Structural prediction of protein interactions and docking using conservation and coevolution

From interaction networks to interfaces, scanning intrinsically disordered regions using AlphaFold2

The revolution brought about by AlphaFold2 opens promising perspectives to unravel the complexity of protein-protein interaction networks. The analysis of interaction networks obtained from proteomics experiments does not systematically provide the delimitations of the interaction regions. This is of particular concern in the case of interactions mediated by intrinsically disordered regions, in which the interaction site is generally small. Using a dataset of protein-peptide complexes involving intrinsically disordered regions that are non-redundant with the structures used in AlphaFold2 training, we show that when using the full sequences of the proteins, AlphaFold2-Multimer only achieves 40% success rate in identifying the correct site and structure of the interface. By delineating the interaction region into fragments of decreasing size and combining different strategies for integrating evolutionary information, we manage to raise this success rate up to 90%. We obtain similar success rates using a much larger dataset of protein complexes taken from the ELM database. Beyond the correct identification of the interaction site, our study also explores specificity issues. We show the advantages and limitations of using the AlphaFold2 confidence score to discriminate between alternative binding partners, a task that can be particularly challenging in the case of small interaction motifs.

A Perspective on the Prospective Use of AI in Protein Structure Prediction

AlphaFold2 (AF2) and RoseTTaFold (RF) have revolutionized structural biology, serving as highly reliable and effective methods for predicting protein structures. This article explores their impact and limitations, focusing on their integration into experimental pipelines and their application in diverse protein classes, including membrane proteins, intrinsically disordered proteins (IDPs), and oligomers. In experimental pipelines, AF2 models help X-ray crystallography in resolving the phase problem, while complementarity with mass spectrometry and NMR data enhances structure determination and protein flexibility prediction. Predicting the structure of membrane proteins remains challenging for both AF2 and RF due to difficulties in capturing conformational ensembles and interactions with the membrane. Improvements in incorporating membrane-specific features and predicting the structural effect of mutations are crucial. For intrinsically disordered proteins, AF2's confidence score (pLDDT) serves as a competitive disorder predictor, but integrative approaches including molecular dynamics (MD) simulations or hydrophobic cluster analyses are advocated for accurate dynamics representation. AF2 and RF show promising results for oligomeric models, outperforming traditional docking methods, with AlphaFold-Multimer showing improved performance. However, some caveats remain in particular for membrane proteins. Real-life examples demonstrate AF2's predictive capabilities in unknown protein structures, but models should be evaluated for their agreement with experimental data. Furthermore, AF2 models can be used complementarily with MD simulations. In this Perspective, we propose a "wish list" for improving deep-learning-based protein folding prediction models, including using experimental data as constraints and modifying models with binding partners or post-translational modifications. Additionally, a meta-tool for ranking and suggesting composite models is suggested, driving future advancements in this rapidly evolving field.

The impact of AI-based modeling on the accuracy of protein assembly prediction: Insights from CASP15

In CASP15, 87 predictors submitted around 11 000 models on 41 assembly targets. The community demonstrated exceptional performance in overall fold and interface contact predictions, achieving an impressive success rate of 90% (compared to 31% in CASP14). This remarkable accomplishment is largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines. To evaluate the added value of participating methods, we compared the community models to the baseline AF2-Multimer predictor. In over 1/3 of cases, the community models were superior to the baseline predictor. The main reasons for this improved performance were the use of custom-built multiple sequence alignments, optimized AF2-Multimer sampling, and the manual assembly of AF2-Multimer-built subcomplexes. The best three groups, in order, are Zheng, Venclovas, and Wallner. Zheng and Venclovas reached a 73.2% success rate over all (41) cases, while Wallner attained 69.4% success rate over 36 cases. Nonetheless, challenges remain in predicting structures with weak evolutionary signals, such as nanobody-antigen, antibody-antigen, and viral complexes. Expectedly, modeling large complexes also remains challenging due to their high memory compute demands. In addition to the assembly category, we assessed the accuracy of modeling interdomain interfaces in the tertiary structure prediction targets. Models on seven targets featuring 17 unique interfaces were analyzed. Best predictors achieved a 76.5% success rate, with the UM-TBM group being the leader. In the interdomain category, we observed that the predictors faced challenges, as in the case of the assembly category, when the evolutionary signal for a given domain pair was weak or the structure was large. Overall, CASP15 witnessed unprecedented improvement in interface modeling, reflecting the AI revolution seen in CASP14.

