunter skeleton from segmented cryoEM density of RDV P8. The segmented cryoEM density is shown in grey with the skeleton in red (A). In (B), a zoomed in view of portion of the lower domain of P8 is shown with the X-ray structure (1UF2, ribbon) superimposed on the density map and skeleton, illustrating the ability of the skeleton to approximate the polypeptide chain. While the skeleton does approximate the overall path of the polypeptide chain, the exact path in the skeleton is ambiguous in certain regions containing branches and breaks corresponding to the density features.