Flexible Backbone Assembly and Refinement of Symmetrical Homomeric Complexes

Abstract

Symmetrical homomeric proteins are ubiquitous in every domain of life, and information about their structure is essential to decipher function. The size of these complexes often makes them intractable to high-resolution structure determination experiments. Computational docking algorithms offer a promising alternative for modeling large complexes with arbitrary symmetry. Accuracy of existing algorithms, however, is limited by backbone inaccuracies when using homology-modeled monomers. Here, we present Rosetta SymDock2 with a broad search of symmetrical conformational space using a six-dimensional coarse-grained score function followed by an all-atom flexible-backbone refinement, which we demonstrate to be essential for physically realistic modeling of tightly packed complexes. In global docking of a benchmark set of complexes of different point symmetries-starting from homology-modeled monomers-we successfully dock (defined as predicting three near-native structures in the five top-scoring models) 17 out of 31 cyclic complexes and 3 out of 12 dihedral complexes.

Keywords: Rosetta; protein docking; symmetry.

Figure 1.. Comparison of energy landscapes in all-atom phase and coarse-grained phase.

Score versus RMSD_Cα plots for two representative complexes, Rhamnulose-1-phosphate aldolase (A, B and C) and snRNP Sm-like protein (C, D and E) for 5,000 models generated from global docking of homology-modeled monomers (black, grey circles) and 100 models generated by re-docking of bound subunits (triangles). Coarse-grained energy landscapes with Motif Dock Score (MDS) (C and F) resemble the all-atom energy landscapes (A and D), but those with Centroid Score (B and E) do not. Starting from the homology-modeled monomers, none of the 50 top-scoring models generated using Centroid Score are within 5 Å RMSD_Cα. All the 100 topscoring models generated using MDS are under 3 Å RMSD_Cα. When re-docking bound subunits, closest models generated using Centroid Score (B and E) have 1.9 Å RMSD_Cα and high relative scores in both cases. Bound re-docking with MDS (C and F) produces over 80% of the models docked to within 1 Å RMSD_Cα in both cases. These sub-angstrom re-docked models also score more favorably than all docking models made using homology-modeled monomers. Hence, Centroid Score does not recognize the energy well near the native conformation, whereas MDS does.

Figure 2.. Fixed-backbone refinement is insufficient to enter narrow binding funnel.

(A) Coarse-grained score versus RMSD_Cα (after coarse-grained phase) plots for Xenopus Nucleophosmin for 5,000 models. Models are colored by their interface score after fixed-backbone refinement. Almost all models under 5 Å RMSD_Cα have a positive interface after fixed-backbone refinement arising from minor clashes due to the introduction of side chains, despite repacking. Consequently, these models are discarded. (B) Interface score versus RMSD_Cα (after full-protocol) plots for Xenopus Nucleophosmin. A rapid drop in interface score between 0.6 and 0.4 Å RMSD_Cα leads to an energy funnel with steep slope (dashed line) of 423 Å⁻¹ and a radius of 0.25 Å. (C) Conceptual representation of the energy landscape near the binding funnel for heterodimers. The funnel is comparatively shallow with local minima near it. (D) Conceptual representation of the energy landscape near the binding funnel for homodimers as seen by symmetrical docking protocols. The funnel is narrow and steep with no comparable local minima.

Figure 3.. Flexible-backbone refinement improves docking performance.

Comparison of bootstrapped averages of the number of near-native structures in the set of 2,500 docking models using: [white] the homology models (HM) and fixed-backbone refinement, [light grey] homology models supplemented with an ensemble of 150 pregenerated backbone conformations (HM+Ens) and [dark grey] fixed-backbone refinement, and the homology models and flexible-backbone refinement after the coarse-grained phase (A) and after the full protocol (B). Starting with 150 additional backbone conformations generated without the context of the complex improves docking performance for 6 out of 8 complexes, but makes it worse for 1 complex. Starting with just the homology models and performing flexible-backbone refinement leads to improvements in 7 out of 8 complexes after the coarse-grained phase and after the full protocol. After flexible-backbone refinement, more than 75% of the top-scoring models were near-native for 6 out of the 8 complexes.

Figure 4.. Rosetta SymDock2 compares favorably with Rosetta SymDock on various assessment metrics.

Comparison of bootstrapped-averaged metrics for 43 individual complexes (31 cyclic complexes [triangle] and 12 dihedral complexes [diamond]) both after the coarse-grained phase (A and B) and after the full protocol (C) shows significant performance gains. All complexes (points) above the diagonal line are improved in SymDock2. (A) Comparison of fold-enrichment of near-native models in the 1% top-scoring models, 〈E_1%〉 on a log-log scale shows a higher enrichment in 15 cyclics and 4 dihedrals and a lower value in 5 cyclics and 0 dihedrals. Complexes to the right of the vertical dashed line are enriched in SymDock, and complexes above the horizontal dashed line are enriched in SymDock2. (B and C) Comparison of number of near-native models in the five top-scoring models, 〈N5〉, shows marked improvements both after the coarse-grained phase (B) and after the full protocol (C). Areas above and below the dashed lines indicate cases where the two methods differ significantly, i.e. by more than 1 model on average. SymDock2 has significant improvements in 13 cyclics and 1 dihedral complex after the coarse-grained phase, and most importantly, in 15 cyclics and 4 dihedrals after the full protocol. 2 cyclic complexes were modeled significantly worse with SymDock2.

Figure 5.. On average, Rosetta SymDock and SymDock2 have similar per-decoy runtimes in the benchmark.

Comparison of average time per decoy on a log-log plot demonstrates similar scaling with complex size and symmetry for SymDock (×) and SymDock2 (+). Despite having a slower all-atom refinement phase, no complex had a more than a 60% overhead with SymDock2. For the two methods, run times were within ± 20% for 31 out of 43 complexes.