The Impact of AI-Based Modeling on the Accuracy of Protein Assembly Prediction: Insights from CASP15

In CASP15, 87 predictors submitted around 11,000 models on 41 assembly targets. The community demonstrated exceptional performance in overall fold and interface contact prediction, achieving an impressive success rate of 90% (compared to 31% in CASP14). This remarkable accomplishment is largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines. To evaluate the added value of participating methods, we compared the community models to the baseline AF2-Multimer predictor. In over 1/3 of cases the community models were superior to the baseline predictor. The main reasons for this improved performance were the use of custom-built multiple sequence alignments, optimized AF2-Multimer sampling, and the manual assembly of AF2-Multimer-built subcomplexes. The best three groups, in order, are Zheng, Venclovas and Wallner. Zheng and Venclovas reached a 73.2% success rate over all (41) cases, while Wallner attained 69.4% success rate over 36 cases. Nonetheless, challenges remain in predicting structures with weak evolutionary signals, such as nanobody-antigen, antibody-antigen, and viral complexes. Expectedly, modeling large complexes remains also challenging due to their high memory compute demands. In addition to the assembly category, we assessed the accuracy of modeling interdomain interfaces in the tertiary structure prediction targets. Models on seven targets featuring 17 unique interfaces were analyzed. Best predictors achieved the 76.5% success rate, with the UM-TBM group being the leader. In the interdomain category, we observed that the predictors faced challenges, as in the case of the assembly category, when the evolutionary signal for a given domain pair was weak or the structure was large. Overall, CASP15 witnessed unprecedented improvement in interface modeling, reflecting the AI revolution seen in CASP14.

In Silico Selection and Validation of High-Affinity ssDNA Aptamers Targeting Paromomycin

Glycans are promising for disease diagnosis since glycan biosynthesis is significantly affected by disease states, and glycosylation changes are probably more pronounced than protein expression during the transformation to the diseased condition. Glycan-specific aptamers can be developed for challenging applications such as cancer targeting; however, the high flexibility of glycosidic bonds and scarcity of studies on glycan-aptamer binding mechanisms increased the difficulty of screening. In this work, the model of interactions between glycans and ssDNA aptamers synthesized based on the sequence of rRNA genes was developed. Our simulation-based approach revealed that paromomycin as a representative example of glycans is preferred to bind base-restricted stem structures of aptamers because they are more critical in stabilizing the flexible structures of glycans. Combined experiments and simulations have identified two optimal mutant aptamers. Our work would provide a potential strategy that the glycan-binding rRNA genes could act as the initial aptamer pools to accelerate aptamer screening. In addition, this in silico workflow would be potentially applied in the more extensive in vitro development and application of RNA-templated ssDNA aptamers targeting glycans.

Scoring of protein–protein docking models utilizing predicted interface residues

Scoring docking solutions is a difficult task, and many methods have been developed for this purpose. In docking, only a handful of the hundreds of thousands of models generated by docking algorithms are acceptable, causing difficulties when developing scoring functions. Today's best scoring functions can significantly increase the number of top‐ranked models but still fail for most targets. Here, we examine the possibility of utilizing predicted interface residues to score docking models generated during the scan stage of a docking algorithm. Many methods have been developed to infer the regions of a protein surface that interact with another protein, but most have not been benchmarked using docking algorithms. This study systematically tests different interface prediction methods for scoring >300.000 low‐resolution rigid‐body template free docking decoys. Overall we find that contact‐based interface prediction by BIPSPI is the best method to score docking solutions, with >12% of first ranked docking models being acceptable. Additional experiments indicated precision as a high‐importance metric when estimating interface prediction quality, focusing on docking constraints production. Finally, we discussed several limitations for adopting interface predictions as constraints in a docking protocol.

