Template-based structure modeling of protein-protein interactions

Abstract

The structure of protein-protein complexes can be constructed by using the known structure of other protein complexes as a template. The complex structure templates are generally detected either by homology-based sequence alignments or, given the structure of monomer components, by structure-based comparisons. Critical improvements have been made in recent years by utilizing interface recognition and by recombining monomer and complex template libraries. Encouraging progress has also been witnessed in genome-wide applications of template-based modeling, with modeling accuracy comparable to high-throughput experimental data. Nevertheless, bottlenecks exist due to the incompleteness of the protein-protein complex structure library and the lack of methods for distant homologous template identification and full-length complex structure refinement.

Figure 1

Two principal protocols for protein complex structure prediction. Red and blue represent sequences and structures of two individual chains. (a) Rigid-body protein-protein docking constructs protein complex structures by assembling known structures of monomer components which are usually solved (or modeled) in their unbound states. The final model is selected from those with the best shape complementarity, desolvation free energy and electrostatic matches between interfaces of the component structures [–12]. (b) Template-based modeling (TBM) identifies complex structure templates by aligning the amino acid sequences of the target chains with the solved complex structures in the PDB library (shown on the left). The alignment can be generated based on sequence, sequence profile, or a combination of the sequence and structure feature information. The best template of the highest alignment score is selected; and the structure framework in the aligned regions is copied from the template protein which serves as a basis for constructing the structure model of the target [,,–25]. Note that (b) only shows a typical protocol of homology-based template detection. There are variants of TBM which detect complex templates by query and template structure comparisons (see Figure 2) [–,–23,30].

Figure 2

Flowcharts for the three representative template-based complex structure prediction strategies. (a) Dimeric threading method. The black lines outline a threading procedure, similar to MULTIPROSPECTOR [24], which identifies complex templates from a dimer template library by dimeric query-to-template alignments. Blue lines indicate additional steps that improve upon the base method by utilizing a monomer template library and structural superposition, similar to COTH [18•]. Parts in magenta indicate stages where interface evaluation is used to increase alignment accuracy, ranking, and specificity. (b) Monomer threading and oligomer mapping. The protocol was used in SPRING [21••] where a combined template library containing both monomer and oligomer proteins is used. Monomeric threading is first used to identify a list of templates for each monomer chain where some templates will be parts of oligomers. The complex models are constructed by mapping the top templates of each monomer onto the framework excised from the associated oligomers, and ranked by monomer threading and interface matching scores. (c) Template-based docking. In this protocol, full-length models or experimental structures of the monomer proteins are matched against the dimer template library based on either global fold or interface structure comparisons. Dimer templates are selected from the complexes which have both components structurally similar to monomer structure of the target chains. A similar protocol is used in PrePPI [20••], PRISM [23] and the approach by Vakser et al [19•,22•].

Figure 3

Tertiary structure models from monomer threading were used to improve the model accuracy of dimeric threading models by structural superposition in COTH [18•]. Red cartoons represent experimental structures and blue ones are predicted models from monomer and dimeric threading, with sticks highlighting the interface residues. (a) A homodimer example from the 1-aminocyclopropane-1-carboxylate deaminase (PDB ID: 1f2d), which has the TM-score increased from 0.696 to 0.884 after the structural superposition of the monomer threading models on the dimer threading framework. The interface RMSD (iRMSD) is reduced from 6.01 Å to 4.43 Å with the alignment coverage of interface residues (iCoverage) increasing from 84.1% to 89.5%. (b) A heterodimer example from GTP-Bound Rab4Q67L GTPase (PDB ID: 1zok), where TM-score, iRMSD and iCoverage are improved, after the structure superposition, from 0.786, 2.79 Å, 72.8% to 0.906, 2.27 Å and 94.2%, respectively.