QSalignWeb: A Server to Predict and Analyze Protein Quaternary Structure

The identification of physiologically relevant quaternary structures (QSs) in crystal lattices is challenging. To predict the physiological relevance of a particular QS, QSalign searches for homologous structures in which subunits interact in the same geometry. This approach proved accurate but was limited to structures already present in the Protein Data Bank (PDB). Here, we introduce a webserver (www.QSalign.org) allowing users to submit homo-oligomeric structures of their choice to the QSalign pipeline. Given a user-uploaded structure, the sequence is extracted and used to search homologs based on sequence similarity and PFAM domain architecture. If structural conservation is detected between a homolog and the user-uploaded QS, physiological relevance is inferred. The web server also generates alternative QSs with PISA and processes them the same way as the query submitted to widen the predictions. The result page also shows representative QSs in the protein family of the query, which is informative if no QS conservation was detected or if the protein appears monomeric. These representative QSs can also serve as a starting point for homology modeling.

Evolution of a cytoplasmic determinant: evidence for the biochemical basis of functional evolution of the novel germ line regulator oskar

Germ line specification is essential in sexually reproducing organisms. Despite their critical role, the evolutionary history of the genes that specify animal germ cells is heterogeneous and dynamic. In many insects, the gene oskar is required for the specification of the germ line. However, the germ line role of oskar is thought to be a derived role resulting from co-option from an ancestral somatic role. To address how evolutionary changes in protein sequence could have led to changes in the function of Oskar protein that enabled it to regulate germ line specification, we searched for oskar orthologs in 1,565 publicly available insect genomic and transcriptomic data sets. The earliest-diverging lineage in which we identified an oskar ortholog was the order Zygentoma (silverfish and firebrats), suggesting that oskar originated before the origin of winged insects. We noted some order-specific trends in oskar sequence evolution, including whole gene duplications, clade-specific losses, and rapid divergence. An alignment of all known 379 Oskar sequences revealed new highly conserved residues as candidates that promote dimerization of the LOTUS domain. Moreover, we identified regions of the OSK domain with conserved predicted RNA binding potential. Furthermore, we show that despite a low overall amino acid conservation, the LOTUS domain shows higher conservation of predicted secondary structure than the OSK domain. Finally, we suggest new key amino acids in the LOTUS domain that may be involved in the previously reported Oskar−Vasa physical interaction that is required for its germ line role.

InterEvDock3: a combined template-based and free docking server with increased performance through explicit modeling of complex homologs and integration of covariation-based contact maps

The InterEvDock3 protein docking server exploits the constraints of evolution by multiple means to generate structural models of protein assemblies. The server takes as input either several sequences or 3D structures of proteins known to interact. It returns a set of 10 consensus candidate complexes, together with interface predictions to guide further experimental validation interactively. Three key novelties were implemented in InterEvDock3 to help obtain more reliable models: users can (i) generate template-based structural models of assemblies using close and remote homologs of known 3D structure, detected through an automated search protocol, (ii) select the assembly models most consistent with contact maps from external methods that implement covariation-based contact prediction with or without deep learning and (iii) exploit a novel coevolution-based scoring scheme at atomic level, which leads to significantly higher free docking success rates. The performance of the server was validated on two large free docking benchmark databases, containing respectively 230 unbound targets (Weng dataset) and 812 models of unbound targets (PPI4DOCK dataset). Its effectiveness has also been proven on a number of challenging examples. The InterEvDock3 web interface is available at http://bioserv.rpbs.univ-paris-diderot.fr/services/InterEvDock3/.

Atomic-level evolutionary information improves protein-protein interface scoring

MOTIVATION

The crucial role of protein interactions and the difficulty in characterising them experimentally strongly motivates the development of computational approaches for structural prediction. Even when protein-protein docking samples correct models, current scoring functions struggle to discriminate them from incorrect decoys. The previous incorporation of conservation and coevolution information has shown promise for improving protein-protein scoring. Here, we present a novel strategy to integrate atomic-level evolutionary information into different types of scoring functions to improve their docking discrimination.

RESULTS

: We applied this general strategy to our residue-level statistical potential from InterEvScore and to two atomic-level scores, SOAP-PP and Rosetta interface score (ISC). Including evolutionary information from as few as ten homologous sequences improves the top 10 success rates of individual atomic-level scores SOAP-PP and Rosetta ISC by respectively 6 and 13.5 percentage points, on a large benchmark of 752 docking cases. The best individual homology-enriched score reaches a top 10 success rate of 34.4%. A consensus approach based on the complementarity between different homology-enriched scores further increases the top 10 success rate to 40%.

AVAILABILITY

All data used for benchmarking and scoring results, as well as a Singularity container of the pipeline, are available at http://biodev.cea.fr/interevol/interevdata/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.